Text Generation
Transformers
Safetensors
mixtral
Mixture of Experts
reasoning
text-generation-inference
Instructions to use llm-jp/optimal-sparsity-math-d1024-E32-k8-3.5B-A1.1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use llm-jp/optimal-sparsity-math-d1024-E32-k8-3.5B-A1.1B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="llm-jp/optimal-sparsity-math-d1024-E32-k8-3.5B-A1.1B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("llm-jp/optimal-sparsity-math-d1024-E32-k8-3.5B-A1.1B") model = AutoModelForCausalLM.from_pretrained("llm-jp/optimal-sparsity-math-d1024-E32-k8-3.5B-A1.1B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use llm-jp/optimal-sparsity-math-d1024-E32-k8-3.5B-A1.1B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "llm-jp/optimal-sparsity-math-d1024-E32-k8-3.5B-A1.1B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "llm-jp/optimal-sparsity-math-d1024-E32-k8-3.5B-A1.1B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/llm-jp/optimal-sparsity-math-d1024-E32-k8-3.5B-A1.1B
- SGLang
How to use llm-jp/optimal-sparsity-math-d1024-E32-k8-3.5B-A1.1B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "llm-jp/optimal-sparsity-math-d1024-E32-k8-3.5B-A1.1B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "llm-jp/optimal-sparsity-math-d1024-E32-k8-3.5B-A1.1B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "llm-jp/optimal-sparsity-math-d1024-E32-k8-3.5B-A1.1B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "llm-jp/optimal-sparsity-math-d1024-E32-k8-3.5B-A1.1B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use llm-jp/optimal-sparsity-math-d1024-E32-k8-3.5B-A1.1B with Docker Model Runner:
docker model run hf.co/llm-jp/optimal-sparsity-math-d1024-E32-k8-3.5B-A1.1B
| { | |
| "metadata": { | |
| "total_size": 6985680896 | |
| }, | |
| "weight_map": { | |
| "model.embed_tokens.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.27.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.28.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.28.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.29.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.29.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.30.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.30.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.31.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.31.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.8.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.9.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.10.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.11.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.12.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.13.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.14.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.15.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.16.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.17.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.18.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.19.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.20.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.21.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.22.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.23.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.24.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.25.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.26.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.27.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.28.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.29.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.30.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.block_sparse_moe.experts.31.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.8.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.8.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.9.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.9.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.10.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.10.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.11.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.11.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.12.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.12.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.13.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.13.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.14.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.14.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.15.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.15.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.16.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.16.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.17.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.17.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.18.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.18.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.19.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.19.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.20.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.20.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.21.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.21.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.22.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.22.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.23.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.23.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.24.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.24.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.25.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.25.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.26.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.26.w3.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.27.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.27.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.28.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.28.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.29.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.29.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.30.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.30.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.31.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.31.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.8.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.9.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.10.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.11.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.12.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.13.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.14.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.15.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.16.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.17.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.18.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.19.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.20.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.21.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.22.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.23.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.24.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.25.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.26.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.27.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.28.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.29.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.30.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.11.block_sparse_moe.experts.31.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.8.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.8.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.9.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.9.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.10.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.10.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.11.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.11.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.12.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.12.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.13.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.13.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.14.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.14.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.15.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.15.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.16.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.16.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.17.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.17.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.18.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.18.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.19.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.19.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.20.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.20.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.21.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.21.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.22.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.22.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.23.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.23.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.24.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.24.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.25.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.25.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.26.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.26.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.27.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.27.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.28.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.28.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.29.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.29.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.30.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.30.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.31.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.31.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.8.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.9.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.10.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.11.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.12.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.13.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.14.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.15.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.16.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.17.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.18.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.19.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.20.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.21.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.22.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.23.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.24.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.25.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.26.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.27.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.28.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.29.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.30.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.12.block_sparse_moe.experts.31.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.8.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.8.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.9.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.9.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.10.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.10.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.11.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.11.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.12.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.12.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.13.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.13.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.14.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.14.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.15.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.15.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.16.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.16.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.17.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.17.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.18.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.18.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.19.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.19.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.20.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.20.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.21.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.21.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.22.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.22.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.23.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.23.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.24.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.24.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.25.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.25.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.26.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.26.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.27.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.27.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.28.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.28.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.29.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.29.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.30.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.30.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.31.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.31.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.8.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.9.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.10.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.11.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.12.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.13.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.14.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.15.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.16.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.17.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.18.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.19.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.20.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.21.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.22.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.23.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.24.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.25.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.26.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.27.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.28.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.29.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.30.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.13.block_sparse_moe.experts.31.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.8.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.8.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.9.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.9.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.10.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.10.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.11.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.11.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.12.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.12.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.13.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.13.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.14.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.14.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.15.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.15.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.16.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.16.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.17.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.17.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.18.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.18.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.19.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.19.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.20.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.20.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.21.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.21.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.22.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.22.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.23.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.23.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.24.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.24.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.25.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.25.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.26.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.26.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.27.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.27.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.28.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.28.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.29.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.29.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.30.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.30.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.31.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.31.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.8.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.9.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.10.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.11.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.12.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.13.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.14.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.15.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.16.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.17.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.18.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.19.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.20.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.21.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.22.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.23.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.24.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.25.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.26.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.27.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.28.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.29.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.30.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.14.block_sparse_moe.experts.31.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.8.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.8.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.9.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.9.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.10.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.10.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.11.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.11.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.12.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.12.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.13.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.13.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.14.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.14.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.15.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.15.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.16.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.16.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.17.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.17.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.18.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.18.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.19.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.19.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.20.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.20.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.21.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.21.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.22.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.22.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.23.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.23.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.24.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.24.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.25.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.25.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.26.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.26.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.27.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.27.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.28.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.28.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.29.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.29.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.30.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.30.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.31.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.31.w3.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.8.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.9.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.10.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.11.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.12.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.13.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.14.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.15.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.16.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.17.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.18.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.19.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.20.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.21.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.22.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.23.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.24.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.25.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.26.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.27.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.28.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.29.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.30.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.15.block_sparse_moe.experts.31.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.norm.weight": "model-00002-of-00002.safetensors", | |
| "lm_head.weight": "model-00002-of-00002.safetensors" | |
| } | |
| } |