Text Generation
Transformers
Safetensors
English
zamba2
mamba
hybrid
compressed
hxq
helix-substrate
vector-quantization
helixcode
conversational
Instructions to use EchoLabs33/zamba2-7b-instruct-hxq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use EchoLabs33/zamba2-7b-instruct-hxq with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="EchoLabs33/zamba2-7b-instruct-hxq") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("EchoLabs33/zamba2-7b-instruct-hxq") model = AutoModelForCausalLM.from_pretrained("EchoLabs33/zamba2-7b-instruct-hxq", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use EchoLabs33/zamba2-7b-instruct-hxq with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "EchoLabs33/zamba2-7b-instruct-hxq" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "EchoLabs33/zamba2-7b-instruct-hxq", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/EchoLabs33/zamba2-7b-instruct-hxq
- SGLang
How to use EchoLabs33/zamba2-7b-instruct-hxq 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 "EchoLabs33/zamba2-7b-instruct-hxq" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "EchoLabs33/zamba2-7b-instruct-hxq", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "EchoLabs33/zamba2-7b-instruct-hxq" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "EchoLabs33/zamba2-7b-instruct-hxq", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use EchoLabs33/zamba2-7b-instruct-hxq with Docker Model Runner:
docker model run hf.co/EchoLabs33/zamba2-7b-instruct-hxq
| { | |
| "verdict": "PASS", | |
| "summary": { | |
| "dense_tensors": 1597, | |
| "output_tensors": 2236, | |
| "compressed_weights": 213, | |
| "accounted": 1597, | |
| "missing": 0, | |
| "skip_tensors_found": 979, | |
| "skip_categories": { | |
| "bias": "OK (162/162)", | |
| "embedding": "OK (1/1)", | |
| "layernorm": "OK (329/329)", | |
| "output_head": "OK (1/1)", | |
| "ssm_param": "OK (486/486)" | |
| } | |
| }, | |
| "failures": [], | |
| "missing_tensors": [], | |
| "skip_found": { | |
| "output_head": [ | |
| "lm_head.weight" | |
| ], | |
| "layernorm": [ | |
| "model.blocks.0.input_layernorm.weight", | |
| "model.blocks.1.input_layernorm.weight", | |
| "model.final_layernorm.weight", | |
| "model.layers.0.input_layernorm.weight", | |
| "model.layers.0.mamba.norm.weight", | |
| "model.layers.1.input_layernorm.weight", | |
| "model.layers.1.mamba.norm.weight", | |
| "model.layers.10.input_layernorm.weight", | |
| "model.layers.10.mamba.norm.weight", | |
| "model.layers.11.mamba_decoder.input_layernorm.weight", | |
| "model.layers.11.mamba_decoder.mamba.norm.weight", | |
| "model.layers.11.shared_transformer.input_layernorm.weight", | |
| "model.layers.12.input_layernorm.weight", | |
| "model.layers.12.mamba.norm.weight", | |
| "model.layers.13.input_layernorm.weight", | |
| "model.layers.13.mamba.norm.weight", | |
| "model.layers.14.input_layernorm.weight", | |
| "model.layers.14.mamba.norm.weight", | |
| "model.layers.15.input_layernorm.weight", | |
| "model.layers.15.mamba.norm.weight", | |
| "model.layers.16.input_layernorm.weight", | |
| "model.layers.16.mamba.norm.weight", | |
| "model.layers.17.mamba_decoder.input_layernorm.weight", | |
| "model.layers.17.mamba_decoder.mamba.norm.weight", | |
| "model.layers.18.input_layernorm.weight", | |
| "model.layers.18.mamba.norm.weight", | |
| "model.layers.19.input_layernorm.weight", | |
| "model.layers.19.mamba.norm.weight", | |
| "model.layers.2.input_layernorm.weight", | |
| "model.layers.2.mamba.norm.weight", | |
| "model.layers.20.input_layernorm.weight", | |
| "model.layers.20.mamba.norm.weight", | |
| "model.layers.21.input_layernorm.weight", | |
| "model.layers.21.mamba.norm.weight", | |
| "model.layers.22.input_layernorm.weight", | |
| "model.layers.22.mamba.norm.weight", | |
| "model.layers.23.mamba_decoder.input_layernorm.weight", | |
| "model.layers.23.mamba_decoder.mamba.norm.weight", | |
| "model.layers.24.input_layernorm.weight", | |
| "model.layers.24.mamba.norm.weight", | |
| "model.layers.25.input_layernorm.weight", | |
| "model.layers.25.mamba.norm.weight", | |
| "model.layers.26.input_layernorm.weight", | |
| "model.layers.26.mamba.norm.weight", | |
| "model.layers.27.input_layernorm.weight", | |
| "model.layers.27.mamba.norm.weight", | |
| "model.layers.28.input_layernorm.weight", | |
| "model.layers.28.mamba.norm.weight", | |
| "model.layers.29.mamba_decoder.input_layernorm.weight", | |
| "model.layers.29.mamba_decoder.mamba.norm.weight", | |
| "model.layers.3.input_layernorm.weight", | |
| "model.layers.3.mamba.norm.weight", | |
| "model.layers.30.input_layernorm.weight", | |
| "model.layers.30.mamba.norm.weight", | |
| "model.layers.31.input_layernorm.weight", | |
| "model.layers.31.mamba.norm.weight", | |
| "model.layers.32.input_layernorm.weight", | |
| "model.layers.32.mamba.norm.weight", | |
| "model.layers.33.input_layernorm.weight", | |
| "model.layers.33.mamba.norm.weight", | |
| "model.layers.34.input_layernorm.weight", | |
| "model.layers.34.mamba.norm.weight", | |
| "model.layers.35.mamba_decoder.input_layernorm.weight", | |
| "model.layers.35.mamba_decoder.mamba.norm.weight", | |
| "model.layers.36.input_layernorm.weight", | |
| "model.layers.36.mamba.norm.weight", | |
| "model.layers.37.input_layernorm.weight", | |
| "model.layers.37.mamba.norm.weight", | |
| "model.layers.38.input_layernorm.weight", | |
| "model.layers.38.mamba.norm.weight", | |
| "model.layers.39.input_layernorm.weight", | |
| "model.layers.39.mamba.norm.weight", | |
| "model.layers.4.input_layernorm.weight", | |
| "model.layers.4.mamba.norm.weight", | |
| "model.layers.40.input_layernorm.weight", | |
| "model.layers.40.mamba.norm.weight", | |
| "model.layers.41.mamba_decoder.input_layernorm.weight", | |
| "model.layers.41.mamba_decoder.mamba.norm.weight", | |
| "model.layers.42.input_layernorm.weight", | |
| "model.layers.42.mamba.norm.weight", | |
| "model.layers.43.input_layernorm.weight", | |
| "model.layers.43.mamba.norm.weight", | |
| "model.layers.44.input_layernorm.weight", | |
| "model.layers.44.mamba.norm.weight", | |
| "model.layers.45.input_layernorm.weight", | |
| "model.layers.45.mamba.norm.weight", | |
| "model.layers.46.input_layernorm.weight", | |
| "model.layers.46.mamba.norm.weight", | |
| "model.layers.47.mamba_decoder.input_layernorm.weight", | |
| "model.layers.47.mamba_decoder.mamba.norm.weight", | |
| "model.layers.48.input_layernorm.weight", | |
| "model.layers.48.mamba.norm.weight", | |
| "model.layers.49.input_layernorm.weight", | |
| "model.layers.49.mamba.norm.weight", | |
| "model.layers.5.input_layernorm.weight", | |
| "model.layers.5.mamba.norm.weight", | |
| "model.layers.50.input_layernorm.weight", | |
| "model.layers.50.mamba.norm.weight", | |
| "model.layers.51.input_layernorm.weight", | |
| "model.layers.51.mamba.norm.weight", | |
| "model.layers.52.input_layernorm.weight", | |
| "model.layers.52.mamba.norm.weight", | |
| "model.layers.53.mamba_decoder.input_layernorm.weight", | |
| "model.layers.53.mamba_decoder.mamba.norm.weight", | |
| "model.layers.54.input_layernorm.weight", | |
| "model.layers.54.mamba.norm.weight", | |
| "model.layers.55.input_layernorm.weight", | |
| "model.layers.55.mamba.norm.weight", | |
| "model.layers.56.input_layernorm.weight", | |
| "model.layers.56.mamba.norm.weight", | |
| "model.layers.57.input_layernorm.weight", | |
| "model.layers.57.mamba.norm.weight", | |
| "model.layers.58.input_layernorm.weight", | |
| "model.layers.58.mamba.norm.weight", | |
| "model.layers.59.mamba_decoder.input_layernorm.weight", | |
| "model.layers.59.mamba_decoder.mamba.norm.weight", | |
| "model.layers.6.mamba_decoder.input_layernorm.weight", | |
| "model.layers.6.mamba_decoder.mamba.norm.weight", | |
| "model.layers.6.shared_transformer.input_layernorm.weight", | |
| "model.layers.60.input_layernorm.weight", | |
| "model.layers.60.mamba.norm.weight", | |
| "model.layers.61.input_layernorm.weight", | |
| "model.layers.61.mamba.norm.weight", | |
| "model.layers.62.input_layernorm.weight", | |
| "model.layers.62.mamba.norm.weight", | |
| "model.layers.63.input_layernorm.weight", | |
| "model.layers.63.mamba.norm.weight", | |
| "model.layers.64.input_layernorm.weight", | |
| "model.layers.64.mamba.norm.weight", | |
| "model.layers.65.mamba_decoder.input_layernorm.weight", | |
| "model.layers.65.mamba_decoder.mamba.norm.weight", | |
| "model.layers.66.input_layernorm.weight", | |
| "model.layers.66.mamba.norm.weight", | |
| "model.layers.67.input_layernorm.weight", | |
| "model.layers.67.mamba.norm.weight", | |
| "model.layers.68.input_layernorm.weight", | |
| "model.layers.68.mamba.norm.weight", | |
| "model.layers.69.input_layernorm.weight", | |
| "model.layers.69.mamba.norm.weight", | |
| "model.layers.7.input_layernorm.weight", | |
| "model.layers.7.mamba.norm.weight", | |
| "model.layers.70.input_layernorm.weight", | |
| "model.layers.70.mamba.norm.weight", | |
| "model.layers.71.mamba_decoder.input_layernorm.weight", | |
| "model.layers.71.mamba_decoder.mamba.norm.weight", | |
| "model.layers.72.input_layernorm.weight", | |
| "model.layers.72.mamba.norm.weight", | |
| "model.layers.73.input_layernorm.weight", | |
| "model.layers.73.mamba.norm.weight", | |
| "model.layers.74.input_layernorm.weight", | |
| "model.layers.74.mamba.norm.weight", | |
| "model.layers.75.input_layernorm.weight", | |
| "model.layers.75.mamba.norm.weight", | |
| "model.layers.76.input_layernorm.weight", | |
| "model.layers.76.mamba.norm.weight", | |
| "model.layers.77.mamba_decoder.input_layernorm.weight", | |
| "model.layers.77.mamba_decoder.mamba.norm.weight", | |
| "model.layers.78.input_layernorm.weight", | |
| "model.layers.78.mamba.norm.weight", | |
| "model.layers.79.input_layernorm.weight", | |
| "model.layers.79.mamba.norm.weight", | |
| "model.layers.8.input_layernorm.weight", | |
| "model.layers.8.mamba.norm.weight", | |
| "model.layers.80.input_layernorm.weight", | |
| "model.layers.80.mamba.norm.weight", | |
| "model.layers.9.input_layernorm.weight", | |
| "model.layers.9.mamba.norm.weight", | |
| "model.mamba_layers.0.input_layernorm.weight", | |
| "model.mamba_layers.0.mamba.norm.weight", | |
| "model.mamba_layers.1.input_layernorm.weight", | |
| "model.mamba_layers.1.mamba.norm.weight", | |
| "model.mamba_layers.10.input_layernorm.weight", | |
| "model.mamba_layers.10.mamba.norm.weight", | |
| "model.mamba_layers.11.input_layernorm.weight", | |
| "model.mamba_layers.11.mamba.norm.weight", | |
| "model.mamba_layers.12.input_layernorm.weight", | |
| "model.mamba_layers.12.mamba.norm.weight", | |
| "model.mamba_layers.13.input_layernorm.weight", | |
| "model.mamba_layers.13.mamba.norm.weight", | |
| "model.mamba_layers.14.input_layernorm.weight", | |
| "model.mamba_layers.14.mamba.norm.weight", | |
| "model.mamba_layers.15.input_layernorm.weight", | |
| "model.mamba_layers.15.mamba.norm.weight", | |
| "model.mamba_layers.16.input_layernorm.weight", | |
| "model.mamba_layers.16.mamba.norm.weight", | |
| "model.mamba_layers.17.input_layernorm.weight", | |
| "model.mamba_layers.17.mamba.norm.weight", | |
| "model.mamba_layers.18.input_layernorm.weight", | |
| "model.mamba_layers.18.mamba.norm.weight", | |
| "model.mamba_layers.19.input_layernorm.weight", | |
| "model.mamba_layers.19.mamba.norm.weight", | |
| "model.mamba_layers.2.input_layernorm.weight", | |
| "model.mamba_layers.2.mamba.norm.weight", | |
| "model.mamba_layers.20.input_layernorm.weight", | |
| "model.mamba_layers.20.mamba.norm.weight", | |
| "model.mamba_layers.21.input_layernorm.weight", | |
| "model.mamba_layers.21.mamba.norm.weight", | |
| "model.mamba_layers.22.input_layernorm.weight", | |
| "model.mamba_layers.22.mamba.norm.weight", | |
| "model.mamba_layers.23.input_layernorm.weight", | |
| "model.mamba_layers.23.mamba.norm.weight", | |
| "model.mamba_layers.24.input_layernorm.weight", | |
| "model.mamba_layers.24.mamba.norm.weight", | |
| "model.mamba_layers.25.input_layernorm.weight", | |
| "model.mamba_layers.25.mamba.norm.weight", | |
| "model.mamba_layers.26.input_layernorm.weight", | |
| "model.mamba_layers.26.mamba.norm.weight", | |
| "model.mamba_layers.27.input_layernorm.weight", | |
| "model.mamba_layers.27.mamba.norm.weight", | |
| "model.mamba_layers.28.input_layernorm.weight", | |
| "model.mamba_layers.28.mamba.norm.weight", | |
| "model.mamba_layers.29.input_layernorm.weight", | |
| "model.mamba_layers.29.mamba.norm.weight", | |
| "model.mamba_layers.3.input_layernorm.weight", | |
| "model.mamba_layers.3.mamba.norm.weight", | |
| "model.mamba_layers.30.input_layernorm.weight", | |
| "model.mamba_layers.30.mamba.norm.weight", | |
| "model.mamba_layers.31.input_layernorm.weight", | |
| "model.mamba_layers.31.mamba.norm.weight", | |
| "model.mamba_layers.32.input_layernorm.weight", | |
| "model.mamba_layers.32.mamba.norm.weight", | |
| "model.mamba_layers.33.input_layernorm.weight", | |
| "model.mamba_layers.33.mamba.norm.weight", | |
| "model.mamba_layers.34.input_layernorm.weight", | |
| "model.mamba_layers.34.mamba.norm.weight", | |
| "model.mamba_layers.35.input_layernorm.weight", | |
| "model.mamba_layers.35.mamba.norm.weight", | |
| "model.mamba_layers.36.input_layernorm.weight", | |
| "model.mamba_layers.36.mamba.norm.weight", | |
| "model.mamba_layers.37.input_layernorm.weight", | |
| "model.mamba_layers.37.mamba.norm.weight", | |
| "model.mamba_layers.38.input_layernorm.weight", | |
| "model.mamba_layers.38.mamba.norm.weight", | |
| "model.mamba_layers.39.input_layernorm.weight", | |
| "model.mamba_layers.39.mamba.norm.weight", | |
| "model.mamba_layers.4.input_layernorm.weight", | |
| "model.mamba_layers.4.mamba.norm.weight", | |
| "model.mamba_layers.40.input_layernorm.weight", | |
| "model.mamba_layers.40.mamba.norm.weight", | |
| "model.mamba_layers.41.input_layernorm.weight", | |
| "model.mamba_layers.41.mamba.norm.weight", | |
| "model.mamba_layers.42.input_layernorm.weight", | |
| "model.mamba_layers.42.mamba.norm.weight", | |
| "model.mamba_layers.43.input_layernorm.weight", | |
| "model.mamba_layers.43.mamba.norm.weight", | |
| "model.mamba_layers.44.input_layernorm.weight", | |
| "model.mamba_layers.44.mamba.norm.weight", | |
| "model.mamba_layers.45.input_layernorm.weight", | |
| "model.mamba_layers.45.mamba.norm.weight", | |
| "model.mamba_layers.46.input_layernorm.weight", | |
| "model.mamba_layers.46.mamba.norm.weight", | |
| "model.mamba_layers.47.input_layernorm.weight", | |
| "model.mamba_layers.47.mamba.norm.weight", | |
| "model.mamba_layers.48.input_layernorm.weight", | |
| "model.mamba_layers.48.mamba.norm.weight", | |
| "model.mamba_layers.49.input_layernorm.weight", | |
| "model.mamba_layers.49.mamba.norm.weight", | |
| "model.mamba_layers.5.input_layernorm.weight", | |
| "model.mamba_layers.5.mamba.norm.weight", | |
| "model.mamba_layers.50.input_layernorm.weight", | |
| "model.mamba_layers.50.mamba.norm.weight", | |
| "model.mamba_layers.51.input_layernorm.weight", | |
| "model.mamba_layers.51.mamba.norm.weight", | |
| "model.mamba_layers.52.input_layernorm.weight", | |
| "model.mamba_layers.52.mamba.norm.weight", | |
| "model.mamba_layers.53.input_layernorm.weight", | |
| "model.mamba_layers.53.mamba.norm.weight", | |
| "model.mamba_layers.54.input_layernorm.weight", | |
| "model.mamba_layers.54.mamba.norm.weight", | |
| "model.mamba_layers.55.input_layernorm.weight", | |
| "model.mamba_layers.55.mamba.norm.weight", | |
| "model.mamba_layers.56.input_layernorm.weight", | |
| "model.mamba_layers.56.mamba.norm.weight", | |
| "model.mamba_layers.57.input_layernorm.weight", | |
| "model.mamba_layers.57.mamba.norm.weight", | |
| "model.mamba_layers.58.input_layernorm.weight", | |
| "model.mamba_layers.58.mamba.norm.weight", | |
| "model.mamba_layers.59.input_layernorm.weight", | |
| "model.mamba_layers.59.mamba.norm.weight", | |
| "model.mamba_layers.6.input_layernorm.weight", | |
| "model.mamba_layers.6.mamba.norm.weight", | |
| "model.mamba_layers.60.input_layernorm.weight", | |
| "model.mamba_layers.60.mamba.norm.weight", | |
| "model.mamba_layers.61.input_layernorm.weight", | |
| "model.mamba_layers.61.mamba.norm.weight", | |
| "model.mamba_layers.62.input_layernorm.weight", | |
| "model.mamba_layers.62.mamba.norm.weight", | |
| "model.mamba_layers.63.input_layernorm.weight", | |
| "model.mamba_layers.63.mamba.norm.weight", | |
| "model.mamba_layers.64.input_layernorm.weight", | |
| "model.mamba_layers.64.mamba.norm.weight", | |
| "model.mamba_layers.65.input_layernorm.weight", | |
| "model.mamba_layers.65.mamba.norm.weight", | |
| "model.mamba_layers.66.input_layernorm.weight", | |
| "model.mamba_layers.66.mamba.norm.weight", | |
| "model.mamba_layers.67.input_layernorm.weight", | |
| "model.mamba_layers.67.mamba.norm.weight", | |
| "model.mamba_layers.68.input_layernorm.weight", | |
| "model.mamba_layers.68.mamba.norm.weight", | |
| "model.mamba_layers.69.input_layernorm.weight", | |
| "model.mamba_layers.69.mamba.norm.weight", | |
| "model.mamba_layers.7.input_layernorm.weight", | |
| "model.mamba_layers.7.mamba.norm.weight", | |
| "model.mamba_layers.70.input_layernorm.weight", | |
| "model.mamba_layers.70.mamba.norm.weight", | |
| "model.mamba_layers.71.input_layernorm.weight", | |
| "model.mamba_layers.71.mamba.norm.weight", | |
| "model.mamba_layers.72.input_layernorm.weight", | |
| "model.mamba_layers.72.mamba.norm.weight", | |
| "model.mamba_layers.73.input_layernorm.weight", | |
| "model.mamba_layers.73.mamba.norm.weight", | |
| "model.mamba_layers.74.input_layernorm.weight", | |
| "model.mamba_layers.74.mamba.norm.weight", | |
| "model.mamba_layers.75.input_layernorm.weight", | |
| "model.mamba_layers.75.mamba.norm.weight", | |
| "model.mamba_layers.76.input_layernorm.weight", | |
| "model.mamba_layers.76.mamba.norm.weight", | |
| "model.mamba_layers.77.input_layernorm.weight", | |
| "model.mamba_layers.77.mamba.norm.weight", | |
| "model.mamba_layers.78.input_layernorm.weight", | |
| "model.mamba_layers.78.mamba.norm.weight", | |
| "model.mamba_layers.79.input_layernorm.weight", | |
| "model.mamba_layers.79.mamba.norm.weight", | |
| "model.mamba_layers.8.input_layernorm.weight", | |
| "model.mamba_layers.8.mamba.norm.weight", | |
| "model.mamba_layers.80.input_layernorm.weight", | |
| "model.mamba_layers.80.mamba.norm.weight", | |
| "model.mamba_layers.9.input_layernorm.weight", | |
| "model.mamba_layers.9.mamba.norm.weight" | |
| ], | |
| "embedding": [ | |
| "model.embed_tokens.weight" | |
| ], | |
| "ssm_param": [ | |
| "model.layers.0.mamba.A_log", | |
| "model.layers.0.mamba.D", | |
| "model.layers.0.mamba.dt_bias", | |
| "model.layers.1.mamba.A_log", | |
| "model.layers.1.mamba.D", | |
| "model.layers.1.mamba.dt_bias", | |
| "model.layers.10.mamba.A_log", | |
| "model.layers.10.mamba.D", | |
| "model.layers.10.mamba.dt_bias", | |
| "model.layers.11.mamba_decoder.mamba.A_log", | |
| "model.layers.11.mamba_decoder.mamba.D", | |
| "model.layers.11.mamba_decoder.mamba.dt_bias", | |
| "model.layers.12.mamba.A_log", | |
| "model.layers.12.mamba.D", | |
| "model.layers.12.mamba.dt_bias", | |
| "model.layers.13.mamba.A_log", | |
| "model.layers.13.mamba.D", | |
| "model.layers.13.mamba.dt_bias", | |
| "model.layers.14.mamba.A_log", | |
| "model.layers.14.mamba.D", | |
| "model.layers.14.mamba.dt_bias", | |
| "model.layers.15.mamba.A_log", | |
| "model.layers.15.mamba.D", | |
| "model.layers.15.mamba.dt_bias", | |
| "model.layers.16.mamba.A_log", | |
| "model.layers.16.mamba.D", | |
| "model.layers.16.mamba.dt_bias", | |
| "model.layers.17.mamba_decoder.mamba.A_log", | |
| "model.layers.17.mamba_decoder.mamba.D", | |
| "model.layers.17.mamba_decoder.mamba.dt_bias", | |
| "model.layers.18.mamba.A_log", | |
| "model.layers.18.mamba.D", | |
| "model.layers.18.mamba.dt_bias", | |
| "model.layers.19.mamba.A_log", | |
| "model.layers.19.mamba.D", | |
| "model.layers.19.mamba.dt_bias", | |
| "model.layers.2.mamba.A_log", | |
| "model.layers.2.mamba.D", | |
| "model.layers.2.mamba.dt_bias", | |
| "model.layers.20.mamba.A_log", | |
| "model.layers.20.mamba.D", | |
| "model.layers.20.mamba.dt_bias", | |
| "model.layers.21.mamba.A_log", | |
| "model.layers.21.mamba.D", | |
| "model.layers.21.mamba.dt_bias", | |
| "model.layers.22.mamba.A_log", | |
| "model.layers.22.mamba.D", | |
| "model.layers.22.mamba.dt_bias", | |
| "model.layers.23.mamba_decoder.mamba.A_log", | |
| "model.layers.23.mamba_decoder.mamba.D", | |
| "model.layers.23.mamba_decoder.mamba.dt_bias", | |
| "model.layers.24.mamba.A_log", | |
| "model.layers.24.mamba.D", | |
| "model.layers.24.mamba.dt_bias", | |
| "model.layers.25.mamba.A_log", | |
| "model.layers.25.mamba.D", | |
| "model.layers.25.mamba.dt_bias", | |
| "model.layers.26.mamba.A_log", | |
| "model.layers.26.mamba.D", | |
| "model.layers.26.mamba.dt_bias", | |
| "model.layers.27.mamba.A_log", | |
| "model.layers.27.mamba.D", | |
| "model.layers.27.mamba.dt_bias", | |
| "model.layers.28.mamba.A_log", | |
| "model.layers.28.mamba.D", | |
| "model.layers.28.mamba.dt_bias", | |
| "model.layers.29.mamba_decoder.mamba.A_log", | |
| "model.layers.29.mamba_decoder.mamba.D", | |
| "model.layers.29.mamba_decoder.mamba.dt_bias", | |
| "model.layers.3.mamba.A_log", | |
| "model.layers.3.mamba.D", | |
| "model.layers.3.mamba.dt_bias", | |
| "model.layers.30.mamba.A_log", | |
| "model.layers.30.mamba.D", | |
| "model.layers.30.mamba.dt_bias", | |
| "model.layers.31.mamba.A_log", | |
| "model.layers.31.mamba.D", | |
| "model.layers.31.mamba.dt_bias", | |
| "model.layers.32.mamba.A_log", | |
| "model.layers.32.mamba.D", | |
| "model.layers.32.mamba.dt_bias", | |
| "model.layers.33.mamba.A_log", | |
| "model.layers.33.mamba.D", | |
| "model.layers.33.mamba.dt_bias", | |
| "model.layers.34.mamba.A_log", | |
| "model.layers.34.mamba.D", | |
| "model.layers.34.mamba.dt_bias", | |
| "model.layers.35.mamba_decoder.mamba.A_log", | |
| "model.layers.35.mamba_decoder.mamba.D", | |
| "model.layers.35.mamba_decoder.mamba.dt_bias", | |
| "model.layers.36.mamba.A_log", | |
| "model.layers.36.mamba.D", | |
| "model.layers.36.mamba.dt_bias", | |
| "model.layers.37.mamba.A_log", | |
| "model.layers.37.mamba.D", | |
| "model.layers.37.mamba.dt_bias", | |
| "model.layers.38.mamba.A_log", | |
| "model.layers.38.mamba.D", | |
| "model.layers.38.mamba.dt_bias", | |
| "model.layers.39.mamba.A_log", | |
| "model.layers.39.mamba.D", | |
| "model.layers.39.mamba.dt_bias", | |
| "model.layers.4.mamba.A_log", | |
| "model.layers.4.mamba.D", | |
| "model.layers.4.mamba.dt_bias", | |
| "model.layers.40.mamba.A_log", | |
| "model.layers.40.mamba.D", | |
| "model.layers.40.mamba.dt_bias", | |
| "model.layers.41.mamba_decoder.mamba.A_log", | |
| "model.layers.41.mamba_decoder.mamba.D", | |
| "model.layers.41.mamba_decoder.mamba.dt_bias", | |
| "model.layers.42.mamba.A_log", | |
| "model.layers.42.mamba.D", | |
| "model.layers.42.mamba.dt_bias", | |
| "model.layers.43.mamba.A_log", | |
| "model.layers.43.mamba.D", | |
| "model.layers.43.mamba.dt_bias", | |
| "model.layers.44.mamba.A_log", | |
| "model.layers.44.mamba.D", | |
| "model.layers.44.mamba.dt_bias", | |
| "model.layers.45.mamba.A_log", | |
| "model.layers.45.mamba.D", | |
| "model.layers.45.mamba.dt_bias", | |
| "model.layers.46.mamba.A_log", | |
| "model.layers.46.mamba.D", | |
| "model.layers.46.mamba.dt_bias", | |
| "model.layers.47.mamba_decoder.mamba.A_log", | |
| "model.layers.47.mamba_decoder.mamba.D", | |
| "model.layers.47.mamba_decoder.mamba.dt_bias", | |
| "model.layers.48.mamba.A_log", | |
| "model.layers.48.mamba.D", | |
| "model.layers.48.mamba.dt_bias", | |
| "model.layers.49.mamba.A_log", | |
| "model.layers.49.mamba.D", | |
| "model.layers.49.mamba.dt_bias", | |
| "model.layers.5.mamba.A_log", | |
| "model.layers.5.mamba.D", | |
| "model.layers.5.mamba.dt_bias", | |
| "model.layers.50.mamba.A_log", | |
| "model.layers.50.mamba.D", | |
| "model.layers.50.mamba.dt_bias", | |
| "model.layers.51.mamba.A_log", | |
| "model.layers.51.mamba.D", | |
| "model.layers.51.mamba.dt_bias", | |
| "model.layers.52.mamba.A_log", | |
| "model.layers.52.mamba.D", | |
| "model.layers.52.mamba.dt_bias", | |
| "model.layers.53.mamba_decoder.mamba.A_log", | |
| "model.layers.53.mamba_decoder.mamba.D", | |
| "model.layers.53.mamba_decoder.mamba.dt_bias", | |
| "model.layers.54.mamba.A_log", | |
| "model.layers.54.mamba.D", | |
| "model.layers.54.mamba.dt_bias", | |
| "model.layers.55.mamba.A_log", | |
| "model.layers.55.mamba.D", | |
| "model.layers.55.mamba.dt_bias", | |
| "model.layers.56.mamba.A_log", | |
| "model.layers.56.mamba.D", | |
| "model.layers.56.mamba.dt_bias", | |
| "model.layers.57.mamba.A_log", | |
| "model.layers.57.mamba.D", | |
| "model.layers.57.mamba.dt_bias", | |
| "model.layers.58.mamba.A_log", | |
| "model.layers.58.mamba.D", | |
| "model.layers.58.mamba.dt_bias", | |
| "model.layers.59.mamba_decoder.mamba.A_log", | |
| "model.layers.59.mamba_decoder.mamba.D", | |
| "model.layers.59.mamba_decoder.mamba.dt_bias", | |
| "model.layers.6.mamba_decoder.mamba.A_log", | |
| "model.layers.6.mamba_decoder.mamba.D", | |
| "model.layers.6.mamba_decoder.mamba.dt_bias", | |
| "model.layers.60.mamba.A_log", | |
| "model.layers.60.mamba.D", | |
| "model.layers.60.mamba.dt_bias", | |
| "model.layers.61.mamba.A_log", | |
| "model.layers.61.mamba.D", | |
| "model.layers.61.mamba.dt_bias", | |
| "model.layers.62.mamba.A_log", | |
| "model.layers.62.mamba.D", | |
| "model.layers.62.mamba.dt_bias", | |
| "model.layers.63.mamba.A_log", | |
| "model.layers.63.mamba.D", | |
| "model.layers.63.mamba.dt_bias", | |
| "model.layers.64.mamba.A_log", | |
| "model.layers.64.mamba.D", | |
| "model.layers.64.mamba.dt_bias", | |
| "model.layers.65.mamba_decoder.mamba.A_log", | |
| "model.layers.65.mamba_decoder.mamba.D", | |
| "model.layers.65.mamba_decoder.mamba.dt_bias", | |
| "model.layers.66.mamba.A_log", | |
| "model.layers.66.mamba.D", | |
| "model.layers.66.mamba.dt_bias", | |
| "model.layers.67.mamba.A_log", | |
| "model.layers.67.mamba.D", | |
| "model.layers.67.mamba.dt_bias", | |
| "model.layers.68.mamba.A_log", | |
| "model.layers.68.mamba.D", | |
| "model.layers.68.mamba.dt_bias", | |
| "model.layers.69.mamba.A_log", | |
| "model.layers.69.mamba.D", | |
| "model.layers.69.mamba.dt_bias", | |
| "model.layers.7.mamba.A_log", | |
| "model.layers.7.mamba.D", | |
| "model.layers.7.mamba.dt_bias", | |
| "model.layers.70.mamba.A_log", | |
| "model.layers.70.mamba.D", | |
| "model.layers.70.mamba.dt_bias", | |
| "model.layers.71.mamba_decoder.mamba.A_log", | |
| "model.layers.71.mamba_decoder.mamba.D", | |
| "model.layers.71.mamba_decoder.mamba.dt_bias", | |
| "model.layers.72.mamba.A_log", | |
| "model.layers.72.mamba.D", | |
| "model.layers.72.mamba.dt_bias", | |
| "model.layers.73.mamba.A_log", | |
| "model.layers.73.mamba.D", | |
| "model.layers.73.mamba.dt_bias", | |
| "model.layers.74.mamba.A_log", | |
| "model.layers.74.mamba.D", | |
| "model.layers.74.mamba.dt_bias", | |
| "model.layers.75.mamba.A_log", | |
| "model.layers.75.mamba.D", | |
| "model.layers.75.mamba.dt_bias", | |
| "model.layers.76.mamba.A_log", | |
| "model.layers.76.mamba.D", | |
| "model.layers.76.mamba.dt_bias", | |
| "model.layers.77.mamba_decoder.mamba.A_log", | |
| "model.layers.77.mamba_decoder.mamba.D", | |
| "model.layers.77.mamba_decoder.mamba.dt_bias", | |
| "model.layers.78.mamba.A_log", | |
| "model.layers.78.mamba.D", | |
| "model.layers.78.mamba.dt_bias", | |
| "model.layers.79.mamba.A_log", | |
| "model.layers.79.mamba.D", | |
| "model.layers.79.mamba.dt_bias", | |
| "model.layers.8.mamba.A_log", | |
| "model.layers.8.mamba.D", | |
| "model.layers.8.mamba.dt_bias", | |
| "model.layers.80.mamba.A_log", | |
| "model.layers.80.mamba.D", | |
| "model.layers.80.mamba.dt_bias", | |
| "model.layers.9.mamba.A_log", | |
| "model.layers.9.mamba.D", | |
| "model.layers.9.mamba.dt_bias", | |
| "model.mamba_layers.0.mamba.A_log", | |
| "model.mamba_layers.0.mamba.D", | |
| "model.mamba_layers.0.mamba.dt_bias", | |
| "model.mamba_layers.1.mamba.A_log", | |
| "model.mamba_layers.1.mamba.D", | |
| "model.mamba_layers.1.mamba.dt_bias", | |
| "model.mamba_layers.10.mamba.A_log", | |
| "model.mamba_layers.10.mamba.D", | |
| "model.mamba_layers.10.mamba.dt_bias", | |
| "model.mamba_layers.11.mamba.A_log", | |
| "model.mamba_layers.11.mamba.D", | |
| "model.mamba_layers.11.mamba.dt_bias", | |
| "model.mamba_layers.12.mamba.A_log", | |
| "model.mamba_layers.12.mamba.D", | |
| "model.mamba_layers.12.mamba.dt_bias", | |
| "model.mamba_layers.13.mamba.A_log", | |
| "model.mamba_layers.13.mamba.D", | |
| "model.mamba_layers.13.mamba.dt_bias", | |
| "model.mamba_layers.14.mamba.A_log", | |
| "model.mamba_layers.14.mamba.D", | |
| "model.mamba_layers.14.mamba.dt_bias", | |
| "model.mamba_layers.15.mamba.A_log", | |
| "model.mamba_layers.15.mamba.D", | |
| "model.mamba_layers.15.mamba.dt_bias", | |
| "model.mamba_layers.16.mamba.A_log", | |
| "model.mamba_layers.16.mamba.D", | |
| "model.mamba_layers.16.mamba.dt_bias", | |
| "model.mamba_layers.17.mamba.A_log", | |
| "model.mamba_layers.17.mamba.D", | |
| "model.mamba_layers.17.mamba.dt_bias", | |
| "model.mamba_layers.18.mamba.A_log", | |
| "model.mamba_layers.18.mamba.D", | |
| "model.mamba_layers.18.mamba.dt_bias", | |
| "model.mamba_layers.19.mamba.A_log", | |
| "model.mamba_layers.19.mamba.D", | |
| "model.mamba_layers.19.mamba.dt_bias", | |
| "model.mamba_layers.2.mamba.A_log", | |
| "model.mamba_layers.2.mamba.D", | |
| "model.mamba_layers.2.mamba.dt_bias", | |
| "model.mamba_layers.20.mamba.A_log", | |
| "model.mamba_layers.20.mamba.D", | |
| "model.mamba_layers.20.mamba.dt_bias", | |
| "model.mamba_layers.21.mamba.A_log", | |
| "model.mamba_layers.21.mamba.D", | |
| "model.mamba_layers.21.mamba.dt_bias", | |
| "model.mamba_layers.22.mamba.A_log", | |
| "model.mamba_layers.22.mamba.D", | |
| "model.mamba_layers.22.mamba.dt_bias", | |
| "model.mamba_layers.23.mamba.A_log", | |
| "model.mamba_layers.23.mamba.D", | |
| "model.mamba_layers.23.mamba.dt_bias", | |
| "model.mamba_layers.24.mamba.A_log", | |
| "model.mamba_layers.24.mamba.D", | |
| "model.mamba_layers.24.mamba.dt_bias", | |
| "model.mamba_layers.25.mamba.A_log", | |
| "model.mamba_layers.25.mamba.D", | |
| "model.mamba_layers.25.mamba.dt_bias", | |
| "model.mamba_layers.26.mamba.A_log", | |
| "model.mamba_layers.26.mamba.D", | |
| "model.mamba_layers.26.mamba.dt_bias", | |
| "model.mamba_layers.27.mamba.A_log", | |
| "model.mamba_layers.27.mamba.D", | |
| "model.mamba_layers.27.mamba.dt_bias", | |
| "model.mamba_layers.28.mamba.A_log", | |
| "model.mamba_layers.28.mamba.D", | |
| "model.mamba_layers.28.mamba.dt_bias", | |
| "model.mamba_layers.29.mamba.A_log", | |
| "model.mamba_layers.29.mamba.D", | |
| "model.mamba_layers.29.mamba.dt_bias", | |
| "model.mamba_layers.3.mamba.A_log", | |
| "model.mamba_layers.3.mamba.D", | |
| "model.mamba_layers.3.mamba.dt_bias", | |
| "model.mamba_layers.30.mamba.A_log", | |
| "model.mamba_layers.30.mamba.D", | |
| "model.mamba_layers.30.mamba.dt_bias", | |
| "model.mamba_layers.31.mamba.A_log", | |
| "model.mamba_layers.31.mamba.D", | |
| "model.mamba_layers.31.mamba.dt_bias", | |
| "model.mamba_layers.32.mamba.A_log", | |
| "model.mamba_layers.32.mamba.D", | |
| "model.mamba_layers.32.mamba.dt_bias", | |
| "model.mamba_layers.33.mamba.A_log", | |
| "model.mamba_layers.33.mamba.D", | |
| "model.mamba_layers.33.mamba.dt_bias", | |
| "model.mamba_layers.34.mamba.A_log", | |
| "model.mamba_layers.34.mamba.D", | |
| "model.mamba_layers.34.mamba.dt_bias", | |
| "model.mamba_layers.35.mamba.A_log", | |
| "model.mamba_layers.35.mamba.D", | |
| "model.mamba_layers.35.mamba.dt_bias", | |
| "model.mamba_layers.36.mamba.A_log", | |
| "model.mamba_layers.36.mamba.D", | |
| "model.mamba_layers.36.mamba.dt_bias", | |
| "model.mamba_layers.37.mamba.A_log", | |
| "model.mamba_layers.37.mamba.D", | |
| "model.mamba_layers.37.mamba.dt_bias", | |
| "model.mamba_layers.38.mamba.A_log", | |
| "model.mamba_layers.38.mamba.D", | |
| "model.mamba_layers.38.mamba.dt_bias", | |
| "model.mamba_layers.39.mamba.A_log", | |
| "model.mamba_layers.39.mamba.D", | |
| "model.mamba_layers.39.mamba.dt_bias", | |
| "model.mamba_layers.4.mamba.A_log", | |
| "model.mamba_layers.4.mamba.D", | |
| "model.mamba_layers.4.mamba.dt_bias", | |
| "model.mamba_layers.40.mamba.A_log", | |
| "model.mamba_layers.40.mamba.D", | |
| "model.mamba_layers.40.mamba.dt_bias", | |
| "model.mamba_layers.41.mamba.A_log", | |
| "model.mamba_layers.41.mamba.D", | |
| "model.mamba_layers.41.mamba.dt_bias", | |
| "model.mamba_layers.42.mamba.A_log", | |
| "model.mamba_layers.42.mamba.D", | |
| "model.mamba_layers.42.mamba.dt_bias", | |
| "model.mamba_layers.43.mamba.A_log", | |
| "model.mamba_layers.43.mamba.D", | |
| "model.mamba_layers.43.mamba.dt_bias", | |
| "model.mamba_layers.44.mamba.A_log", | |
| "model.mamba_layers.44.mamba.D", | |
| "model.mamba_layers.44.mamba.dt_bias", | |
| "model.mamba_layers.45.mamba.A_log", | |
| "model.mamba_layers.45.mamba.D", | |
| "model.mamba_layers.45.mamba.dt_bias", | |
| "model.mamba_layers.46.mamba.A_log", | |
| "model.mamba_layers.46.mamba.D", | |
| "model.mamba_layers.46.mamba.dt_bias", | |
| "model.mamba_layers.47.mamba.A_log", | |
| "model.mamba_layers.47.mamba.D", | |
| "model.mamba_layers.47.mamba.dt_bias", | |
| "model.mamba_layers.48.mamba.A_log", | |
| "model.mamba_layers.48.mamba.D", | |
| "model.mamba_layers.48.mamba.dt_bias", | |
| "model.mamba_layers.49.mamba.A_log", | |
| "model.mamba_layers.49.mamba.D", | |
| "model.mamba_layers.49.mamba.dt_bias", | |
| "model.mamba_layers.5.mamba.A_log", | |
| "model.mamba_layers.5.mamba.D", | |
| "model.mamba_layers.5.mamba.dt_bias", | |
| "model.mamba_layers.50.mamba.A_log", | |
| "model.mamba_layers.50.mamba.D", | |
| "model.mamba_layers.50.mamba.dt_bias", | |
| "model.mamba_layers.51.mamba.A_log", | |
| "model.mamba_layers.51.mamba.D", | |
| "model.mamba_layers.51.mamba.dt_bias", | |
| "model.mamba_layers.52.mamba.A_log", | |
| "model.mamba_layers.52.mamba.D", | |
| "model.mamba_layers.52.mamba.dt_bias", | |
| "model.mamba_layers.53.mamba.A_log", | |
| "model.mamba_layers.53.mamba.D", | |
| "model.mamba_layers.53.mamba.dt_bias", | |
| "model.mamba_layers.54.mamba.A_log", | |
| "model.mamba_layers.54.mamba.D", | |
| "model.mamba_layers.54.mamba.dt_bias", | |
| "model.mamba_layers.55.mamba.A_log", | |
| "model.mamba_layers.55.mamba.D", | |
| "model.mamba_layers.55.mamba.dt_bias", | |
| "model.mamba_layers.56.mamba.A_log", | |
| "model.mamba_layers.56.mamba.D", | |
| "model.mamba_layers.56.mamba.dt_bias", | |
| "model.mamba_layers.57.mamba.A_log", | |
| "model.mamba_layers.57.mamba.D", | |
| "model.mamba_layers.57.mamba.dt_bias", | |
| "model.mamba_layers.58.mamba.A_log", | |
| "model.mamba_layers.58.mamba.D", | |
| "model.mamba_layers.58.mamba.dt_bias", | |
| "model.mamba_layers.59.mamba.A_log", | |
| "model.mamba_layers.59.mamba.D", | |
| "model.mamba_layers.59.mamba.dt_bias", | |
| "model.mamba_layers.6.mamba.A_log", | |
| "model.mamba_layers.6.mamba.D", | |
| "model.mamba_layers.6.mamba.dt_bias", | |
| "model.mamba_layers.60.mamba.A_log", | |
| "model.mamba_layers.60.mamba.D", | |
| "model.mamba_layers.60.mamba.dt_bias", | |
| "model.mamba_layers.61.mamba.A_log", | |
| "model.mamba_layers.61.mamba.D", | |
| "model.mamba_layers.61.mamba.dt_bias", | |
| "model.mamba_layers.62.mamba.A_log", | |
| "model.mamba_layers.62.mamba.D", | |
| "model.mamba_layers.62.mamba.dt_bias", | |
| "model.mamba_layers.63.mamba.A_log", | |
| "model.mamba_layers.63.mamba.D", | |
| "model.mamba_layers.63.mamba.dt_bias", | |
| "model.mamba_layers.64.mamba.A_log", | |
| "model.mamba_layers.64.mamba.D", | |
| "model.mamba_layers.64.mamba.dt_bias", | |
| "model.mamba_layers.65.mamba.A_log", | |
| "model.mamba_layers.65.mamba.D", | |
| "model.mamba_layers.65.mamba.dt_bias", | |
| "model.mamba_layers.66.mamba.A_log", | |
| "model.mamba_layers.66.mamba.D", | |
| "model.mamba_layers.66.mamba.dt_bias", | |
| "model.mamba_layers.67.mamba.A_log", | |
| "model.mamba_layers.67.mamba.D", | |
| "model.mamba_layers.67.mamba.dt_bias", | |
| "model.mamba_layers.68.mamba.A_log", | |
| "model.mamba_layers.68.mamba.D", | |
| "model.mamba_layers.68.mamba.dt_bias", | |
| "model.mamba_layers.69.mamba.A_log", | |
| "model.mamba_layers.69.mamba.D", | |
| "model.mamba_layers.69.mamba.dt_bias", | |
| "model.mamba_layers.7.mamba.A_log", | |
| "model.mamba_layers.7.mamba.D", | |
| "model.mamba_layers.7.mamba.dt_bias", | |
| "model.mamba_layers.70.mamba.A_log", | |
| "model.mamba_layers.70.mamba.D", | |
| "model.mamba_layers.70.mamba.dt_bias", | |
| "model.mamba_layers.71.mamba.A_log", | |
| "model.mamba_layers.71.mamba.D", | |
| "model.mamba_layers.71.mamba.dt_bias", | |
| "model.mamba_layers.72.mamba.A_log", | |
| "model.mamba_layers.72.mamba.D", | |
| "model.mamba_layers.72.mamba.dt_bias", | |
| "model.mamba_layers.73.mamba.A_log", | |
| "model.mamba_layers.73.mamba.D", | |
| "model.mamba_layers.73.mamba.dt_bias", | |
| "model.mamba_layers.74.mamba.A_log", | |
| "model.mamba_layers.74.mamba.D", | |
| "model.mamba_layers.74.mamba.dt_bias", | |
| "model.mamba_layers.75.mamba.A_log", | |
| "model.mamba_layers.75.mamba.D", | |
| "model.mamba_layers.75.mamba.dt_bias", | |
| "model.mamba_layers.76.mamba.A_log", | |
| "model.mamba_layers.76.mamba.D", | |
| "model.mamba_layers.76.mamba.dt_bias", | |
| "model.mamba_layers.77.mamba.A_log", | |
| "model.mamba_layers.77.mamba.D", | |
| "model.mamba_layers.77.mamba.dt_bias", | |
| "model.mamba_layers.78.mamba.A_log", | |
| "model.mamba_layers.78.mamba.D", | |
| "model.mamba_layers.78.mamba.dt_bias", | |
| "model.mamba_layers.79.mamba.A_log", | |
| "model.mamba_layers.79.mamba.D", | |
| "model.mamba_layers.79.mamba.dt_bias", | |
| "model.mamba_layers.8.mamba.A_log", | |
| "model.mamba_layers.8.mamba.D", | |
| "model.mamba_layers.8.mamba.dt_bias", | |
| "model.mamba_layers.80.mamba.A_log", | |
| "model.mamba_layers.80.mamba.D", | |
| "model.mamba_layers.80.mamba.dt_bias", | |
| "model.mamba_layers.9.mamba.A_log", | |
| "model.mamba_layers.9.mamba.D", | |
| "model.mamba_layers.9.mamba.dt_bias" | |
| ], | |
| "bias": [ | |
| "model.layers.0.mamba.conv1d.bias", | |
| "model.layers.1.mamba.conv1d.bias", | |
| "model.layers.10.mamba.conv1d.bias", | |
| "model.layers.11.mamba_decoder.mamba.conv1d.bias", | |
| "model.layers.12.mamba.conv1d.bias", | |
| "model.layers.13.mamba.conv1d.bias", | |
| "model.layers.14.mamba.conv1d.bias", | |
| "model.layers.15.mamba.conv1d.bias", | |
| "model.layers.16.mamba.conv1d.bias", | |
| "model.layers.17.mamba_decoder.mamba.conv1d.bias", | |
| "model.layers.18.mamba.conv1d.bias", | |
| "model.layers.19.mamba.conv1d.bias", | |
| "model.layers.2.mamba.conv1d.bias", | |
| "model.layers.20.mamba.conv1d.bias", | |
| "model.layers.21.mamba.conv1d.bias", | |
| "model.layers.22.mamba.conv1d.bias", | |
| "model.layers.23.mamba_decoder.mamba.conv1d.bias", | |
| "model.layers.24.mamba.conv1d.bias", | |
| "model.layers.25.mamba.conv1d.bias", | |
| "model.layers.26.mamba.conv1d.bias", | |
| "model.layers.27.mamba.conv1d.bias", | |
| "model.layers.28.mamba.conv1d.bias", | |
| "model.layers.29.mamba_decoder.mamba.conv1d.bias", | |
| "model.layers.3.mamba.conv1d.bias", | |
| "model.layers.30.mamba.conv1d.bias", | |
| "model.layers.31.mamba.conv1d.bias", | |
| "model.layers.32.mamba.conv1d.bias", | |
| "model.layers.33.mamba.conv1d.bias", | |
| "model.layers.34.mamba.conv1d.bias", | |
| "model.layers.35.mamba_decoder.mamba.conv1d.bias", | |
| "model.layers.36.mamba.conv1d.bias", | |
| "model.layers.37.mamba.conv1d.bias", | |
| "model.layers.38.mamba.conv1d.bias", | |
| "model.layers.39.mamba.conv1d.bias", | |
| "model.layers.4.mamba.conv1d.bias", | |
| "model.layers.40.mamba.conv1d.bias", | |
| "model.layers.41.mamba_decoder.mamba.conv1d.bias", | |
| "model.layers.42.mamba.conv1d.bias", | |
| "model.layers.43.mamba.conv1d.bias", | |
| "model.layers.44.mamba.conv1d.bias", | |
| "model.layers.45.mamba.conv1d.bias", | |
| "model.layers.46.mamba.conv1d.bias", | |
| "model.layers.47.mamba_decoder.mamba.conv1d.bias", | |
| "model.layers.48.mamba.conv1d.bias", | |
| "model.layers.49.mamba.conv1d.bias", | |
| "model.layers.5.mamba.conv1d.bias", | |
| "model.layers.50.mamba.conv1d.bias", | |
| "model.layers.51.mamba.conv1d.bias", | |
| "model.layers.52.mamba.conv1d.bias", | |
| "model.layers.53.mamba_decoder.mamba.conv1d.bias", | |
| "model.layers.54.mamba.conv1d.bias", | |
| "model.layers.55.mamba.conv1d.bias", | |
| "model.layers.56.mamba.conv1d.bias", | |
| "model.layers.57.mamba.conv1d.bias", | |
| "model.layers.58.mamba.conv1d.bias", | |
| "model.layers.59.mamba_decoder.mamba.conv1d.bias", | |
| "model.layers.6.mamba_decoder.mamba.conv1d.bias", | |
| "model.layers.60.mamba.conv1d.bias", | |
| "model.layers.61.mamba.conv1d.bias", | |
| "model.layers.62.mamba.conv1d.bias", | |
| "model.layers.63.mamba.conv1d.bias", | |
| "model.layers.64.mamba.conv1d.bias", | |
| "model.layers.65.mamba_decoder.mamba.conv1d.bias", | |
| "model.layers.66.mamba.conv1d.bias", | |
| "model.layers.67.mamba.conv1d.bias", | |
| "model.layers.68.mamba.conv1d.bias", | |
| "model.layers.69.mamba.conv1d.bias", | |
| "model.layers.7.mamba.conv1d.bias", | |
| "model.layers.70.mamba.conv1d.bias", | |
| "model.layers.71.mamba_decoder.mamba.conv1d.bias", | |
| "model.layers.72.mamba.conv1d.bias", | |
| "model.layers.73.mamba.conv1d.bias", | |
| "model.layers.74.mamba.conv1d.bias", | |
| "model.layers.75.mamba.conv1d.bias", | |
| "model.layers.76.mamba.conv1d.bias", | |
| "model.layers.77.mamba_decoder.mamba.conv1d.bias", | |
| "model.layers.78.mamba.conv1d.bias", | |
| "model.layers.79.mamba.conv1d.bias", | |
| "model.layers.8.mamba.conv1d.bias", | |
| "model.layers.80.mamba.conv1d.bias", | |
| "model.layers.9.mamba.conv1d.bias", | |
| "model.mamba_layers.0.mamba.conv1d.bias", | |
| "model.mamba_layers.1.mamba.conv1d.bias", | |
| "model.mamba_layers.10.mamba.conv1d.bias", | |
| "model.mamba_layers.11.mamba.conv1d.bias", | |
| "model.mamba_layers.12.mamba.conv1d.bias", | |
| "model.mamba_layers.13.mamba.conv1d.bias", | |
| "model.mamba_layers.14.mamba.conv1d.bias", | |
| "model.mamba_layers.15.mamba.conv1d.bias", | |
| "model.mamba_layers.16.mamba.conv1d.bias", | |
| "model.mamba_layers.17.mamba.conv1d.bias", | |
| "model.mamba_layers.18.mamba.conv1d.bias", | |
| "model.mamba_layers.19.mamba.conv1d.bias", | |
| "model.mamba_layers.2.mamba.conv1d.bias", | |
| "model.mamba_layers.20.mamba.conv1d.bias", | |
| "model.mamba_layers.21.mamba.conv1d.bias", | |
| "model.mamba_layers.22.mamba.conv1d.bias", | |
| "model.mamba_layers.23.mamba.conv1d.bias", | |
| "model.mamba_layers.24.mamba.conv1d.bias", | |
| "model.mamba_layers.25.mamba.conv1d.bias", | |
| "model.mamba_layers.26.mamba.conv1d.bias", | |
| "model.mamba_layers.27.mamba.conv1d.bias", | |
| "model.mamba_layers.28.mamba.conv1d.bias", | |
| "model.mamba_layers.29.mamba.conv1d.bias", | |
| "model.mamba_layers.3.mamba.conv1d.bias", | |
| "model.mamba_layers.30.mamba.conv1d.bias", | |
| "model.mamba_layers.31.mamba.conv1d.bias", | |
| "model.mamba_layers.32.mamba.conv1d.bias", | |
| "model.mamba_layers.33.mamba.conv1d.bias", | |
| "model.mamba_layers.34.mamba.conv1d.bias", | |
| "model.mamba_layers.35.mamba.conv1d.bias", | |
| "model.mamba_layers.36.mamba.conv1d.bias", | |
| "model.mamba_layers.37.mamba.conv1d.bias", | |
| "model.mamba_layers.38.mamba.conv1d.bias", | |
| "model.mamba_layers.39.mamba.conv1d.bias", | |
| "model.mamba_layers.4.mamba.conv1d.bias", | |
| "model.mamba_layers.40.mamba.conv1d.bias", | |
| "model.mamba_layers.41.mamba.conv1d.bias", | |
| "model.mamba_layers.42.mamba.conv1d.bias", | |
| "model.mamba_layers.43.mamba.conv1d.bias", | |
| "model.mamba_layers.44.mamba.conv1d.bias", | |
| "model.mamba_layers.45.mamba.conv1d.bias", | |
| "model.mamba_layers.46.mamba.conv1d.bias", | |
| "model.mamba_layers.47.mamba.conv1d.bias", | |
| "model.mamba_layers.48.mamba.conv1d.bias", | |
| "model.mamba_layers.49.mamba.conv1d.bias", | |
| "model.mamba_layers.5.mamba.conv1d.bias", | |
| "model.mamba_layers.50.mamba.conv1d.bias", | |
| "model.mamba_layers.51.mamba.conv1d.bias", | |
| "model.mamba_layers.52.mamba.conv1d.bias", | |
| "model.mamba_layers.53.mamba.conv1d.bias", | |
| "model.mamba_layers.54.mamba.conv1d.bias", | |
| "model.mamba_layers.55.mamba.conv1d.bias", | |
| "model.mamba_layers.56.mamba.conv1d.bias", | |
| "model.mamba_layers.57.mamba.conv1d.bias", | |
| "model.mamba_layers.58.mamba.conv1d.bias", | |
| "model.mamba_layers.59.mamba.conv1d.bias", | |
| "model.mamba_layers.6.mamba.conv1d.bias", | |
| "model.mamba_layers.60.mamba.conv1d.bias", | |
| "model.mamba_layers.61.mamba.conv1d.bias", | |
| "model.mamba_layers.62.mamba.conv1d.bias", | |
| "model.mamba_layers.63.mamba.conv1d.bias", | |
| "model.mamba_layers.64.mamba.conv1d.bias", | |
| "model.mamba_layers.65.mamba.conv1d.bias", | |
| "model.mamba_layers.66.mamba.conv1d.bias", | |
| "model.mamba_layers.67.mamba.conv1d.bias", | |
| "model.mamba_layers.68.mamba.conv1d.bias", | |
| "model.mamba_layers.69.mamba.conv1d.bias", | |
| "model.mamba_layers.7.mamba.conv1d.bias", | |
| "model.mamba_layers.70.mamba.conv1d.bias", | |
| "model.mamba_layers.71.mamba.conv1d.bias", | |
| "model.mamba_layers.72.mamba.conv1d.bias", | |
| "model.mamba_layers.73.mamba.conv1d.bias", | |
| "model.mamba_layers.74.mamba.conv1d.bias", | |
| "model.mamba_layers.75.mamba.conv1d.bias", | |
| "model.mamba_layers.76.mamba.conv1d.bias", | |
| "model.mamba_layers.77.mamba.conv1d.bias", | |
| "model.mamba_layers.78.mamba.conv1d.bias", | |
| "model.mamba_layers.79.mamba.conv1d.bias", | |
| "model.mamba_layers.8.mamba.conv1d.bias", | |
| "model.mamba_layers.80.mamba.conv1d.bias", | |
| "model.mamba_layers.9.mamba.conv1d.bias" | |
| ] | |
| } | |
| } |