Instructions to use LLMWildling/gemma-4-120b-a12b-coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LLMWildling/gemma-4-120b-a12b-coder with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="LLMWildling/gemma-4-120b-a12b-coder")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("LLMWildling/gemma-4-120b-a12b-coder")
model = AutoModelForMultimodalLM.from_pretrained("LLMWildling/gemma-4-120b-a12b-coder", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LLMWildling/gemma-4-120b-a12b-coder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LLMWildling/gemma-4-120b-a12b-coder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LLMWildling/gemma-4-120b-a12b-coder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LLMWildling/gemma-4-120b-a12b-coder

SGLang

How to use LLMWildling/gemma-4-120b-a12b-coder 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 "LLMWildling/gemma-4-120b-a12b-coder" \
    --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": "LLMWildling/gemma-4-120b-a12b-coder",
		"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 "LLMWildling/gemma-4-120b-a12b-coder" \
        --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": "LLMWildling/gemma-4-120b-a12b-coder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LLMWildling/gemma-4-120b-a12b-coder with Docker Model Runner:
```
docker model run hf.co/LLMWildling/gemma-4-120b-a12b-coder
```

gemma-4-120b-a12b-coder / model.safetensors.index.json

LLMWildling

Upload gemma-4-120b-a12b-coder

9d1b005 verified about 2 months ago

Raw

History Blame Contribute Delete

99.8 kB

	{
	"metadata": {
	"total_size": 73857853532
	},
	"weight_map": {
	"model.embed_vision.embedding_projection.weight": "model-00001.safetensors",
	"model.language_model.embed_tokens.weight": "model-00001.safetensors",
	"model.language_model.layers.0.input_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.0.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.0.mlp.down_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.0.mlp.up_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.0.moe.experts.w13_weight": "model-00002.safetensors",
	"model.language_model.layers.0.moe.experts.w13_weight_scale": "model-00002.safetensors",
	"model.language_model.layers.0.moe.experts.w2_weight": "model-00002.safetensors",
	"model.language_model.layers.0.moe.experts.w2_weight_scale": "model-00002.safetensors",
	"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.0.post_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.0.post_feedforward_layernorm_1.weight": "model-00001.safetensors",
	"model.language_model.layers.0.post_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.0.pre_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.0.pre_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.0.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.0.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.0.router.scale": "model-00001.safetensors",
	"model.language_model.layers.0.self_attn.k_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.0.self_attn.k_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.0.self_attn.o_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.0.self_attn.q_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.0.self_attn.q_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.0.self_attn.v_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.1.input_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.1.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.1.mlp.down_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.1.mlp.up_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.1.moe.experts.w13_weight": "model-00003.safetensors",
	"model.language_model.layers.1.moe.experts.w13_weight_scale": "model-00003.safetensors",
	"model.language_model.layers.1.moe.experts.w2_weight": "model-00003.safetensors",
	"model.language_model.layers.1.moe.experts.w2_weight_scale": "model-00003.safetensors",
	"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.1.post_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.1.post_feedforward_layernorm_1.weight": "model-00001.safetensors",
	"model.language_model.layers.1.post_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.1.pre_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.1.pre_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.1.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.1.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.1.router.scale": "model-00001.safetensors",
	"model.language_model.layers.1.self_attn.k_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.1.self_attn.k_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.1.self_attn.o_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.1.self_attn.q_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.1.self_attn.q_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.1.self_attn.v_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.10.input_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.10.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.10.mlp.down_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.10.mlp.gate_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.10.mlp.up_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.10.moe.experts.w13_weight": "model-00004.safetensors",
	"model.language_model.layers.10.moe.experts.w13_weight_scale": "model-00004.safetensors",
	"model.language_model.layers.10.moe.experts.w2_weight": "model-00003.safetensors",
	"model.language_model.layers.10.moe.experts.w2_weight_scale": "model-00003.safetensors",
	"model.language_model.layers.10.post_attention_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.10.post_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.10.post_feedforward_layernorm_1.weight": "model-00001.safetensors",
	"model.language_model.layers.10.post_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.10.pre_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.10.pre_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.10.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.10.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.10.router.scale": "model-00001.safetensors",
	"model.language_model.layers.10.self_attn.k_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.10.self_attn.k_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.10.self_attn.o_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.10.self_attn.q_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.10.self_attn.q_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.10.self_attn.v_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.11.input_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.11.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.11.mlp.down_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.11.mlp.gate_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.11.mlp.up_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.11.moe.experts.w13_weight": "model-00004.safetensors",
	"model.language_model.layers.11.moe.experts.w13_weight_scale": "model-00004.safetensors",
	"model.language_model.layers.11.moe.experts.w2_weight": "model-00004.safetensors",
	"model.language_model.layers.11.moe.experts.w2_weight_scale": "model-00004.safetensors",
	"model.language_model.layers.11.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.11.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.11.post_feedforward_layernorm_1.weight": "model-00002.safetensors",
	"model.language_model.layers.11.post_feedforward_layernorm_2.weight": "model-00002.safetensors",
	"model.language_model.layers.11.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.11.pre_feedforward_layernorm_2.weight": "model-00002.safetensors",
	"model.language_model.layers.11.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.11.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.11.router.scale": "model-00001.safetensors",
	"model.language_model.layers.11.self_attn.k_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.11.self_attn.k_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.11.self_attn.o_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.11.self_attn.q_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.11.self_attn.q_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.12.input_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.12.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.12.mlp.down_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.12.mlp.gate_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.12.mlp.up_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.12.moe.experts.w13_weight": "model-00005.safetensors",
	"model.language_model.layers.12.moe.experts.w13_weight_scale": "model-00005.safetensors",
	"model.language_model.layers.12.moe.experts.w2_weight": "model-00005.safetensors",
	"model.language_model.layers.12.moe.experts.w2_weight_scale": "model-00005.safetensors",
	"model.language_model.layers.12.post_attention_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.12.post_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.12.post_feedforward_layernorm_1.weight": "model-00001.safetensors",
	"model.language_model.layers.12.post_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.12.pre_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.12.pre_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.12.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.12.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.12.router.scale": "model-00001.safetensors",
	"model.language_model.layers.12.self_attn.k_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.12.self_attn.k_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.12.self_attn.o_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.12.self_attn.q_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.12.self_attn.q_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.12.self_attn.v_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.13.input_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.13.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.13.mlp.down_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.13.mlp.gate_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.13.mlp.up_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.13.moe.experts.w13_weight": "model-00006.safetensors",
	"model.language_model.layers.13.moe.experts.w13_weight_scale": "model-00006.safetensors",
	"model.language_model.layers.13.moe.experts.w2_weight": "model-00005.safetensors",
	"model.language_model.layers.13.moe.experts.w2_weight_scale": "model-00005.safetensors",
	"model.language_model.layers.13.post_attention_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.13.post_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.13.post_feedforward_layernorm_1.weight": "model-00001.safetensors",
	"model.language_model.layers.13.post_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.13.pre_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.13.pre_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.13.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.13.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.13.router.scale": "model-00001.safetensors",
	"model.language_model.layers.13.self_attn.k_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.13.self_attn.k_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.13.self_attn.o_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.13.self_attn.q_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.13.self_attn.q_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.13.self_attn.v_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.14.input_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.14.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.14.mlp.down_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.14.mlp.gate_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.14.mlp.up_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.14.moe.experts.w13_weight": "model-00006.safetensors",
	"model.language_model.layers.14.moe.experts.w13_weight_scale": "model-00006.safetensors",
	"model.language_model.layers.14.moe.experts.w2_weight": "model-00006.safetensors",
	"model.language_model.layers.14.moe.experts.w2_weight_scale": "model-00006.safetensors",
	"model.language_model.layers.14.post_attention_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.14.post_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.14.post_feedforward_layernorm_1.weight": "model-00001.safetensors",
	"model.language_model.layers.14.post_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.14.pre_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.14.pre_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.14.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.14.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.14.router.scale": "model-00001.safetensors",
	"model.language_model.layers.14.self_attn.k_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.14.self_attn.k_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.14.self_attn.o_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.14.self_attn.q_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.14.self_attn.q_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.14.self_attn.v_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.15.input_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.15.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.15.mlp.down_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.15.mlp.gate_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.15.mlp.up_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.15.moe.experts.w13_weight": "model-00007.safetensors",
	"model.language_model.layers.15.moe.experts.w13_weight_scale": "model-00007.safetensors",
	"model.language_model.layers.15.moe.experts.w2_weight": "model-00007.safetensors",
	"model.language_model.layers.15.moe.experts.w2_weight_scale": "model-00007.safetensors",
	"model.language_model.layers.15.post_attention_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.15.post_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.15.post_feedforward_layernorm_1.weight": "model-00001.safetensors",
	"model.language_model.layers.15.post_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.15.pre_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.15.pre_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.15.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.15.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.15.router.scale": "model-00001.safetensors",
	"model.language_model.layers.15.self_attn.k_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.15.self_attn.k_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.15.self_attn.o_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.15.self_attn.q_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.15.self_attn.q_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.15.self_attn.v_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.16.input_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.16.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.16.mlp.down_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.16.mlp.gate_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.16.mlp.up_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.16.moe.experts.w13_weight": "model-00008.safetensors",
	"model.language_model.layers.16.moe.experts.w13_weight_scale": "model-00008.safetensors",
	"model.language_model.layers.16.moe.experts.w2_weight": "model-00007.safetensors",
	"model.language_model.layers.16.moe.experts.w2_weight_scale": "model-00007.safetensors",
	"model.language_model.layers.16.post_attention_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.16.post_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.16.post_feedforward_layernorm_1.weight": "model-00001.safetensors",
	"model.language_model.layers.16.post_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.16.pre_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.16.pre_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.16.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.16.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.16.router.scale": "model-00001.safetensors",
	"model.language_model.layers.16.self_attn.k_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.16.self_attn.k_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.16.self_attn.o_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.16.self_attn.q_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.16.self_attn.q_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.16.self_attn.v_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.17.input_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.17.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.17.mlp.down_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.17.mlp.gate_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.17.mlp.up_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.17.moe.experts.w13_weight": "model-00008.safetensors",
	"model.language_model.layers.17.moe.experts.w13_weight_scale": "model-00008.safetensors",
	"model.language_model.layers.17.moe.experts.w2_weight": "model-00008.safetensors",
	"model.language_model.layers.17.moe.experts.w2_weight_scale": "model-00008.safetensors",
	"model.language_model.layers.17.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.17.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.17.post_feedforward_layernorm_1.weight": "model-00002.safetensors",
	"model.language_model.layers.17.post_feedforward_layernorm_2.weight": "model-00002.safetensors",
	"model.language_model.layers.17.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.17.pre_feedforward_layernorm_2.weight": "model-00002.safetensors",
	"model.language_model.layers.17.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.17.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.17.router.scale": "model-00001.safetensors",
	"model.language_model.layers.17.self_attn.k_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.17.self_attn.k_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.17.self_attn.o_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.17.self_attn.q_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.17.self_attn.q_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.18.input_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.18.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.18.mlp.down_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.18.mlp.gate_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.18.mlp.up_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.18.moe.experts.w13_weight": "model-00009.safetensors",
	"model.language_model.layers.18.moe.experts.w13_weight_scale": "model-00009.safetensors",
	"model.language_model.layers.18.moe.experts.w2_weight": "model-00009.safetensors",
	"model.language_model.layers.18.moe.experts.w2_weight_scale": "model-00009.safetensors",
	"model.language_model.layers.18.post_attention_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.18.post_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.18.post_feedforward_layernorm_1.weight": "model-00001.safetensors",
	"model.language_model.layers.18.post_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.18.pre_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.18.pre_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.18.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.18.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.18.router.scale": "model-00001.safetensors",
	"model.language_model.layers.18.self_attn.k_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.18.self_attn.k_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.18.self_attn.o_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.18.self_attn.q_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.18.self_attn.q_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.18.self_attn.v_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.19.input_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.19.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.19.mlp.down_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.19.mlp.gate_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.19.mlp.up_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.19.moe.experts.w13_weight": "model-00010.safetensors",
	"model.language_model.layers.19.moe.experts.w13_weight_scale": "model-00010.safetensors",
	"model.language_model.layers.19.moe.experts.w2_weight": "model-00009.safetensors",
	"model.language_model.layers.19.moe.experts.w2_weight_scale": "model-00009.safetensors",
	"model.language_model.layers.19.post_attention_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.19.post_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.19.post_feedforward_layernorm_1.weight": "model-00001.safetensors",
	"model.language_model.layers.19.post_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.19.pre_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.19.pre_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.19.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.19.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.19.router.scale": "model-00001.safetensors",
	"model.language_model.layers.19.self_attn.k_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.19.self_attn.k_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.19.self_attn.o_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.19.self_attn.q_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.19.self_attn.q_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.19.self_attn.v_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.2.input_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.2.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.2.mlp.down_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.2.mlp.up_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.2.moe.experts.w13_weight": "model-00010.safetensors",
	"model.language_model.layers.2.moe.experts.w13_weight_scale": "model-00010.safetensors",
	"model.language_model.layers.2.moe.experts.w2_weight": "model-00010.safetensors",
	"model.language_model.layers.2.moe.experts.w2_weight_scale": "model-00010.safetensors",
	"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.2.post_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.2.post_feedforward_layernorm_1.weight": "model-00001.safetensors",
	"model.language_model.layers.2.post_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.2.pre_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.2.pre_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.2.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.2.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.2.router.scale": "model-00001.safetensors",
	"model.language_model.layers.2.self_attn.k_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.2.self_attn.k_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.2.self_attn.o_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.2.self_attn.q_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.2.self_attn.q_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.2.self_attn.v_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.20.input_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.20.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.20.mlp.down_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.20.mlp.gate_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.20.mlp.up_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.20.moe.experts.w13_weight": "model-00011.safetensors",
	"model.language_model.layers.20.moe.experts.w13_weight_scale": "model-00011.safetensors",
	"model.language_model.layers.20.moe.experts.w2_weight": "model-00011.safetensors",
	"model.language_model.layers.20.moe.experts.w2_weight_scale": "model-00011.safetensors",
	"model.language_model.layers.20.post_attention_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.20.post_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.20.post_feedforward_layernorm_1.weight": "model-00001.safetensors",
	"model.language_model.layers.20.post_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.20.pre_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.20.pre_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.20.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.20.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.20.router.scale": "model-00001.safetensors",
	"model.language_model.layers.20.self_attn.k_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.20.self_attn.k_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.20.self_attn.o_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.20.self_attn.q_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.20.self_attn.q_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.20.self_attn.v_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.21.input_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.21.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.21.mlp.down_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.21.mlp.gate_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.21.mlp.up_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.21.moe.experts.w13_weight": "model-00012.safetensors",
	"model.language_model.layers.21.moe.experts.w13_weight_scale": "model-00012.safetensors",
	"model.language_model.layers.21.moe.experts.w2_weight": "model-00011.safetensors",
	"model.language_model.layers.21.moe.experts.w2_weight_scale": "model-00011.safetensors",
	"model.language_model.layers.21.post_attention_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.21.post_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.21.post_feedforward_layernorm_1.weight": "model-00001.safetensors",
	"model.language_model.layers.21.post_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.21.pre_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.21.pre_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.21.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.21.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.21.router.scale": "model-00001.safetensors",
	"model.language_model.layers.21.self_attn.k_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.21.self_attn.k_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.21.self_attn.o_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.21.self_attn.q_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.21.self_attn.q_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.21.self_attn.v_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.22.input_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.22.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.22.mlp.down_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.22.mlp.gate_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.22.mlp.up_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.22.moe.experts.w13_weight": "model-00012.safetensors",
	"model.language_model.layers.22.moe.experts.w13_weight_scale": "model-00012.safetensors",
	"model.language_model.layers.22.moe.experts.w2_weight": "model-00012.safetensors",
	"model.language_model.layers.22.moe.experts.w2_weight_scale": "model-00012.safetensors",
	"model.language_model.layers.22.post_attention_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.22.post_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.22.post_feedforward_layernorm_1.weight": "model-00001.safetensors",
	"model.language_model.layers.22.post_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.22.pre_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.22.pre_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.22.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.22.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.22.router.scale": "model-00001.safetensors",
	"model.language_model.layers.22.self_attn.k_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.22.self_attn.k_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.22.self_attn.o_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.22.self_attn.q_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.22.self_attn.q_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.22.self_attn.v_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.23.input_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.23.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.23.mlp.down_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.23.mlp.gate_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.23.mlp.up_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.23.moe.experts.w13_weight": "model-00013.safetensors",
	"model.language_model.layers.23.moe.experts.w13_weight_scale": "model-00013.safetensors",
	"model.language_model.layers.23.moe.experts.w2_weight": "model-00013.safetensors",
	"model.language_model.layers.23.moe.experts.w2_weight_scale": "model-00013.safetensors",
	"model.language_model.layers.23.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.23.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.23.post_feedforward_layernorm_1.weight": "model-00002.safetensors",
	"model.language_model.layers.23.post_feedforward_layernorm_2.weight": "model-00002.safetensors",
	"model.language_model.layers.23.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.23.pre_feedforward_layernorm_2.weight": "model-00002.safetensors",
	"model.language_model.layers.23.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.23.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.23.router.scale": "model-00001.safetensors",
	"model.language_model.layers.23.self_attn.k_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.23.self_attn.k_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.23.self_attn.o_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.23.self_attn.q_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.23.self_attn.q_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.24.input_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.24.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.24.mlp.down_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.24.mlp.gate_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.24.mlp.up_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.24.moe.experts.w13_weight": "model-00014.safetensors",
	"model.language_model.layers.24.moe.experts.w13_weight_scale": "model-00014.safetensors",
	"model.language_model.layers.24.moe.experts.w2_weight": "model-00013.safetensors",
	"model.language_model.layers.24.moe.experts.w2_weight_scale": "model-00013.safetensors",
	"model.language_model.layers.24.post_attention_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.24.post_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.24.post_feedforward_layernorm_1.weight": "model-00001.safetensors",
	"model.language_model.layers.24.post_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.24.pre_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.24.pre_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.24.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.24.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.24.router.scale": "model-00001.safetensors",
	"model.language_model.layers.24.self_attn.k_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.24.self_attn.k_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.24.self_attn.o_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.24.self_attn.q_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.24.self_attn.q_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.24.self_attn.v_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.25.input_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.25.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.25.mlp.down_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.25.mlp.gate_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.25.mlp.up_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.25.moe.experts.w13_weight": "model-00014.safetensors",
	"model.language_model.layers.25.moe.experts.w13_weight_scale": "model-00014.safetensors",
	"model.language_model.layers.25.moe.experts.w2_weight": "model-00014.safetensors",
	"model.language_model.layers.25.moe.experts.w2_weight_scale": "model-00014.safetensors",
	"model.language_model.layers.25.post_attention_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.25.post_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.25.post_feedforward_layernorm_1.weight": "model-00001.safetensors",
	"model.language_model.layers.25.post_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.25.pre_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.25.pre_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.25.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.25.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.25.router.scale": "model-00001.safetensors",
	"model.language_model.layers.25.self_attn.k_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.25.self_attn.k_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.25.self_attn.o_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.25.self_attn.q_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.25.self_attn.q_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.25.self_attn.v_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.26.input_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.26.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.26.mlp.down_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.26.mlp.gate_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.26.mlp.up_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.26.moe.experts.w13_weight": "model-00015.safetensors",
	"model.language_model.layers.26.moe.experts.w13_weight_scale": "model-00015.safetensors",
	"model.language_model.layers.26.moe.experts.w2_weight": "model-00015.safetensors",
	"model.language_model.layers.26.moe.experts.w2_weight_scale": "model-00015.safetensors",
	"model.language_model.layers.26.post_attention_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.26.post_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.26.post_feedforward_layernorm_1.weight": "model-00001.safetensors",
	"model.language_model.layers.26.post_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.26.pre_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.26.pre_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.26.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.26.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.26.router.scale": "model-00001.safetensors",
	"model.language_model.layers.26.self_attn.k_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.26.self_attn.k_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.26.self_attn.o_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.26.self_attn.q_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.26.self_attn.q_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.26.self_attn.v_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.27.input_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.27.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.27.mlp.down_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.27.mlp.gate_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.27.mlp.up_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.27.moe.experts.w13_weight": "model-00016.safetensors",
	"model.language_model.layers.27.moe.experts.w13_weight_scale": "model-00016.safetensors",
	"model.language_model.layers.27.moe.experts.w2_weight": "model-00015.safetensors",
	"model.language_model.layers.27.moe.experts.w2_weight_scale": "model-00015.safetensors",
	"model.language_model.layers.27.post_attention_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.27.post_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.27.post_feedforward_layernorm_1.weight": "model-00001.safetensors",
	"model.language_model.layers.27.post_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.27.pre_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.27.pre_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.27.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.27.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.27.router.scale": "model-00001.safetensors",
	"model.language_model.layers.27.self_attn.k_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.27.self_attn.k_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.27.self_attn.o_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.27.self_attn.q_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.27.self_attn.q_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.27.self_attn.v_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.28.input_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.28.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.28.mlp.down_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.28.mlp.gate_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.28.mlp.up_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.28.moe.experts.w13_weight": "model-00016.safetensors",
	"model.language_model.layers.28.moe.experts.w13_weight_scale": "model-00016.safetensors",
	"model.language_model.layers.28.moe.experts.w2_weight": "model-00016.safetensors",
	"model.language_model.layers.28.moe.experts.w2_weight_scale": "model-00016.safetensors",
	"model.language_model.layers.28.post_attention_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.28.post_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.28.post_feedforward_layernorm_1.weight": "model-00001.safetensors",
	"model.language_model.layers.28.post_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.28.pre_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.28.pre_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.28.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.28.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.28.router.scale": "model-00001.safetensors",
	"model.language_model.layers.28.self_attn.k_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.28.self_attn.k_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.28.self_attn.o_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.28.self_attn.q_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.28.self_attn.q_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.28.self_attn.v_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.29.input_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.29.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.29.mlp.down_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.29.mlp.gate_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.29.mlp.up_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.29.moe.experts.w13_weight": "model-00017.safetensors",
	"model.language_model.layers.29.moe.experts.w13_weight_scale": "model-00017.safetensors",
	"model.language_model.layers.29.moe.experts.w2_weight": "model-00017.safetensors",
	"model.language_model.layers.29.moe.experts.w2_weight_scale": "model-00017.safetensors",
	"model.language_model.layers.29.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.29.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.29.post_feedforward_layernorm_1.weight": "model-00002.safetensors",
	"model.language_model.layers.29.post_feedforward_layernorm_2.weight": "model-00002.safetensors",
	"model.language_model.layers.29.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.29.pre_feedforward_layernorm_2.weight": "model-00002.safetensors",
	"model.language_model.layers.29.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.29.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.29.router.scale": "model-00001.safetensors",
	"model.language_model.layers.29.self_attn.k_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.29.self_attn.k_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.29.self_attn.o_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.29.self_attn.q_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.29.self_attn.q_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.3.input_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.3.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.3.mlp.down_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.3.mlp.gate_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.3.mlp.up_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.3.moe.experts.w13_weight": "model-00018.safetensors",
	"model.language_model.layers.3.moe.experts.w13_weight_scale": "model-00018.safetensors",
	"model.language_model.layers.3.moe.experts.w2_weight": "model-00017.safetensors",
	"model.language_model.layers.3.moe.experts.w2_weight_scale": "model-00017.safetensors",
	"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.3.post_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.3.post_feedforward_layernorm_1.weight": "model-00001.safetensors",
	"model.language_model.layers.3.post_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.3.pre_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.3.pre_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.3.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.3.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.3.router.scale": "model-00001.safetensors",
	"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.3.self_attn.q_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.4.input_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.4.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.4.mlp.down_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.4.mlp.gate_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.4.mlp.up_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.4.moe.experts.w13_weight": "model-00018.safetensors",
	"model.language_model.layers.4.moe.experts.w13_weight_scale": "model-00018.safetensors",
	"model.language_model.layers.4.moe.experts.w2_weight": "model-00018.safetensors",
	"model.language_model.layers.4.moe.experts.w2_weight_scale": "model-00018.safetensors",
	"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.4.post_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.4.post_feedforward_layernorm_1.weight": "model-00001.safetensors",
	"model.language_model.layers.4.post_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.4.pre_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.4.pre_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.4.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.4.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.4.router.scale": "model-00001.safetensors",
	"model.language_model.layers.4.self_attn.k_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.4.self_attn.k_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.4.self_attn.o_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.4.self_attn.q_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.4.self_attn.q_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.4.self_attn.v_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.5.input_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.5.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.5.mlp.down_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.5.mlp.gate_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.5.mlp.up_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.5.moe.experts.w13_weight": "model-00019.safetensors",
	"model.language_model.layers.5.moe.experts.w13_weight_scale": "model-00019.safetensors",
	"model.language_model.layers.5.moe.experts.w2_weight": "model-00019.safetensors",
	"model.language_model.layers.5.moe.experts.w2_weight_scale": "model-00019.safetensors",
	"model.language_model.layers.5.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.5.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.5.post_feedforward_layernorm_1.weight": "model-00002.safetensors",
	"model.language_model.layers.5.post_feedforward_layernorm_2.weight": "model-00002.safetensors",
	"model.language_model.layers.5.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.5.pre_feedforward_layernorm_2.weight": "model-00002.safetensors",
	"model.language_model.layers.5.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.5.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.5.router.scale": "model-00001.safetensors",
	"model.language_model.layers.5.self_attn.k_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.5.self_attn.k_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.5.self_attn.o_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.5.self_attn.q_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.5.self_attn.q_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.6.input_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.6.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.6.mlp.down_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.6.mlp.gate_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.6.mlp.up_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.6.moe.experts.w13_weight": "model-00020.safetensors",
	"model.language_model.layers.6.moe.experts.w13_weight_scale": "model-00020.safetensors",
	"model.language_model.layers.6.moe.experts.w2_weight": "model-00019.safetensors",
	"model.language_model.layers.6.moe.experts.w2_weight_scale": "model-00019.safetensors",
	"model.language_model.layers.6.post_attention_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.6.post_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.6.post_feedforward_layernorm_1.weight": "model-00001.safetensors",
	"model.language_model.layers.6.post_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.6.pre_feedforward_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.6.pre_feedforward_layernorm_2.weight": "model-00001.safetensors",
	"model.language_model.layers.6.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.6.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.6.router.scale": "model-00001.safetensors",
	"model.language_model.layers.6.self_attn.k_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.6.self_attn.k_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.6.self_attn.o_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.6.self_attn.q_norm.weight": "model-00001.safetensors",
	"model.language_model.layers.6.self_attn.q_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.6.self_attn.v_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.7.input_layernorm.weight": "model-00001.safetensors",
	"model.language_model.layers.7.layer_scalar": "model-00001.safetensors",
	"model.language_model.layers.7.mlp.down_proj.weight": "model-00001.safetensors",
	"model.language_model.layers.7.mlp.gate_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.7.mlp.up_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.7.moe.experts.w13_weight": "model-00020.safetensors",
	"model.language_model.layers.7.moe.experts.w13_weight_scale": "model-00020.safetensors",
	"model.language_model.layers.7.moe.experts.w2_weight": "model-00020.safetensors",
	"model.language_model.layers.7.moe.experts.w2_weight_scale": "model-00020.safetensors",
	"model.language_model.layers.7.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.7.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.7.post_feedforward_layernorm_1.weight": "model-00002.safetensors",
	"model.language_model.layers.7.post_feedforward_layernorm_2.weight": "model-00002.safetensors",
	"model.language_model.layers.7.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.7.pre_feedforward_layernorm_2.weight": "model-00002.safetensors",
	"model.language_model.layers.7.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.7.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.7.router.scale": "model-00002.safetensors",
	"model.language_model.layers.7.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.language_model.layers.7.self_attn.k_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.7.self_attn.o_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.7.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.language_model.layers.7.self_attn.q_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.7.self_attn.v_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.8.input_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.8.layer_scalar": "model-00002.safetensors",
	"model.language_model.layers.8.mlp.down_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.8.mlp.gate_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.8.mlp.up_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.8.moe.experts.w13_weight": "model-00021.safetensors",
	"model.language_model.layers.8.moe.experts.w13_weight_scale": "model-00021.safetensors",
	"model.language_model.layers.8.moe.experts.w2_weight": "model-00021.safetensors",
	"model.language_model.layers.8.moe.experts.w2_weight_scale": "model-00021.safetensors",
	"model.language_model.layers.8.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.8.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.8.post_feedforward_layernorm_1.weight": "model-00002.safetensors",
	"model.language_model.layers.8.post_feedforward_layernorm_2.weight": "model-00002.safetensors",
	"model.language_model.layers.8.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.8.pre_feedforward_layernorm_2.weight": "model-00002.safetensors",
	"model.language_model.layers.8.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.8.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.8.router.scale": "model-00002.safetensors",
	"model.language_model.layers.8.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.language_model.layers.8.self_attn.k_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.8.self_attn.o_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.8.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.language_model.layers.8.self_attn.q_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.8.self_attn.v_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.9.input_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.9.layer_scalar": "model-00002.safetensors",
	"model.language_model.layers.9.mlp.down_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.9.mlp.gate_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.9.mlp.up_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.9.moe.experts.w13_weight": "model-00022.safetensors",
	"model.language_model.layers.9.moe.experts.w13_weight_scale": "model-00022.safetensors",
	"model.language_model.layers.9.moe.experts.w2_weight": "model-00021.safetensors",
	"model.language_model.layers.9.moe.experts.w2_weight_scale": "model-00021.safetensors",
	"model.language_model.layers.9.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.9.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.9.post_feedforward_layernorm_1.weight": "model-00002.safetensors",
	"model.language_model.layers.9.post_feedforward_layernorm_2.weight": "model-00002.safetensors",
	"model.language_model.layers.9.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.language_model.layers.9.pre_feedforward_layernorm_2.weight": "model-00002.safetensors",
	"model.language_model.layers.9.router.per_expert_scale": "model-00022.safetensors",
	"model.language_model.layers.9.router.proj.weight": "model-00022.safetensors",
	"model.language_model.layers.9.router.scale": "model-00002.safetensors",
	"model.language_model.layers.9.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.language_model.layers.9.self_attn.k_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.9.self_attn.o_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.9.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.language_model.layers.9.self_attn.q_proj.weight": "model-00002.safetensors",
	"model.language_model.layers.9.self_attn.v_proj.weight": "model-00002.safetensors",
	"model.language_model.norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.0.input_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.0.mlp.down_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.0.mlp.gate_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.0.mlp.up_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.0.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.0.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.0.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.0.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.0.self_attn.k_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.0.self_attn.o_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.0.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.0.self_attn.q_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.0.self_attn.v_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.1.input_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.1.mlp.down_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.1.mlp.gate_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.1.mlp.up_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.1.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.1.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.1.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.1.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.1.self_attn.k_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.1.self_attn.o_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.1.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.1.self_attn.q_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.1.self_attn.v_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.10.input_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.10.mlp.down_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.10.mlp.gate_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.10.mlp.up_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.10.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.10.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.10.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.10.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.10.self_attn.k_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.10.self_attn.o_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.10.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.10.self_attn.q_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.10.self_attn.v_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.11.input_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.11.mlp.down_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.11.mlp.gate_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.11.mlp.up_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.11.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.11.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.11.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.11.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.11.self_attn.k_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.11.self_attn.o_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.11.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.11.self_attn.q_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.11.self_attn.v_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.12.input_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.12.mlp.down_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.12.mlp.gate_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.12.mlp.up_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.12.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.12.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.12.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.12.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.12.self_attn.k_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.12.self_attn.o_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.12.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.12.self_attn.q_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.12.self_attn.v_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.13.input_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.13.mlp.down_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.13.mlp.gate_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.13.mlp.up_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.13.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.13.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.13.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.13.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.13.self_attn.k_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.13.self_attn.o_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.13.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.13.self_attn.q_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.13.self_attn.v_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.14.input_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.14.mlp.down_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.14.mlp.gate_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.14.mlp.up_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.14.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.14.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.14.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.14.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.14.self_attn.k_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.14.self_attn.o_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.14.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.14.self_attn.q_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.14.self_attn.v_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.15.input_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.15.mlp.down_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.15.mlp.gate_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.15.mlp.up_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.15.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.15.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.15.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.15.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.15.self_attn.k_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.15.self_attn.o_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.15.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.15.self_attn.q_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.15.self_attn.v_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.16.input_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.16.mlp.down_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.16.mlp.gate_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.16.mlp.up_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.16.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.16.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.16.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.16.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.16.self_attn.k_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.16.self_attn.o_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.16.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.16.self_attn.q_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.16.self_attn.v_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.17.input_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.17.mlp.down_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.17.mlp.gate_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.17.mlp.up_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.17.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.17.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.17.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.17.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.17.self_attn.k_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.17.self_attn.o_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.17.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.17.self_attn.q_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.17.self_attn.v_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.18.input_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.18.mlp.down_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.18.mlp.gate_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.18.mlp.up_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.18.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.18.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.18.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.18.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.18.self_attn.k_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.18.self_attn.o_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.18.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.18.self_attn.q_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.18.self_attn.v_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.19.input_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.19.mlp.down_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.19.mlp.gate_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.19.mlp.up_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.19.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.19.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.19.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.19.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.19.self_attn.k_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.19.self_attn.o_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.19.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.19.self_attn.q_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.19.self_attn.v_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.2.input_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.2.mlp.down_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.2.mlp.gate_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.2.mlp.up_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.2.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.2.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.2.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.2.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.2.self_attn.k_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.2.self_attn.o_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.2.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.2.self_attn.q_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.2.self_attn.v_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.20.input_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.20.mlp.down_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.20.mlp.gate_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.20.mlp.up_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.20.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.20.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.20.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.20.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.20.self_attn.k_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.20.self_attn.o_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.20.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.20.self_attn.q_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.20.self_attn.v_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.21.input_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.21.mlp.down_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.21.mlp.gate_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.21.mlp.up_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.21.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.21.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.21.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.21.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.21.self_attn.k_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.21.self_attn.o_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.21.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.21.self_attn.q_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.21.self_attn.v_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.22.input_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.22.mlp.down_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.22.mlp.gate_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.22.mlp.up_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.22.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.22.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.22.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.22.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.22.self_attn.k_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.22.self_attn.o_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.22.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.22.self_attn.q_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.22.self_attn.v_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.23.input_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.23.mlp.down_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.23.mlp.gate_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.23.mlp.up_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.23.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.23.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.23.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.23.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.23.self_attn.k_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.23.self_attn.o_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.23.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.23.self_attn.q_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.23.self_attn.v_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.24.input_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.24.mlp.down_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.24.mlp.gate_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.24.mlp.up_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.24.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.24.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.24.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.24.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.24.self_attn.k_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.24.self_attn.o_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.24.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.24.self_attn.q_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.24.self_attn.v_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.25.input_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.25.mlp.down_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.25.mlp.gate_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.25.mlp.up_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.25.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.25.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.25.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.25.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.25.self_attn.k_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.25.self_attn.o_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.25.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.25.self_attn.q_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.25.self_attn.v_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.26.input_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.26.mlp.down_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.26.mlp.gate_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.26.mlp.up_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.26.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.26.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.26.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.26.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.26.self_attn.k_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.26.self_attn.o_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.26.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.26.self_attn.q_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.26.self_attn.v_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.3.input_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.3.mlp.down_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.3.mlp.gate_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.3.mlp.up_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.3.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.3.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.3.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.3.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.3.self_attn.k_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.3.self_attn.o_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.3.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.3.self_attn.q_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.3.self_attn.v_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.4.input_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.4.mlp.down_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.4.mlp.gate_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.4.mlp.up_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.4.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.4.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.4.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.4.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.4.self_attn.k_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.4.self_attn.o_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.4.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.4.self_attn.q_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.4.self_attn.v_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.5.input_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.5.mlp.down_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.5.mlp.gate_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.5.mlp.up_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.5.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.5.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.5.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.5.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.5.self_attn.k_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.5.self_attn.o_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.5.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.5.self_attn.q_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.5.self_attn.v_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.6.input_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.6.mlp.down_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.6.mlp.gate_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.6.mlp.up_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.6.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.6.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.6.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.6.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.6.self_attn.k_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.6.self_attn.o_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.6.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.6.self_attn.q_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.6.self_attn.v_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.7.input_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.7.mlp.down_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.7.mlp.gate_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.7.mlp.up_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.7.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.7.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.7.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.7.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.7.self_attn.k_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.7.self_attn.o_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.7.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.7.self_attn.q_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.7.self_attn.v_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.8.input_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.8.mlp.down_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.8.mlp.gate_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.8.mlp.up_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.8.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.8.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.8.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.8.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.8.self_attn.k_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.8.self_attn.o_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.8.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.8.self_attn.q_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.8.self_attn.v_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.9.input_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.9.mlp.down_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.9.mlp.gate_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.9.mlp.up_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.9.post_attention_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.9.post_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.9.pre_feedforward_layernorm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.9.self_attn.k_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.9.self_attn.k_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.9.self_attn.o_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.9.self_attn.q_norm.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.9.self_attn.q_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.encoder.layers.9.self_attn.v_proj.linear.weight": "model-00002.safetensors",
	"model.vision_tower.patch_embedder.input_proj.weight": "model-00002.safetensors",
	"model.vision_tower.patch_embedder.position_embedding_table": "model-00002.safetensors",
	"model.vision_tower.std_bias": "model-00002.safetensors",
	"model.vision_tower.std_scale": "model-00002.safetensors"
	}
	}