Instructions to use eousphoros/persona_lambda_27b_v10-fp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use eousphoros/persona_lambda_27b_v10-fp8 with Transformers:

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

pipe = pipeline("image-text-to-text", model="eousphoros/persona_lambda_27b_v10-fp8")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("eousphoros/persona_lambda_27b_v10-fp8")
model = AutoModelForMultimodalLM.from_pretrained("eousphoros/persona_lambda_27b_v10-fp8", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use eousphoros/persona_lambda_27b_v10-fp8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "eousphoros/persona_lambda_27b_v10-fp8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "eousphoros/persona_lambda_27b_v10-fp8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/eousphoros/persona_lambda_27b_v10-fp8

SGLang

How to use eousphoros/persona_lambda_27b_v10-fp8 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 "eousphoros/persona_lambda_27b_v10-fp8" \
    --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": "eousphoros/persona_lambda_27b_v10-fp8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "eousphoros/persona_lambda_27b_v10-fp8" \
        --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": "eousphoros/persona_lambda_27b_v10-fp8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use eousphoros/persona_lambda_27b_v10-fp8 with Docker Model Runner:
```
docker model run hf.co/eousphoros/persona_lambda_27b_v10-fp8
```

persona_lambda_27b_v10-fp8 / config.json

eousphoros

Upload persona_lambda_27b_v10-fp8

9fb6b50 verified 7 days ago

Raw History Blame Contribute Delete

51.4 kB

{
  "architectures": [
    "Qwen3_5ForConditionalGeneration"
  ],
  "image_token_id": 248056,
  "language_model_only": false,
  "model_type": "qwen3_5",
  "text_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "attn_output_gate": true,
    "bos_token_id": 248044,
    "dtype": "bfloat16",
    "eos_token_id": 248044,
    "full_attention_interval": 4,
    "head_dim": 256,
    "hidden_act": "silu",
    "hidden_size": 5120,
    "initializer_range": 0.02,
    "intermediate_size": 17408,
    "layer_types": [
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention"
    ],
    "linear_conv_kernel_dim": 4,
    "linear_key_head_dim": 128,
    "linear_num_key_heads": 16,
    "linear_num_value_heads": 48,
    "linear_value_head_dim": 128,
    "mamba_ssm_dtype": "float32",
    "max_position_embeddings": 262144,
    "model_type": "qwen3_5_text",
    "mtp_num_hidden_layers": 1,
    "mtp_use_dedicated_embeddings": false,
    "num_attention_heads": 24,
    "num_hidden_layers": 64,
    "num_key_value_heads": 4,
    "output_gate_type": "swish",
    "pad_token_id": null,
    "partial_rotary_factor": 0.25,
    "rms_norm_eps": 1e-06,
    "rope_parameters": {
      "mrope_interleaved": true,
      "mrope_section": [
        11,
        11,
        10
      ],
      "partial_rotary_factor": 0.25,
      "rope_theta": 10000000,
      "rope_type": "default"
    },
    "tie_word_embeddings": false,
    "use_cache": true,
    "vocab_size": 248320
  },
  "tie_word_embeddings": false,
  "transformers_version": "5.8.0.dev0",
  "video_token_id": 248057,
  "vision_config": {
    "deepstack_visual_indexes": [],
    "depth": 27,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 1152,
    "in_channels": 3,
    "initializer_range": 0.02,
    "intermediate_size": 4304,
    "model_type": "qwen3_5",
    "num_heads": 16,
    "num_position_embeddings": 2304,
    "out_hidden_size": 5120,
    "patch_size": 16,
    "spatial_merge_size": 2,
    "temporal_patch_size": 2
  },
  "vision_end_token_id": 248054,
  "vision_start_token_id": 248053,
  "quantization_config": {
    "activation_scheme": "dynamic",
    "fmt": "e4m3",
    "quant_method": "fp8",
    "modules_to_not_convert": [
      "model.visual.blocks.0.attn.proj",
      "model.visual.blocks.0.attn.qkv",
      "model.visual.blocks.0.mlp.linear_fc1",
      "model.visual.blocks.0.mlp.linear_fc2",
      "visual.blocks.0.attn.proj",
      "visual.blocks.0.attn.qkv_proj",
      "visual.blocks.0.mlp.linear_fc1",
      "visual.blocks.0.mlp.linear_fc2",
      "model.visual.blocks.1.attn.proj",
      "model.visual.blocks.1.attn.qkv",
      "model.visual.blocks.1.mlp.linear_fc1",
      "model.visual.blocks.1.mlp.linear_fc2",
      "visual.blocks.1.attn.proj",
      "visual.blocks.1.attn.qkv_proj",
      "visual.blocks.1.mlp.linear_fc1",
      "visual.blocks.1.mlp.linear_fc2",
      "model.visual.blocks.2.attn.proj",
      "model.visual.blocks.2.attn.qkv",
      "model.visual.blocks.2.mlp.linear_fc1",
      "model.visual.blocks.2.mlp.linear_fc2",
      "visual.blocks.2.attn.proj",
      "visual.blocks.2.attn.qkv_proj",
      "visual.blocks.2.mlp.linear_fc1",
      "visual.blocks.2.mlp.linear_fc2",
      "model.visual.blocks.3.attn.proj",
      "model.visual.blocks.3.attn.qkv",
      "model.visual.blocks.3.mlp.linear_fc1",
      "model.visual.blocks.3.mlp.linear_fc2",
      "visual.blocks.3.attn.proj",
      "visual.blocks.3.attn.qkv_proj",
      "visual.blocks.3.mlp.linear_fc1",
      "visual.blocks.3.mlp.linear_fc2",
      "model.visual.blocks.4.attn.proj",
      "model.visual.blocks.4.attn.qkv",
      "model.visual.blocks.4.mlp.linear_fc1",
      "model.visual.blocks.4.mlp.linear_fc2",
      "visual.blocks.4.attn.proj",
      "visual.blocks.4.attn.qkv_proj",
      "visual.blocks.4.mlp.linear_fc1",
      "visual.blocks.4.mlp.linear_fc2",
      "model.visual.blocks.5.attn.proj",
      "model.visual.blocks.5.attn.qkv",
      "model.visual.blocks.5.mlp.linear_fc1",
      "model.visual.blocks.5.mlp.linear_fc2",
      "visual.blocks.5.attn.proj",
      "visual.blocks.5.attn.qkv_proj",
      "visual.blocks.5.mlp.linear_fc1",
      "visual.blocks.5.mlp.linear_fc2",
      "model.visual.blocks.6.attn.proj",
      "model.visual.blocks.6.attn.qkv",
      "model.visual.blocks.6.mlp.linear_fc1",
      "model.visual.blocks.6.mlp.linear_fc2",
      "visual.blocks.6.attn.proj",
      "visual.blocks.6.attn.qkv_proj",
      "visual.blocks.6.mlp.linear_fc1",
      "visual.blocks.6.mlp.linear_fc2",
      "model.visual.blocks.7.attn.proj",
      "model.visual.blocks.7.attn.qkv",
      "model.visual.blocks.7.mlp.linear_fc1",
      "model.visual.blocks.7.mlp.linear_fc2",
      "visual.blocks.7.attn.proj",
      "visual.blocks.7.attn.qkv_proj",
      "visual.blocks.7.mlp.linear_fc1",
      "visual.blocks.7.mlp.linear_fc2",
      "model.visual.blocks.8.attn.proj",
      "model.visual.blocks.8.attn.qkv",
      "model.visual.blocks.8.mlp.linear_fc1",
      "model.visual.blocks.8.mlp.linear_fc2",
      "visual.blocks.8.attn.proj",
      "visual.blocks.8.attn.qkv_proj",
      "visual.blocks.8.mlp.linear_fc1",
      "visual.blocks.8.mlp.linear_fc2",
      "model.visual.blocks.9.attn.proj",
      "model.visual.blocks.9.attn.qkv",
      "model.visual.blocks.9.mlp.linear_fc1",
      "model.visual.blocks.9.mlp.linear_fc2",
      "visual.blocks.9.attn.proj",
      "visual.blocks.9.attn.qkv_proj",
      "visual.blocks.9.mlp.linear_fc1",
      "visual.blocks.9.mlp.linear_fc2",
      "model.visual.blocks.10.attn.proj",
      "model.visual.blocks.10.attn.qkv",
      "model.visual.blocks.10.mlp.linear_fc1",
      "model.visual.blocks.10.mlp.linear_fc2",
      "visual.blocks.10.attn.proj",
      "visual.blocks.10.attn.qkv_proj",
      "visual.blocks.10.mlp.linear_fc1",
      "visual.blocks.10.mlp.linear_fc2",
      "model.visual.blocks.11.attn.proj",
      "model.visual.blocks.11.attn.qkv",
      "model.visual.blocks.11.mlp.linear_fc1",
      "model.visual.blocks.11.mlp.linear_fc2",
      "visual.blocks.11.attn.proj",
      "visual.blocks.11.attn.qkv_proj",
      "visual.blocks.11.mlp.linear_fc1",
      "visual.blocks.11.mlp.linear_fc2",
      "model.visual.blocks.12.attn.proj",
      "model.visual.blocks.12.attn.qkv",
      "model.visual.blocks.12.mlp.linear_fc1",
      "model.visual.blocks.12.mlp.linear_fc2",
      "visual.blocks.12.attn.proj",
      "visual.blocks.12.attn.qkv_proj",
      "visual.blocks.12.mlp.linear_fc1",
      "visual.blocks.12.mlp.linear_fc2",
      "model.visual.blocks.13.attn.proj",
      "model.visual.blocks.13.attn.qkv",
      "model.visual.blocks.13.mlp.linear_fc1",
      "model.visual.blocks.13.mlp.linear_fc2",
      "visual.blocks.13.attn.proj",
      "visual.blocks.13.attn.qkv_proj",
      "visual.blocks.13.mlp.linear_fc1",
      "visual.blocks.13.mlp.linear_fc2",
      "model.visual.blocks.14.attn.proj",
      "model.visual.blocks.14.attn.qkv",
      "model.visual.blocks.14.mlp.linear_fc1",
      "model.visual.blocks.14.mlp.linear_fc2",
      "visual.blocks.14.attn.proj",
      "visual.blocks.14.attn.qkv_proj",
      "visual.blocks.14.mlp.linear_fc1",
      "visual.blocks.14.mlp.linear_fc2",
      "model.visual.blocks.15.attn.proj",
      "model.visual.blocks.15.attn.qkv",
      "model.visual.blocks.15.mlp.linear_fc1",
      "model.visual.blocks.15.mlp.linear_fc2",
      "visual.blocks.15.attn.proj",
      "visual.blocks.15.attn.qkv_proj",
      "visual.blocks.15.mlp.linear_fc1",
      "visual.blocks.15.mlp.linear_fc2",
      "model.visual.blocks.16.attn.proj",
      "model.visual.blocks.16.attn.qkv",
      "model.visual.blocks.16.mlp.linear_fc1",
      "model.visual.blocks.16.mlp.linear_fc2",
      "visual.blocks.16.attn.proj",
      "visual.blocks.16.attn.qkv_proj",
      "visual.blocks.16.mlp.linear_fc1",
      "visual.blocks.16.mlp.linear_fc2",
      "model.visual.blocks.17.attn.proj",
      "model.visual.blocks.17.attn.qkv",
      "model.visual.blocks.17.mlp.linear_fc1",
      "model.visual.blocks.17.mlp.linear_fc2",
      "visual.blocks.17.attn.proj",
      "visual.blocks.17.attn.qkv_proj",
      "visual.blocks.17.mlp.linear_fc1",
      "visual.blocks.17.mlp.linear_fc2",
      "model.visual.blocks.18.attn.proj",
      "model.visual.blocks.18.attn.qkv",
      "model.visual.blocks.18.mlp.linear_fc1",
      "model.visual.blocks.18.mlp.linear_fc2",
      "visual.blocks.18.attn.proj",
      "visual.blocks.18.attn.qkv_proj",
      "visual.blocks.18.mlp.linear_fc1",
      "visual.blocks.18.mlp.linear_fc2",
      "model.visual.blocks.19.attn.proj",
      "model.visual.blocks.19.attn.qkv",
      "model.visual.blocks.19.mlp.linear_fc1",
      "model.visual.blocks.19.mlp.linear_fc2",
      "visual.blocks.19.attn.proj",
      "visual.blocks.19.attn.qkv_proj",
      "visual.blocks.19.mlp.linear_fc1",
      "visual.blocks.19.mlp.linear_fc2",
      "model.visual.blocks.20.attn.proj",
      "model.visual.blocks.20.attn.qkv",
      "model.visual.blocks.20.mlp.linear_fc1",
      "model.visual.blocks.20.mlp.linear_fc2",
      "visual.blocks.20.attn.proj",
      "visual.blocks.20.attn.qkv_proj",
      "visual.blocks.20.mlp.linear_fc1",
      "visual.blocks.20.mlp.linear_fc2",
      "model.visual.blocks.21.attn.proj",
      "model.visual.blocks.21.attn.qkv",
      "model.visual.blocks.21.mlp.linear_fc1",
      "model.visual.blocks.21.mlp.linear_fc2",
      "visual.blocks.21.attn.proj",
      "visual.blocks.21.attn.qkv_proj",
      "visual.blocks.21.mlp.linear_fc1",
      "visual.blocks.21.mlp.linear_fc2",
      "model.visual.blocks.22.attn.proj",
      "model.visual.blocks.22.attn.qkv",
      "model.visual.blocks.22.mlp.linear_fc1",
      "model.visual.blocks.22.mlp.linear_fc2",
      "visual.blocks.22.attn.proj",
      "visual.blocks.22.attn.qkv_proj",
      "visual.blocks.22.mlp.linear_fc1",
      "visual.blocks.22.mlp.linear_fc2",
      "model.visual.blocks.23.attn.proj",
      "model.visual.blocks.23.attn.qkv",
      "model.visual.blocks.23.mlp.linear_fc1",
      "model.visual.blocks.23.mlp.linear_fc2",
      "visual.blocks.23.attn.proj",
      "visual.blocks.23.attn.qkv_proj",
      "visual.blocks.23.mlp.linear_fc1",
      "visual.blocks.23.mlp.linear_fc2",
      "model.visual.blocks.24.attn.proj",
      "model.visual.blocks.24.attn.qkv",
      "model.visual.blocks.24.mlp.linear_fc1",
      "model.visual.blocks.24.mlp.linear_fc2",
      "visual.blocks.24.attn.proj",
      "visual.blocks.24.attn.qkv_proj",
      "visual.blocks.24.mlp.linear_fc1",
      "visual.blocks.24.mlp.linear_fc2",
      "model.visual.blocks.25.attn.proj",
      "model.visual.blocks.25.attn.qkv",
      "model.visual.blocks.25.mlp.linear_fc1",
      "model.visual.blocks.25.mlp.linear_fc2",
      "visual.blocks.25.attn.proj",
      "visual.blocks.25.attn.qkv_proj",
      "visual.blocks.25.mlp.linear_fc1",
      "visual.blocks.25.mlp.linear_fc2",
      "model.visual.blocks.26.attn.proj",
      "model.visual.blocks.26.attn.qkv",
      "model.visual.blocks.26.mlp.linear_fc1",
      "model.visual.blocks.26.mlp.linear_fc2",
      "visual.blocks.26.attn.proj",
      "visual.blocks.26.attn.qkv_proj",
      "visual.blocks.26.mlp.linear_fc1",
      "visual.blocks.26.mlp.linear_fc2",
      "model.visual.deepstack_merger_list.0.linear_fc1",
      "model.visual.deepstack_merger_list.0.linear_fc2",
      "model.visual.deepstack_merger_list.0.norm",
      "visual.deepstack_merger_list.0.linear_fc1",
      "visual.deepstack_merger_list.0.linear_fc2",
      "visual.deepstack_merger_list.0.norm",
      "model.visual.deepstack_merger_list.1.linear_fc1",
      "model.visual.deepstack_merger_list.1.linear_fc2",
      "model.visual.deepstack_merger_list.1.norm",
      "visual.deepstack_merger_list.1.linear_fc1",
      "visual.deepstack_merger_list.1.linear_fc2",
      "visual.deepstack_merger_list.1.norm",
      "model.visual.deepstack_merger_list.2.linear_fc1",
      "model.visual.deepstack_merger_list.2.linear_fc2",
      "model.visual.deepstack_merger_list.2.norm",
      "visual.deepstack_merger_list.2.linear_fc1",
      "visual.deepstack_merger_list.2.linear_fc2",
      "visual.deepstack_merger_list.2.norm",
      "model.visual.merger.linear_fc1",
      "model.visual.merger.linear_fc2",
      "model.visual.merger.norm",
      "model.visual.patch_embed.proj",
      "model.visual.pos_embed",
      "visual.merger.linear_fc1",
      "visual.merger.linear_fc2",
      "visual.merger.norm",
      "visual.patch_embed.proj",
      "visual.pos_embed",
      "visual",
      "model.visual",
      "lm_head",
      "model.embed_tokens",
      "model.language_model.layers.0.input_layernorm",
      "model.language_model.layers.0.mlp.shared_expert_gate",
      "model.language_model.layers.0.post_attention_layernorm",
      "model.language_model.layers.0.mlp.gate",
      "model.language_model.layers.0.linear_attn.A_log",
      "model.language_model.layers.0.linear_attn.conv1d",
      "model.language_model.layers.0.linear_attn.dt_bias",
      "model.language_model.layers.0.linear_attn.in_proj_ba",
      "model.language_model.layers.0.linear_attn.in_proj_b",
      "model.language_model.layers.0.linear_attn.in_proj_a",
      "model.language_model.layers.0.linear_attn.norm",
      "model.language_model.layers.1.input_layernorm",
      "model.language_model.layers.1.mlp.shared_expert_gate",
      "model.language_model.layers.1.post_attention_layernorm",
      "model.language_model.layers.1.mlp.gate",
      "model.language_model.layers.1.linear_attn.A_log",
      "model.language_model.layers.1.linear_attn.conv1d",
      "model.language_model.layers.1.linear_attn.dt_bias",
      "model.language_model.layers.1.linear_attn.in_proj_ba",
      "model.language_model.layers.1.linear_attn.in_proj_b",
      "model.language_model.layers.1.linear_attn.in_proj_a",
      "model.language_model.layers.1.linear_attn.norm",
      "model.language_model.layers.2.input_layernorm",
      "model.language_model.layers.2.mlp.shared_expert_gate",
      "model.language_model.layers.2.post_attention_layernorm",
      "model.language_model.layers.2.mlp.gate",
      "model.language_model.layers.2.linear_attn.A_log",
      "model.language_model.layers.2.linear_attn.conv1d",
      "model.language_model.layers.2.linear_attn.dt_bias",
      "model.language_model.layers.2.linear_attn.in_proj_ba",
      "model.language_model.layers.2.linear_attn.in_proj_b",
      "model.language_model.layers.2.linear_attn.in_proj_a",
      "model.language_model.layers.2.linear_attn.norm",
      "model.language_model.layers.3.input_layernorm",
      "model.language_model.layers.3.mlp.shared_expert_gate",
      "model.language_model.layers.3.post_attention_layernorm",
      "model.language_model.layers.3.mlp.gate",
      "model.language_model.layers.3.self_attn.k_norm",
      "model.language_model.layers.3.self_attn.q_norm",
      "model.language_model.layers.4.input_layernorm",
      "model.language_model.layers.4.mlp.shared_expert_gate",
      "model.language_model.layers.4.post_attention_layernorm",
      "model.language_model.layers.4.mlp.gate",
      "model.language_model.layers.4.linear_attn.A_log",
      "model.language_model.layers.4.linear_attn.conv1d",
      "model.language_model.layers.4.linear_attn.dt_bias",
      "model.language_model.layers.4.linear_attn.in_proj_ba",
      "model.language_model.layers.4.linear_attn.in_proj_b",
      "model.language_model.layers.4.linear_attn.in_proj_a",
      "model.language_model.layers.4.linear_attn.norm",
      "model.language_model.layers.5.input_layernorm",
      "model.language_model.layers.5.mlp.shared_expert_gate",
      "model.language_model.layers.5.post_attention_layernorm",
      "model.language_model.layers.5.mlp.gate",
      "model.language_model.layers.5.linear_attn.A_log",
      "model.language_model.layers.5.linear_attn.conv1d",
      "model.language_model.layers.5.linear_attn.dt_bias",
      "model.language_model.layers.5.linear_attn.in_proj_ba",
      "model.language_model.layers.5.linear_attn.in_proj_b",
      "model.language_model.layers.5.linear_attn.in_proj_a",
      "model.language_model.layers.5.linear_attn.norm",
      "model.language_model.layers.6.input_layernorm",
      "model.language_model.layers.6.mlp.shared_expert_gate",
      "model.language_model.layers.6.post_attention_layernorm",
      "model.language_model.layers.6.mlp.gate",
      "model.language_model.layers.6.linear_attn.A_log",
      "model.language_model.layers.6.linear_attn.conv1d",
      "model.language_model.layers.6.linear_attn.dt_bias",
      "model.language_model.layers.6.linear_attn.in_proj_ba",
      "model.language_model.layers.6.linear_attn.in_proj_b",
      "model.language_model.layers.6.linear_attn.in_proj_a",
      "model.language_model.layers.6.linear_attn.norm",
      "model.language_model.layers.7.input_layernorm",
      "model.language_model.layers.7.mlp.shared_expert_gate",
      "model.language_model.layers.7.post_attention_layernorm",
      "model.language_model.layers.7.mlp.gate",
      "model.language_model.layers.7.self_attn.k_norm",
      "model.language_model.layers.7.self_attn.q_norm",
      "model.language_model.layers.8.input_layernorm",
      "model.language_model.layers.8.mlp.shared_expert_gate",
      "model.language_model.layers.8.post_attention_layernorm",
      "model.language_model.layers.8.mlp.gate",
      "model.language_model.layers.8.linear_attn.A_log",
      "model.language_model.layers.8.linear_attn.conv1d",
      "model.language_model.layers.8.linear_attn.dt_bias",
      "model.language_model.layers.8.linear_attn.in_proj_ba",
      "model.language_model.layers.8.linear_attn.in_proj_b",
      "model.language_model.layers.8.linear_attn.in_proj_a",
      "model.language_model.layers.8.linear_attn.norm",
      "model.language_model.layers.9.input_layernorm",
      "model.language_model.layers.9.mlp.shared_expert_gate",
      "model.language_model.layers.9.post_attention_layernorm",
      "model.language_model.layers.9.mlp.gate",
      "model.language_model.layers.9.linear_attn.A_log",
      "model.language_model.layers.9.linear_attn.conv1d",
      "model.language_model.layers.9.linear_attn.dt_bias",
      "model.language_model.layers.9.linear_attn.in_proj_ba",
      "model.language_model.layers.9.linear_attn.in_proj_b",
      "model.language_model.layers.9.linear_attn.in_proj_a",
      "model.language_model.layers.9.linear_attn.norm",
      "model.language_model.layers.10.input_layernorm",
      "model.language_model.layers.10.mlp.shared_expert_gate",
      "model.language_model.layers.10.post_attention_layernorm",
      "model.language_model.layers.10.mlp.gate",
      "model.language_model.layers.10.linear_attn.A_log",
      "model.language_model.layers.10.linear_attn.conv1d",
      "model.language_model.layers.10.linear_attn.dt_bias",
      "model.language_model.layers.10.linear_attn.in_proj_ba",
      "model.language_model.layers.10.linear_attn.in_proj_b",
      "model.language_model.layers.10.linear_attn.in_proj_a",
      "model.language_model.layers.10.linear_attn.norm",
      "model.language_model.layers.11.input_layernorm",
      "model.language_model.layers.11.mlp.shared_expert_gate",
      "model.language_model.layers.11.post_attention_layernorm",
      "model.language_model.layers.11.mlp.gate",
      "model.language_model.layers.11.self_attn.k_norm",
      "model.language_model.layers.11.self_attn.q_norm",
      "model.language_model.layers.12.input_layernorm",
      "model.language_model.layers.12.mlp.shared_expert_gate",
      "model.language_model.layers.12.post_attention_layernorm",
      "model.language_model.layers.12.mlp.gate",
      "model.language_model.layers.12.linear_attn.A_log",
      "model.language_model.layers.12.linear_attn.conv1d",
      "model.language_model.layers.12.linear_attn.dt_bias",
      "model.language_model.layers.12.linear_attn.in_proj_ba",
      "model.language_model.layers.12.linear_attn.in_proj_b",
      "model.language_model.layers.12.linear_attn.in_proj_a",
      "model.language_model.layers.12.linear_attn.norm",
      "model.language_model.layers.13.input_layernorm",
      "model.language_model.layers.13.mlp.shared_expert_gate",
      "model.language_model.layers.13.post_attention_layernorm",
      "model.language_model.layers.13.mlp.gate",
      "model.language_model.layers.13.linear_attn.A_log",
      "model.language_model.layers.13.linear_attn.conv1d",
      "model.language_model.layers.13.linear_attn.dt_bias",
      "model.language_model.layers.13.linear_attn.in_proj_ba",
      "model.language_model.layers.13.linear_attn.in_proj_b",
      "model.language_model.layers.13.linear_attn.in_proj_a",
      "model.language_model.layers.13.linear_attn.norm",
      "model.language_model.layers.14.input_layernorm",
      "model.language_model.layers.14.mlp.shared_expert_gate",
      "model.language_model.layers.14.post_attention_layernorm",
      "model.language_model.layers.14.mlp.gate",
      "model.language_model.layers.14.linear_attn.A_log",
      "model.language_model.layers.14.linear_attn.conv1d",
      "model.language_model.layers.14.linear_attn.dt_bias",
      "model.language_model.layers.14.linear_attn.in_proj_ba",
      "model.language_model.layers.14.linear_attn.in_proj_b",
      "model.language_model.layers.14.linear_attn.in_proj_a",
      "model.language_model.layers.14.linear_attn.norm",
      "model.language_model.layers.15.input_layernorm",
      "model.language_model.layers.15.mlp.shared_expert_gate",
      "model.language_model.layers.15.post_attention_layernorm",
      "model.language_model.layers.15.mlp.gate",
      "model.language_model.layers.15.self_attn.k_norm",
      "model.language_model.layers.15.self_attn.q_norm",
      "model.language_model.layers.16.input_layernorm",
      "model.language_model.layers.16.mlp.shared_expert_gate",
      "model.language_model.layers.16.post_attention_layernorm",
      "model.language_model.layers.16.mlp.gate",
      "model.language_model.layers.16.linear_attn.A_log",
      "model.language_model.layers.16.linear_attn.conv1d",
      "model.language_model.layers.16.linear_attn.dt_bias",
      "model.language_model.layers.16.linear_attn.in_proj_ba",
      "model.language_model.layers.16.linear_attn.in_proj_b",
      "model.language_model.layers.16.linear_attn.in_proj_a",
      "model.language_model.layers.16.linear_attn.norm",
      "model.language_model.layers.17.input_layernorm",
      "model.language_model.layers.17.mlp.shared_expert_gate",
      "model.language_model.layers.17.post_attention_layernorm",
      "model.language_model.layers.17.mlp.gate",
      "model.language_model.layers.17.linear_attn.A_log",
      "model.language_model.layers.17.linear_attn.conv1d",
      "model.language_model.layers.17.linear_attn.dt_bias",
      "model.language_model.layers.17.linear_attn.in_proj_ba",
      "model.language_model.layers.17.linear_attn.in_proj_b",
      "model.language_model.layers.17.linear_attn.in_proj_a",
      "model.language_model.layers.17.linear_attn.norm",
      "model.language_model.layers.18.input_layernorm",
      "model.language_model.layers.18.mlp.shared_expert_gate",
      "model.language_model.layers.18.post_attention_layernorm",
      "model.language_model.layers.18.mlp.gate",
      "model.language_model.layers.18.linear_attn.A_log",
      "model.language_model.layers.18.linear_attn.conv1d",
      "model.language_model.layers.18.linear_attn.dt_bias",
      "model.language_model.layers.18.linear_attn.in_proj_ba",
      "model.language_model.layers.18.linear_attn.in_proj_b",
      "model.language_model.layers.18.linear_attn.in_proj_a",
      "model.language_model.layers.18.linear_attn.norm",
      "model.language_model.layers.19.input_layernorm",
      "model.language_model.layers.19.mlp.shared_expert_gate",
      "model.language_model.layers.19.post_attention_layernorm",
      "model.language_model.layers.19.mlp.gate",
      "model.language_model.layers.19.self_attn.k_norm",
      "model.language_model.layers.19.self_attn.q_norm",
      "model.language_model.layers.20.input_layernorm",
      "model.language_model.layers.20.mlp.shared_expert_gate",
      "model.language_model.layers.20.post_attention_layernorm",
      "model.language_model.layers.20.mlp.gate",
      "model.language_model.layers.20.linear_attn.A_log",
      "model.language_model.layers.20.linear_attn.conv1d",
      "model.language_model.layers.20.linear_attn.dt_bias",
      "model.language_model.layers.20.linear_attn.in_proj_ba",
      "model.language_model.layers.20.linear_attn.in_proj_b",
      "model.language_model.layers.20.linear_attn.in_proj_a",
      "model.language_model.layers.20.linear_attn.norm",
      "model.language_model.layers.21.input_layernorm",
      "model.language_model.layers.21.mlp.shared_expert_gate",
      "model.language_model.layers.21.post_attention_layernorm",
      "model.language_model.layers.21.mlp.gate",
      "model.language_model.layers.21.linear_attn.A_log",
      "model.language_model.layers.21.linear_attn.conv1d",
      "model.language_model.layers.21.linear_attn.dt_bias",
      "model.language_model.layers.21.linear_attn.in_proj_ba",
      "model.language_model.layers.21.linear_attn.in_proj_b",
      "model.language_model.layers.21.linear_attn.in_proj_a",
      "model.language_model.layers.21.linear_attn.norm",
      "model.language_model.layers.22.input_layernorm",
      "model.language_model.layers.22.mlp.shared_expert_gate",
      "model.language_model.layers.22.post_attention_layernorm",
      "model.language_model.layers.22.mlp.gate",
      "model.language_model.layers.22.linear_attn.A_log",
      "model.language_model.layers.22.linear_attn.conv1d",
      "model.language_model.layers.22.linear_attn.dt_bias",
      "model.language_model.layers.22.linear_attn.in_proj_ba",
      "model.language_model.layers.22.linear_attn.in_proj_b",
      "model.language_model.layers.22.linear_attn.in_proj_a",
      "model.language_model.layers.22.linear_attn.norm",
      "model.language_model.layers.23.input_layernorm",
      "model.language_model.layers.23.mlp.shared_expert_gate",
      "model.language_model.layers.23.post_attention_layernorm",
      "model.language_model.layers.23.mlp.gate",
      "model.language_model.layers.23.self_attn.k_norm",
      "model.language_model.layers.23.self_attn.q_norm",
      "model.language_model.layers.24.input_layernorm",
      "model.language_model.layers.24.mlp.shared_expert_gate",
      "model.language_model.layers.24.post_attention_layernorm",
      "model.language_model.layers.24.mlp.gate",
      "model.language_model.layers.24.linear_attn.A_log",
      "model.language_model.layers.24.linear_attn.conv1d",
      "model.language_model.layers.24.linear_attn.dt_bias",
      "model.language_model.layers.24.linear_attn.in_proj_ba",
      "model.language_model.layers.24.linear_attn.in_proj_b",
      "model.language_model.layers.24.linear_attn.in_proj_a",
      "model.language_model.layers.24.linear_attn.norm",
      "model.language_model.layers.25.input_layernorm",
      "model.language_model.layers.25.mlp.shared_expert_gate",
      "model.language_model.layers.25.post_attention_layernorm",
      "model.language_model.layers.25.mlp.gate",
      "model.language_model.layers.25.linear_attn.A_log",
      "model.language_model.layers.25.linear_attn.conv1d",
      "model.language_model.layers.25.linear_attn.dt_bias",
      "model.language_model.layers.25.linear_attn.in_proj_ba",
      "model.language_model.layers.25.linear_attn.in_proj_b",
      "model.language_model.layers.25.linear_attn.in_proj_a",
      "model.language_model.layers.25.linear_attn.norm",
      "model.language_model.layers.26.input_layernorm",
      "model.language_model.layers.26.mlp.shared_expert_gate",
      "model.language_model.layers.26.post_attention_layernorm",
      "model.language_model.layers.26.mlp.gate",
      "model.language_model.layers.26.linear_attn.A_log",
      "model.language_model.layers.26.linear_attn.conv1d",
      "model.language_model.layers.26.linear_attn.dt_bias",
      "model.language_model.layers.26.linear_attn.in_proj_ba",
      "model.language_model.layers.26.linear_attn.in_proj_b",
      "model.language_model.layers.26.linear_attn.in_proj_a",
      "model.language_model.layers.26.linear_attn.norm",
      "model.language_model.layers.27.input_layernorm",
      "model.language_model.layers.27.mlp.shared_expert_gate",
      "model.language_model.layers.27.post_attention_layernorm",
      "model.language_model.layers.27.mlp.gate",
      "model.language_model.layers.27.self_attn.k_norm",
      "model.language_model.layers.27.self_attn.q_norm",
      "model.language_model.layers.28.input_layernorm",
      "model.language_model.layers.28.mlp.shared_expert_gate",
      "model.language_model.layers.28.post_attention_layernorm",
      "model.language_model.layers.28.mlp.gate",
      "model.language_model.layers.28.linear_attn.A_log",
      "model.language_model.layers.28.linear_attn.conv1d",
      "model.language_model.layers.28.linear_attn.dt_bias",
      "model.language_model.layers.28.linear_attn.in_proj_ba",
      "model.language_model.layers.28.linear_attn.in_proj_b",
      "model.language_model.layers.28.linear_attn.in_proj_a",
      "model.language_model.layers.28.linear_attn.norm",
      "model.language_model.layers.29.input_layernorm",
      "model.language_model.layers.29.mlp.shared_expert_gate",
      "model.language_model.layers.29.post_attention_layernorm",
      "model.language_model.layers.29.mlp.gate",
      "model.language_model.layers.29.linear_attn.A_log",
      "model.language_model.layers.29.linear_attn.conv1d",
      "model.language_model.layers.29.linear_attn.dt_bias",
      "model.language_model.layers.29.linear_attn.in_proj_ba",
      "model.language_model.layers.29.linear_attn.in_proj_b",
      "model.language_model.layers.29.linear_attn.in_proj_a",
      "model.language_model.layers.29.linear_attn.norm",
      "model.language_model.layers.30.input_layernorm",
      "model.language_model.layers.30.mlp.shared_expert_gate",
      "model.language_model.layers.30.post_attention_layernorm",
      "model.language_model.layers.30.mlp.gate",
      "model.language_model.layers.30.linear_attn.A_log",
      "model.language_model.layers.30.linear_attn.conv1d",
      "model.language_model.layers.30.linear_attn.dt_bias",
      "model.language_model.layers.30.linear_attn.in_proj_ba",
      "model.language_model.layers.30.linear_attn.in_proj_b",
      "model.language_model.layers.30.linear_attn.in_proj_a",
      "model.language_model.layers.30.linear_attn.norm",
      "model.language_model.layers.31.input_layernorm",
      "model.language_model.layers.31.mlp.shared_expert_gate",
      "model.language_model.layers.31.post_attention_layernorm",
      "model.language_model.layers.31.mlp.gate",
      "model.language_model.layers.31.self_attn.k_norm",
      "model.language_model.layers.31.self_attn.q_norm",
      "model.language_model.layers.32.input_layernorm",
      "model.language_model.layers.32.mlp.shared_expert_gate",
      "model.language_model.layers.32.post_attention_layernorm",
      "model.language_model.layers.32.mlp.gate",
      "model.language_model.layers.32.linear_attn.A_log",
      "model.language_model.layers.32.linear_attn.conv1d",
      "model.language_model.layers.32.linear_attn.dt_bias",
      "model.language_model.layers.32.linear_attn.in_proj_ba",
      "model.language_model.layers.32.linear_attn.in_proj_b",
      "model.language_model.layers.32.linear_attn.in_proj_a",
      "model.language_model.layers.32.linear_attn.norm",
      "model.language_model.layers.33.input_layernorm",
      "model.language_model.layers.33.mlp.shared_expert_gate",
      "model.language_model.layers.33.post_attention_layernorm",
      "model.language_model.layers.33.mlp.gate",
      "model.language_model.layers.33.linear_attn.A_log",
      "model.language_model.layers.33.linear_attn.conv1d",
      "model.language_model.layers.33.linear_attn.dt_bias",
      "model.language_model.layers.33.linear_attn.in_proj_ba",
      "model.language_model.layers.33.linear_attn.in_proj_b",
      "model.language_model.layers.33.linear_attn.in_proj_a",
      "model.language_model.layers.33.linear_attn.norm",
      "model.language_model.layers.34.input_layernorm",
      "model.language_model.layers.34.mlp.shared_expert_gate",
      "model.language_model.layers.34.post_attention_layernorm",
      "model.language_model.layers.34.mlp.gate",
      "model.language_model.layers.34.linear_attn.A_log",
      "model.language_model.layers.34.linear_attn.conv1d",
      "model.language_model.layers.34.linear_attn.dt_bias",
      "model.language_model.layers.34.linear_attn.in_proj_ba",
      "model.language_model.layers.34.linear_attn.in_proj_b",
      "model.language_model.layers.34.linear_attn.in_proj_a",
      "model.language_model.layers.34.linear_attn.norm",
      "model.language_model.layers.35.input_layernorm",
      "model.language_model.layers.35.mlp.shared_expert_gate",
      "model.language_model.layers.35.post_attention_layernorm",
      "model.language_model.layers.35.mlp.gate",
      "model.language_model.layers.35.self_attn.k_norm",
      "model.language_model.layers.35.self_attn.q_norm",
      "model.language_model.layers.36.input_layernorm",
      "model.language_model.layers.36.mlp.shared_expert_gate",
      "model.language_model.layers.36.post_attention_layernorm",
      "model.language_model.layers.36.mlp.gate",
      "model.language_model.layers.36.linear_attn.A_log",
      "model.language_model.layers.36.linear_attn.conv1d",
      "model.language_model.layers.36.linear_attn.dt_bias",
      "model.language_model.layers.36.linear_attn.in_proj_ba",
      "model.language_model.layers.36.linear_attn.in_proj_b",
      "model.language_model.layers.36.linear_attn.in_proj_a",
      "model.language_model.layers.36.linear_attn.norm",
      "model.language_model.layers.37.input_layernorm",
      "model.language_model.layers.37.mlp.shared_expert_gate",
      "model.language_model.layers.37.post_attention_layernorm",
      "model.language_model.layers.37.mlp.gate",
      "model.language_model.layers.37.linear_attn.A_log",
      "model.language_model.layers.37.linear_attn.conv1d",
      "model.language_model.layers.37.linear_attn.dt_bias",
      "model.language_model.layers.37.linear_attn.in_proj_ba",
      "model.language_model.layers.37.linear_attn.in_proj_b",
      "model.language_model.layers.37.linear_attn.in_proj_a",
      "model.language_model.layers.37.linear_attn.norm",
      "model.language_model.layers.38.input_layernorm",
      "model.language_model.layers.38.mlp.shared_expert_gate",
      "model.language_model.layers.38.post_attention_layernorm",
      "model.language_model.layers.38.mlp.gate",
      "model.language_model.layers.38.linear_attn.A_log",
      "model.language_model.layers.38.linear_attn.conv1d",
      "model.language_model.layers.38.linear_attn.dt_bias",
      "model.language_model.layers.38.linear_attn.in_proj_ba",
      "model.language_model.layers.38.linear_attn.in_proj_b",
      "model.language_model.layers.38.linear_attn.in_proj_a",
      "model.language_model.layers.38.linear_attn.norm",
      "model.language_model.layers.39.input_layernorm",
      "model.language_model.layers.39.mlp.shared_expert_gate",
      "model.language_model.layers.39.post_attention_layernorm",
      "model.language_model.layers.39.mlp.gate",
      "model.language_model.layers.39.self_attn.k_norm",
      "model.language_model.layers.39.self_attn.q_norm",
      "model.language_model.layers.40.input_layernorm",
      "model.language_model.layers.40.mlp.shared_expert_gate",
      "model.language_model.layers.40.post_attention_layernorm",
      "model.language_model.layers.40.mlp.gate",
      "model.language_model.layers.40.linear_attn.A_log",
      "model.language_model.layers.40.linear_attn.conv1d",
      "model.language_model.layers.40.linear_attn.dt_bias",
      "model.language_model.layers.40.linear_attn.in_proj_ba",
      "model.language_model.layers.40.linear_attn.in_proj_b",
      "model.language_model.layers.40.linear_attn.in_proj_a",
      "model.language_model.layers.40.linear_attn.norm",
      "model.language_model.layers.41.input_layernorm",
      "model.language_model.layers.41.mlp.shared_expert_gate",
      "model.language_model.layers.41.post_attention_layernorm",
      "model.language_model.layers.41.mlp.gate",
      "model.language_model.layers.41.linear_attn.A_log",
      "model.language_model.layers.41.linear_attn.conv1d",
      "model.language_model.layers.41.linear_attn.dt_bias",
      "model.language_model.layers.41.linear_attn.in_proj_ba",
      "model.language_model.layers.41.linear_attn.in_proj_b",
      "model.language_model.layers.41.linear_attn.in_proj_a",
      "model.language_model.layers.41.linear_attn.norm",
      "model.language_model.layers.42.input_layernorm",
      "model.language_model.layers.42.mlp.shared_expert_gate",
      "model.language_model.layers.42.post_attention_layernorm",
      "model.language_model.layers.42.mlp.gate",
      "model.language_model.layers.42.linear_attn.A_log",
      "model.language_model.layers.42.linear_attn.conv1d",
      "model.language_model.layers.42.linear_attn.dt_bias",
      "model.language_model.layers.42.linear_attn.in_proj_ba",
      "model.language_model.layers.42.linear_attn.in_proj_b",
      "model.language_model.layers.42.linear_attn.in_proj_a",
      "model.language_model.layers.42.linear_attn.norm",
      "model.language_model.layers.43.input_layernorm",
      "model.language_model.layers.43.mlp.shared_expert_gate",
      "model.language_model.layers.43.post_attention_layernorm",
      "model.language_model.layers.43.mlp.gate",
      "model.language_model.layers.43.self_attn.k_norm",
      "model.language_model.layers.43.self_attn.q_norm",
      "model.language_model.layers.44.input_layernorm",
      "model.language_model.layers.44.mlp.shared_expert_gate",
      "model.language_model.layers.44.post_attention_layernorm",
      "model.language_model.layers.44.mlp.gate",
      "model.language_model.layers.44.linear_attn.A_log",
      "model.language_model.layers.44.linear_attn.conv1d",
      "model.language_model.layers.44.linear_attn.dt_bias",
      "model.language_model.layers.44.linear_attn.in_proj_ba",
      "model.language_model.layers.44.linear_attn.in_proj_b",
      "model.language_model.layers.44.linear_attn.in_proj_a",
      "model.language_model.layers.44.linear_attn.norm",
      "model.language_model.layers.45.input_layernorm",
      "model.language_model.layers.45.mlp.shared_expert_gate",
      "model.language_model.layers.45.post_attention_layernorm",
      "model.language_model.layers.45.mlp.gate",
      "model.language_model.layers.45.linear_attn.A_log",
      "model.language_model.layers.45.linear_attn.conv1d",
      "model.language_model.layers.45.linear_attn.dt_bias",
      "model.language_model.layers.45.linear_attn.in_proj_ba",
      "model.language_model.layers.45.linear_attn.in_proj_b",
      "model.language_model.layers.45.linear_attn.in_proj_a",
      "model.language_model.layers.45.linear_attn.norm",
      "model.language_model.layers.46.input_layernorm",
      "model.language_model.layers.46.mlp.shared_expert_gate",
      "model.language_model.layers.46.post_attention_layernorm",
      "model.language_model.layers.46.mlp.gate",
      "model.language_model.layers.46.linear_attn.A_log",
      "model.language_model.layers.46.linear_attn.conv1d",
      "model.language_model.layers.46.linear_attn.dt_bias",
      "model.language_model.layers.46.linear_attn.in_proj_ba",
      "model.language_model.layers.46.linear_attn.in_proj_b",
      "model.language_model.layers.46.linear_attn.in_proj_a",
      "model.language_model.layers.46.linear_attn.norm",
      "model.language_model.layers.47.input_layernorm",
      "model.language_model.layers.47.mlp.shared_expert_gate",
      "model.language_model.layers.47.post_attention_layernorm",
      "model.language_model.layers.47.mlp.gate",
      "model.language_model.layers.47.self_attn.k_norm",
      "model.language_model.layers.47.self_attn.q_norm",
      "model.language_model.layers.48.input_layernorm",
      "model.language_model.layers.48.mlp.shared_expert_gate",
      "model.language_model.layers.48.post_attention_layernorm",
      "model.language_model.layers.48.mlp.gate",
      "model.language_model.layers.48.linear_attn.A_log",
      "model.language_model.layers.48.linear_attn.conv1d",
      "model.language_model.layers.48.linear_attn.dt_bias",
      "model.language_model.layers.48.linear_attn.in_proj_ba",
      "model.language_model.layers.48.linear_attn.in_proj_b",
      "model.language_model.layers.48.linear_attn.in_proj_a",
      "model.language_model.layers.48.linear_attn.norm",
      "model.language_model.layers.49.input_layernorm",
      "model.language_model.layers.49.mlp.shared_expert_gate",
      "model.language_model.layers.49.post_attention_layernorm",
      "model.language_model.layers.49.mlp.gate",
      "model.language_model.layers.49.linear_attn.A_log",
      "model.language_model.layers.49.linear_attn.conv1d",
      "model.language_model.layers.49.linear_attn.dt_bias",
      "model.language_model.layers.49.linear_attn.in_proj_ba",
      "model.language_model.layers.49.linear_attn.in_proj_b",
      "model.language_model.layers.49.linear_attn.in_proj_a",
      "model.language_model.layers.49.linear_attn.norm",
      "model.language_model.layers.50.input_layernorm",
      "model.language_model.layers.50.mlp.shared_expert_gate",
      "model.language_model.layers.50.post_attention_layernorm",
      "model.language_model.layers.50.mlp.gate",
      "model.language_model.layers.50.linear_attn.A_log",
      "model.language_model.layers.50.linear_attn.conv1d",
      "model.language_model.layers.50.linear_attn.dt_bias",
      "model.language_model.layers.50.linear_attn.in_proj_ba",
      "model.language_model.layers.50.linear_attn.in_proj_b",
      "model.language_model.layers.50.linear_attn.in_proj_a",
      "model.language_model.layers.50.linear_attn.norm",
      "model.language_model.layers.51.input_layernorm",
      "model.language_model.layers.51.mlp.shared_expert_gate",
      "model.language_model.layers.51.post_attention_layernorm",
      "model.language_model.layers.51.mlp.gate",
      "model.language_model.layers.51.self_attn.k_norm",
      "model.language_model.layers.51.self_attn.q_norm",
      "model.language_model.layers.52.input_layernorm",
      "model.language_model.layers.52.mlp.shared_expert_gate",
      "model.language_model.layers.52.post_attention_layernorm",
      "model.language_model.layers.52.mlp.gate",
      "model.language_model.layers.52.linear_attn.A_log",
      "model.language_model.layers.52.linear_attn.conv1d",
      "model.language_model.layers.52.linear_attn.dt_bias",
      "model.language_model.layers.52.linear_attn.in_proj_ba",
      "model.language_model.layers.52.linear_attn.in_proj_b",
      "model.language_model.layers.52.linear_attn.in_proj_a",
      "model.language_model.layers.52.linear_attn.norm",
      "model.language_model.layers.53.input_layernorm",
      "model.language_model.layers.53.mlp.shared_expert_gate",
      "model.language_model.layers.53.post_attention_layernorm",
      "model.language_model.layers.53.mlp.gate",
      "model.language_model.layers.53.linear_attn.A_log",
      "model.language_model.layers.53.linear_attn.conv1d",
      "model.language_model.layers.53.linear_attn.dt_bias",
      "model.language_model.layers.53.linear_attn.in_proj_ba",
      "model.language_model.layers.53.linear_attn.in_proj_b",
      "model.language_model.layers.53.linear_attn.in_proj_a",
      "model.language_model.layers.53.linear_attn.norm",
      "model.language_model.layers.54.input_layernorm",
      "model.language_model.layers.54.mlp.shared_expert_gate",
      "model.language_model.layers.54.post_attention_layernorm",
      "model.language_model.layers.54.mlp.gate",
      "model.language_model.layers.54.linear_attn.A_log",
      "model.language_model.layers.54.linear_attn.conv1d",
      "model.language_model.layers.54.linear_attn.dt_bias",
      "model.language_model.layers.54.linear_attn.in_proj_ba",
      "model.language_model.layers.54.linear_attn.in_proj_b",
      "model.language_model.layers.54.linear_attn.in_proj_a",
      "model.language_model.layers.54.linear_attn.norm",
      "model.language_model.layers.55.input_layernorm",
      "model.language_model.layers.55.mlp.shared_expert_gate",
      "model.language_model.layers.55.post_attention_layernorm",
      "model.language_model.layers.55.mlp.gate",
      "model.language_model.layers.55.self_attn.k_norm",
      "model.language_model.layers.55.self_attn.q_norm",
      "model.language_model.layers.56.input_layernorm",
      "model.language_model.layers.56.mlp.shared_expert_gate",
      "model.language_model.layers.56.post_attention_layernorm",
      "model.language_model.layers.56.mlp.gate",
      "model.language_model.layers.56.linear_attn.A_log",
      "model.language_model.layers.56.linear_attn.conv1d",
      "model.language_model.layers.56.linear_attn.dt_bias",
      "model.language_model.layers.56.linear_attn.in_proj_ba",
      "model.language_model.layers.56.linear_attn.in_proj_b",
      "model.language_model.layers.56.linear_attn.in_proj_a",
      "model.language_model.layers.56.linear_attn.norm",
      "model.language_model.layers.57.input_layernorm",
      "model.language_model.layers.57.mlp.shared_expert_gate",
      "model.language_model.layers.57.post_attention_layernorm",
      "model.language_model.layers.57.mlp.gate",
      "model.language_model.layers.57.linear_attn.A_log",
      "model.language_model.layers.57.linear_attn.conv1d",
      "model.language_model.layers.57.linear_attn.dt_bias",
      "model.language_model.layers.57.linear_attn.in_proj_ba",
      "model.language_model.layers.57.linear_attn.in_proj_b",
      "model.language_model.layers.57.linear_attn.in_proj_a",
      "model.language_model.layers.57.linear_attn.norm",
      "model.language_model.layers.58.input_layernorm",
      "model.language_model.layers.58.mlp.shared_expert_gate",
      "model.language_model.layers.58.post_attention_layernorm",
      "model.language_model.layers.58.mlp.gate",
      "model.language_model.layers.58.linear_attn.A_log",
      "model.language_model.layers.58.linear_attn.conv1d",
      "model.language_model.layers.58.linear_attn.dt_bias",
      "model.language_model.layers.58.linear_attn.in_proj_ba",
      "model.language_model.layers.58.linear_attn.in_proj_b",
      "model.language_model.layers.58.linear_attn.in_proj_a",
      "model.language_model.layers.58.linear_attn.norm",
      "model.language_model.layers.59.input_layernorm",
      "model.language_model.layers.59.mlp.shared_expert_gate",
      "model.language_model.layers.59.post_attention_layernorm",
      "model.language_model.layers.59.mlp.gate",
      "model.language_model.layers.59.self_attn.k_norm",
      "model.language_model.layers.59.self_attn.q_norm",
      "model.language_model.layers.60.input_layernorm",
      "model.language_model.layers.60.mlp.shared_expert_gate",
      "model.language_model.layers.60.post_attention_layernorm",
      "model.language_model.layers.60.mlp.gate",
      "model.language_model.layers.60.linear_attn.A_log",
      "model.language_model.layers.60.linear_attn.conv1d",
      "model.language_model.layers.60.linear_attn.dt_bias",
      "model.language_model.layers.60.linear_attn.in_proj_ba",
      "model.language_model.layers.60.linear_attn.in_proj_b",
      "model.language_model.layers.60.linear_attn.in_proj_a",
      "model.language_model.layers.60.linear_attn.norm",
      "model.language_model.layers.61.input_layernorm",
      "model.language_model.layers.61.mlp.shared_expert_gate",
      "model.language_model.layers.61.post_attention_layernorm",
      "model.language_model.layers.61.mlp.gate",
      "model.language_model.layers.61.linear_attn.A_log",
      "model.language_model.layers.61.linear_attn.conv1d",
      "model.language_model.layers.61.linear_attn.dt_bias",
      "model.language_model.layers.61.linear_attn.in_proj_ba",
      "model.language_model.layers.61.linear_attn.in_proj_b",
      "model.language_model.layers.61.linear_attn.in_proj_a",
      "model.language_model.layers.61.linear_attn.norm",
      "model.language_model.layers.62.input_layernorm",
      "model.language_model.layers.62.mlp.shared_expert_gate",
      "model.language_model.layers.62.post_attention_layernorm",
      "model.language_model.layers.62.mlp.gate",
      "model.language_model.layers.62.linear_attn.A_log",
      "model.language_model.layers.62.linear_attn.conv1d",
      "model.language_model.layers.62.linear_attn.dt_bias",
      "model.language_model.layers.62.linear_attn.in_proj_ba",
      "model.language_model.layers.62.linear_attn.in_proj_b",
      "model.language_model.layers.62.linear_attn.in_proj_a",
      "model.language_model.layers.62.linear_attn.norm",
      "model.language_model.layers.63.input_layernorm",
      "model.language_model.layers.63.mlp.shared_expert_gate",
      "model.language_model.layers.63.post_attention_layernorm",
      "model.language_model.layers.63.mlp.gate",
      "model.language_model.layers.63.self_attn.k_norm",
      "model.language_model.layers.63.self_attn.q_norm",
      "mtp.layers.0.input_layernorm",
      "mtp.layers.0.mlp.gate",
      "mtp.layers.0.mlp.shared_expert_gate",
      "mtp.layers.0.post_attention_layernorm",
      "mtp.layers.0.self_attn.k_norm",
      "mtp.layers.0.self_attn.q_norm",
      "mtp.fc",
      "mtp.norm",
      "mtp.pre_fc_norm_embedding",
      "mtp.pre_fc_norm_hidden"
    ],
    "weight_block_size": [
      128,
      128
    ]
  }
}
{
  "architectures": [
    "Qwen3_5ForConditionalGeneration"
  ],
  "image_token_id": 248056,
  "language_model_only": false,
  "model_type": "qwen3_5",
  "text_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "attn_output_gate": true,
    "bos_token_id": 248044,
    "dtype": "bfloat16",
    "eos_token_id": 248044,
    "full_attention_interval": 4,
    "head_dim": 256,
    "hidden_act": "silu",
    "hidden_size": 5120,
    "initializer_range": 0.02,
    "intermediate_size": 17408,
    "layer_types": [
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention"
    ],
    "linear_conv_kernel_dim": 4,
    "linear_key_head_dim": 128,
    "linear_num_key_heads": 16,
    "linear_num_value_heads": 48,
    "linear_value_head_dim": 128,
    "mamba_ssm_dtype": "float32",
    "max_position_embeddings": 262144,
    "model_type": "qwen3_5_text",
    "mtp_num_hidden_layers": 1,
    "mtp_use_dedicated_embeddings": false,
    "num_attention_heads": 24,
    "num_hidden_layers": 64,
    "num_key_value_heads": 4,
    "output_gate_type": "swish",