Instructions to use tiny-random/qwen3.8-flash-next-fp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiny-random/qwen3.8-flash-next-fp8 with Transformers:

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

pipe = pipeline("image-text-to-text", model="tiny-random/qwen3.8-flash-next-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("tiny-random/qwen3.8-flash-next-fp8")
model = AutoModelForMultimodalLM.from_pretrained("tiny-random/qwen3.8-flash-next-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 tiny-random/qwen3.8-flash-next-fp8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiny-random/qwen3.8-flash-next-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": "tiny-random/qwen3.8-flash-next-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/tiny-random/qwen3.8-flash-next-fp8

SGLang

How to use tiny-random/qwen3.8-flash-next-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 "tiny-random/qwen3.8-flash-next-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": "tiny-random/qwen3.8-flash-next-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 "tiny-random/qwen3.8-flash-next-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": "tiny-random/qwen3.8-flash-next-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 tiny-random/qwen3.8-flash-next-fp8 with Docker Model Runner:
```
docker model run hf.co/tiny-random/qwen3.8-flash-next-fp8
```

qwen3.8-flash-next-fp8 / config.json

yujiepan

Add GPU-validated Qwen3.8 Flash-Next tiny random model

833f534 verified 4 days ago

Raw History Blame Contribute Delete

14.3 kB

{
  "architectures": [
    "Qwen4ExpForConditionalGeneration"
  ],
  "image_token_id": 248056,
  "language_model_only": false,
  "model_type": "qwen4_exp",
  "text_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 248044,
    "dtype": "bfloat16",
    "eos_token_id": 248044,
    "full_attention_interval": 4,
    "hc_count": 4,
    "hc_lowrank": 4,
    "head_dim": 32,
    "heads_per_ngram": 8,
    "hidden_act": "silu",
    "hidden_size": 32,
    "indexer_budget": 2048,
    "indexer_compress_ratio": 4,
    "indexer_head_dim": 128,
    "indexer_kv_heads": 1,
    "indexer_n_heads": 4,
    "initializer_range": 0.02,
    "layer_types": [
      "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": 32,
    "linear_num_key_heads": 4,
    "linear_num_value_heads": 12,
    "linear_value_head_dim": 32,
    "make_ngram_vocab_size_divisible_by": 128,
    "mamba_ssm_dtype": "float32",
    "max_position_embeddings": 262144,
    "model_type": "qwen4_exp_text",
    "moe_intermediate_size": 128,
    "mtp": {
      "hybrid": true,
      "layer_types": [
        "full_attention"
      ],
      "mtp_use_hidden_state_from_layer": null,
      "num_hidden_layers": 1,
      "rope_theta": 10000000
    },
    "mtp_num_hidden_layers": 1,
    "mtp_use_dedicated_embeddings": false,
    "ngram_size": 3,
    "ngram_vocab_size_base": 512,
    "num_attention_heads": 12,
    "num_experts": 32,
    "num_experts_per_tok": 10,
    "num_hidden_layers": 8,
    "num_key_value_heads": 1,
    "output_gate_type": "sigmoid",
    "output_router_logits": false,
    "pad_token_id": null,
    "partial_rotary_factor": 0.25,
    "ple_conv_kernel_size": 4,
    "ple_embed_dim": 16,
    "ple_layer_ids": [
      2
    ],
    "rms_norm_eps": 1e-06,
    "rope_parameters": {
      "mrope_interleaved": true,
      "mrope_section": [
        2,
        1,
        1
      ],
      "partial_rotary_factor": 0.25,
      "rope_theta": 10000000,
      "rope_type": "default"
    },
    "router_aux_loss_coef": 0.001,
    "shared_expert_intermediate_size": 128,
    "split_ngram_parts": 128,
    "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": 2,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 64,
    "in_channels": 3,
    "initializer_range": 0.02,
    "intermediate_size": 128,
    "model_type": "qwen4_exp",
    "num_heads": 4,
    "num_position_embeddings": 2304,
    "out_hidden_size": 32,
    "patch_size": 16,
    "spatial_merge_size": 2,
    "temporal_patch_size": 2
  },
  "vision_end_token_id": 248054,
  "vision_start_token_id": 248053,
  "quantization_config": {
    "quant_method": "fp8",
    "activation_scheme": "dynamic",
    "weight_per_tensor": false,
    "act_per_tensor": false,
    "weight_block_size": [
      32,
      32
    ],
    "modules_to_not_convert": [
      "lm_head",
      "model.language_model.embed_tokens",
      "model.language_model.hyper_connection_mixer.input_mix_weight_down",
      "model.language_model.hyper_connection_mixer.input_mix_weight_up",
      "model.language_model.layers.0.attn_hyper_connection.block_inject_weight",
      "model.language_model.layers.0.attn_hyper_connection.input_mix_weight_down",
      "model.language_model.layers.0.attn_hyper_connection.input_mix_weight_up",
      "model.language_model.layers.0.linear_attn.conv1d",
      "model.language_model.layers.0.linear_attn.in_proj_a",
      "model.language_model.layers.0.linear_attn.in_proj_b",
      "model.language_model.layers.0.linear_attn.in_proj_qkv",
      "model.language_model.layers.0.linear_attn.in_proj_z",
      "model.language_model.layers.0.linear_attn.out_proj",
      "model.language_model.layers.0.mlp.gate",
      "model.language_model.layers.0.mlp.shared_expert.down_proj",
      "model.language_model.layers.0.mlp.shared_expert.gate_proj",
      "model.language_model.layers.0.mlp.shared_expert.up_proj",
      "model.language_model.layers.0.mlp.shared_expert_gate",
      "model.language_model.layers.0.mlp_hyper_connection.block_inject_weight",
      "model.language_model.layers.0.mlp_hyper_connection.input_mix_weight_down",
      "model.language_model.layers.0.mlp_hyper_connection.input_mix_weight_up",
      "model.language_model.layers.1.attn_hyper_connection.block_inject_weight",
      "model.language_model.layers.1.attn_hyper_connection.input_mix_weight_down",
      "model.language_model.layers.1.attn_hyper_connection.input_mix_weight_up",
      "model.language_model.layers.1.linear_attn.conv1d",
      "model.language_model.layers.1.linear_attn.in_proj_a",
      "model.language_model.layers.1.linear_attn.in_proj_b",
      "model.language_model.layers.1.linear_attn.in_proj_qkv",
      "model.language_model.layers.1.linear_attn.in_proj_z",
      "model.language_model.layers.1.linear_attn.out_proj",
      "model.language_model.layers.1.mlp.gate",
      "model.language_model.layers.1.mlp.shared_expert.down_proj",
      "model.language_model.layers.1.mlp.shared_expert.gate_proj",
      "model.language_model.layers.1.mlp.shared_expert.up_proj",
      "model.language_model.layers.1.mlp.shared_expert_gate",
      "model.language_model.layers.1.mlp_hyper_connection.block_inject_weight",
      "model.language_model.layers.1.mlp_hyper_connection.input_mix_weight_down",
      "model.language_model.layers.1.mlp_hyper_connection.input_mix_weight_up",
      "model.language_model.layers.1.ple.conv1d",
      "model.language_model.layers.1.ple.key_proj",
      "model.language_model.layers.1.ple.value_proj",
      "model.language_model.layers.2.attn_hyper_connection.block_inject_weight",
      "model.language_model.layers.2.attn_hyper_connection.input_mix_weight_down",
      "model.language_model.layers.2.attn_hyper_connection.input_mix_weight_up",
      "model.language_model.layers.2.linear_attn.conv1d",
      "model.language_model.layers.2.linear_attn.in_proj_a",
      "model.language_model.layers.2.linear_attn.in_proj_b",
      "model.language_model.layers.2.linear_attn.in_proj_qkv",
      "model.language_model.layers.2.linear_attn.in_proj_z",
      "model.language_model.layers.2.linear_attn.out_proj",
      "model.language_model.layers.2.mlp.gate",
      "model.language_model.layers.2.mlp.shared_expert.down_proj",
      "model.language_model.layers.2.mlp.shared_expert.gate_proj",
      "model.language_model.layers.2.mlp.shared_expert.up_proj",
      "model.language_model.layers.2.mlp.shared_expert_gate",
      "model.language_model.layers.2.mlp_hyper_connection.block_inject_weight",
      "model.language_model.layers.2.mlp_hyper_connection.input_mix_weight_down",
      "model.language_model.layers.2.mlp_hyper_connection.input_mix_weight_up",
      "model.language_model.layers.3.attn_hyper_connection.block_inject_weight",
      "model.language_model.layers.3.attn_hyper_connection.input_mix_weight_down",
      "model.language_model.layers.3.attn_hyper_connection.input_mix_weight_up",
      "model.language_model.layers.3.mlp.gate",
      "model.language_model.layers.3.mlp.shared_expert.down_proj",
      "model.language_model.layers.3.mlp.shared_expert.gate_proj",
      "model.language_model.layers.3.mlp.shared_expert.up_proj",
      "model.language_model.layers.3.mlp.shared_expert_gate",
      "model.language_model.layers.3.mlp_hyper_connection.block_inject_weight",
      "model.language_model.layers.3.mlp_hyper_connection.input_mix_weight_down",
      "model.language_model.layers.3.mlp_hyper_connection.input_mix_weight_up",
      "model.language_model.layers.3.self_attn.indexer.index_qk_proj",
      "model.language_model.layers.3.self_attn.k_proj",
      "model.language_model.layers.3.self_attn.o_proj",
      "model.language_model.layers.3.self_attn.q_proj",
      "model.language_model.layers.3.self_attn.v_proj",
      "model.language_model.layers.4.attn_hyper_connection.block_inject_weight",
      "model.language_model.layers.4.attn_hyper_connection.input_mix_weight_down",
      "model.language_model.layers.4.attn_hyper_connection.input_mix_weight_up",
      "model.language_model.layers.4.linear_attn.conv1d",
      "model.language_model.layers.4.linear_attn.in_proj_a",
      "model.language_model.layers.4.linear_attn.in_proj_b",
      "model.language_model.layers.4.linear_attn.in_proj_qkv",
      "model.language_model.layers.4.linear_attn.in_proj_z",
      "model.language_model.layers.4.linear_attn.out_proj",
      "model.language_model.layers.4.mlp.gate",
      "model.language_model.layers.4.mlp.shared_expert.down_proj",
      "model.language_model.layers.4.mlp.shared_expert.gate_proj",
      "model.language_model.layers.4.mlp.shared_expert.up_proj",
      "model.language_model.layers.4.mlp.shared_expert_gate",
      "model.language_model.layers.4.mlp_hyper_connection.block_inject_weight",
      "model.language_model.layers.4.mlp_hyper_connection.input_mix_weight_down",
      "model.language_model.layers.4.mlp_hyper_connection.input_mix_weight_up",
      "model.language_model.layers.5.attn_hyper_connection.block_inject_weight",
      "model.language_model.layers.5.attn_hyper_connection.input_mix_weight_down",
      "model.language_model.layers.5.attn_hyper_connection.input_mix_weight_up",
      "model.language_model.layers.5.linear_attn.conv1d",
      "model.language_model.layers.5.linear_attn.in_proj_a",
      "model.language_model.layers.5.linear_attn.in_proj_b",
      "model.language_model.layers.5.linear_attn.in_proj_qkv",
      "model.language_model.layers.5.linear_attn.in_proj_z",
      "model.language_model.layers.5.linear_attn.out_proj",
      "model.language_model.layers.5.mlp.gate",
      "model.language_model.layers.5.mlp.shared_expert.down_proj",
      "model.language_model.layers.5.mlp.shared_expert.gate_proj",
      "model.language_model.layers.5.mlp.shared_expert.up_proj",
      "model.language_model.layers.5.mlp.shared_expert_gate",
      "model.language_model.layers.5.mlp_hyper_connection.block_inject_weight",
      "model.language_model.layers.5.mlp_hyper_connection.input_mix_weight_down",
      "model.language_model.layers.5.mlp_hyper_connection.input_mix_weight_up",
      "model.language_model.layers.6.attn_hyper_connection.block_inject_weight",
      "model.language_model.layers.6.attn_hyper_connection.input_mix_weight_down",
      "model.language_model.layers.6.attn_hyper_connection.input_mix_weight_up",
      "model.language_model.layers.6.linear_attn.conv1d",
      "model.language_model.layers.6.linear_attn.in_proj_a",
      "model.language_model.layers.6.linear_attn.in_proj_b",
      "model.language_model.layers.6.linear_attn.in_proj_qkv",
      "model.language_model.layers.6.linear_attn.in_proj_z",
      "model.language_model.layers.6.linear_attn.out_proj",
      "model.language_model.layers.6.mlp.gate",
      "model.language_model.layers.6.mlp.shared_expert.down_proj",
      "model.language_model.layers.6.mlp.shared_expert.gate_proj",
      "model.language_model.layers.6.mlp.shared_expert.up_proj",
      "model.language_model.layers.6.mlp.shared_expert_gate",
      "model.language_model.layers.6.mlp_hyper_connection.block_inject_weight",
      "model.language_model.layers.6.mlp_hyper_connection.input_mix_weight_down",
      "model.language_model.layers.6.mlp_hyper_connection.input_mix_weight_up",
      "model.language_model.layers.7.attn_hyper_connection.block_inject_weight",
      "model.language_model.layers.7.attn_hyper_connection.input_mix_weight_down",
      "model.language_model.layers.7.attn_hyper_connection.input_mix_weight_up",
      "model.language_model.layers.7.mlp.gate",
      "model.language_model.layers.7.mlp.shared_expert.down_proj",
      "model.language_model.layers.7.mlp.shared_expert.gate_proj",
      "model.language_model.layers.7.mlp.shared_expert.up_proj",
      "model.language_model.layers.7.mlp.shared_expert_gate",
      "model.language_model.layers.7.mlp_hyper_connection.block_inject_weight",
      "model.language_model.layers.7.mlp_hyper_connection.input_mix_weight_down",
      "model.language_model.layers.7.mlp_hyper_connection.input_mix_weight_up",
      "model.language_model.layers.7.self_attn.indexer.index_qk_proj",
      "model.language_model.layers.7.self_attn.k_proj",
      "model.language_model.layers.7.self_attn.o_proj",
      "model.language_model.layers.7.self_attn.q_proj",
      "model.language_model.layers.7.self_attn.v_proj",
      "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",
      "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",
      "model.visual.merger.linear_fc1",
      "model.visual.merger.linear_fc2",
      "model.visual.patch_embed.proj",
      "model.visual.pos_embed",
      "mtp.fc_embedding",
      "mtp.fc_hidden",
      "mtp.hyper_connection_mixer.input_mix_weight_down",
      "mtp.hyper_connection_mixer.input_mix_weight_up",
      "mtp.layers.0.attn_hyper_connection.block_inject_weight",
      "mtp.layers.0.attn_hyper_connection.input_mix_weight_down",
      "mtp.layers.0.attn_hyper_connection.input_mix_weight_up",
      "mtp.layers.0.mlp.gate",
      "mtp.layers.0.mlp.shared_expert.down_proj",
      "mtp.layers.0.mlp.shared_expert.gate_proj",
      "mtp.layers.0.mlp.shared_expert.up_proj",
      "mtp.layers.0.mlp.shared_expert_gate",
      "mtp.layers.0.mlp_hyper_connection.block_inject_weight",
      "mtp.layers.0.mlp_hyper_connection.input_mix_weight_down",
      "mtp.layers.0.mlp_hyper_connection.input_mix_weight_up",
      "mtp.layers.0.self_attn.indexer.index_qk_proj",
      "mtp.layers.0.self_attn.k_proj",
      "mtp.layers.0.self_attn.o_proj",
      "mtp.layers.0.self_attn.q_proj",
      "mtp.layers.0.self_attn.v_proj"
    ],
    "modules_to_convert": [
      "ple.ple_embedding.ngram_embedding"
    ]
  }
}

	{
	"architectures": [
	"Qwen4ExpForConditionalGeneration"
	],
	"image_token_id": 248056,
	"language_model_only": false,
	"model_type": "qwen4_exp",
	"text_config": {
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 248044,
	"dtype": "bfloat16",
	"eos_token_id": 248044,
	"full_attention_interval": 4,
	"hc_count": 4,
	"hc_lowrank": 4,
	"head_dim": 32,
	"heads_per_ngram": 8,
	"hidden_act": "silu",
	"hidden_size": 32,
	"indexer_budget": 2048,
	"indexer_compress_ratio": 4,
	"indexer_head_dim": 128,
	"indexer_kv_heads": 1,
	"indexer_n_heads": 4,
	"initializer_range": 0.02,
	"layer_types": [
	"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": 32,
	"linear_num_key_heads": 4,
	"linear_num_value_heads": 12,
	"linear_value_head_dim": 32,
	"make_ngram_vocab_size_divisible_by": 128,
	"mamba_ssm_dtype": "float32",
	"max_position_embeddings": 262144,
	"model_type": "qwen4_exp_text",
	"moe_intermediate_size": 128,
	"mtp": {
	"hybrid": true,
	"layer_types": [
	"full_attention"
	],
	"mtp_use_hidden_state_from_layer": null,
	"num_hidden_layers": 1,
	"rope_theta": 10000000
	},
	"mtp_num_hidden_layers": 1,
	"mtp_use_dedicated_embeddings": false,
	"ngram_size": 3,
	"ngram_vocab_size_base": 512,
	"num_attention_heads": 12,
	"num_experts": 32,
	"num_experts_per_tok": 10,
	"num_hidden_layers": 8,
	"num_key_value_heads": 1,
	"output_gate_type": "sigmoid",
	"output_router_logits": false,
	"pad_token_id": null,
	"partial_rotary_factor": 0.25,
	"ple_conv_kernel_size": 4,
	"ple_embed_dim": 16,
	"ple_layer_ids": [
	2
	],
	"rms_norm_eps": 1e-06,
	"rope_parameters": {
	"mrope_interleaved": true,
	"mrope_section": [
	2,
	1,
	1
	],
	"partial_rotary_factor": 0.25,
	"rope_theta": 10000000,
	"rope_type": "default"
	},
	"router_aux_loss_coef": 0.001,
	"shared_expert_intermediate_size": 128,
	"split_ngram_parts": 128,
	"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": 2,
	"hidden_act": "gelu_pytorch_tanh",
	"hidden_size": 64,
	"in_channels": 3,
	"initializer_range": 0.02,
	"intermediate_size": 128,
	"model_type": "qwen4_exp",
	"num_heads": 4,
	"num_position_embeddings": 2304,
	"out_hidden_size": 32,
	"patch_size": 16,
	"spatial_merge_size": 2,
	"temporal_patch_size": 2
	},
	"vision_end_token_id": 248054,
	"vision_start_token_id": 248053,
	"quantization_config": {
	"quant_method": "fp8",
	"activation_scheme": "dynamic",
	"weight_per_tensor": false,
	"act_per_tensor": false,
	"weight_block_size": [
	32,
	32
	],
	"modules_to_not_convert": [
	"lm_head",
	"model.language_model.embed_tokens",
	"model.language_model.hyper_connection_mixer.input_mix_weight_down",
	"model.language_model.hyper_connection_mixer.input_mix_weight_up",
	"model.language_model.layers.0.attn_hyper_connection.block_inject_weight",
	"model.language_model.layers.0.attn_hyper_connection.input_mix_weight_down",
	"model.language_model.layers.0.attn_hyper_connection.input_mix_weight_up",
	"model.language_model.layers.0.linear_attn.conv1d",
	"model.language_model.layers.0.linear_attn.in_proj_a",
	"model.language_model.layers.0.linear_attn.in_proj_b",
	"model.language_model.layers.0.linear_attn.in_proj_qkv",
	"model.language_model.layers.0.linear_attn.in_proj_z",
	"model.language_model.layers.0.linear_attn.out_proj",
	"model.language_model.layers.0.mlp.gate",
	"model.language_model.layers.0.mlp.shared_expert.down_proj",
	"model.language_model.layers.0.mlp.shared_expert.gate_proj",
	"model.language_model.layers.0.mlp.shared_expert.up_proj",
	"model.language_model.layers.0.mlp.shared_expert_gate",
	"model.language_model.layers.0.mlp_hyper_connection.block_inject_weight",
	"model.language_model.layers.0.mlp_hyper_connection.input_mix_weight_down",
	"model.language_model.layers.0.mlp_hyper_connection.input_mix_weight_up",
	"model.language_model.layers.1.attn_hyper_connection.block_inject_weight",
	"model.language_model.layers.1.attn_hyper_connection.input_mix_weight_down",
	"model.language_model.layers.1.attn_hyper_connection.input_mix_weight_up",
	"model.language_model.layers.1.linear_attn.conv1d",
	"model.language_model.layers.1.linear_attn.in_proj_a",
	"model.language_model.layers.1.linear_attn.in_proj_b",
	"model.language_model.layers.1.linear_attn.in_proj_qkv",
	"model.language_model.layers.1.linear_attn.in_proj_z",
	"model.language_model.layers.1.linear_attn.out_proj",
	"model.language_model.layers.1.mlp.gate",
	"model.language_model.layers.1.mlp.shared_expert.down_proj",
	"model.language_model.layers.1.mlp.shared_expert.gate_proj",
	"model.language_model.layers.1.mlp.shared_expert.up_proj",
	"model.language_model.layers.1.mlp.shared_expert_gate",
	"model.language_model.layers.1.mlp_hyper_connection.block_inject_weight",
	"model.language_model.layers.1.mlp_hyper_connection.input_mix_weight_down",
	"model.language_model.layers.1.mlp_hyper_connection.input_mix_weight_up",
	"model.language_model.layers.1.ple.conv1d",
	"model.language_model.layers.1.ple.key_proj",
	"model.language_model.layers.1.ple.value_proj",
	"model.language_model.layers.2.attn_hyper_connection.block_inject_weight",
	"model.language_model.layers.2.attn_hyper_connection.input_mix_weight_down",
	"model.language_model.layers.2.attn_hyper_connection.input_mix_weight_up",
	"model.language_model.layers.2.linear_attn.conv1d",
	"model.language_model.layers.2.linear_attn.in_proj_a",
	"model.language_model.layers.2.linear_attn.in_proj_b",
	"model.language_model.layers.2.linear_attn.in_proj_qkv",
	"model.language_model.layers.2.linear_attn.in_proj_z",
	"model.language_model.layers.2.linear_attn.out_proj",
	"model.language_model.layers.2.mlp.gate",
	"model.language_model.layers.2.mlp.shared_expert.down_proj",
	"model.language_model.layers.2.mlp.shared_expert.gate_proj",
	"model.language_model.layers.2.mlp.shared_expert.up_proj",
	"model.language_model.layers.2.mlp.shared_expert_gate",
	"model.language_model.layers.2.mlp_hyper_connection.block_inject_weight",
	"model.language_model.layers.2.mlp_hyper_connection.input_mix_weight_down",
	"model.language_model.layers.2.mlp_hyper_connection.input_mix_weight_up",
	"model.language_model.layers.3.attn_hyper_connection.block_inject_weight",
	"model.language_model.layers.3.attn_hyper_connection.input_mix_weight_down",
	"model.language_model.layers.3.attn_hyper_connection.input_mix_weight_up",
	"model.language_model.layers.3.mlp.gate",
	"model.language_model.layers.3.mlp.shared_expert.down_proj",
	"model.language_model.layers.3.mlp.shared_expert.gate_proj",
	"model.language_model.layers.3.mlp.shared_expert.up_proj",
	"model.language_model.layers.3.mlp.shared_expert_gate",
	"model.language_model.layers.3.mlp_hyper_connection.block_inject_weight",
	"model.language_model.layers.3.mlp_hyper_connection.input_mix_weight_down",
	"model.language_model.layers.3.mlp_hyper_connection.input_mix_weight_up",
	"model.language_model.layers.3.self_attn.indexer.index_qk_proj",
	"model.language_model.layers.3.self_attn.k_proj",
	"model.language_model.layers.3.self_attn.o_proj",
	"model.language_model.layers.3.self_attn.q_proj",
	"model.language_model.layers.3.self_attn.v_proj",
	"model.language_model.layers.4.attn_hyper_connection.block_inject_weight",
	"model.language_model.layers.4.attn_hyper_connection.input_mix_weight_down",
	"model.language_model.layers.4.attn_hyper_connection.input_mix_weight_up",
	"model.language_model.layers.4.linear_attn.conv1d",
	"model.language_model.layers.4.linear_attn.in_proj_a",
	"model.language_model.layers.4.linear_attn.in_proj_b",
	"model.language_model.layers.4.linear_attn.in_proj_qkv",
	"model.language_model.layers.4.linear_attn.in_proj_z",
	"model.language_model.layers.4.linear_attn.out_proj",
	"model.language_model.layers.4.mlp.gate",
	"model.language_model.layers.4.mlp.shared_expert.down_proj",
	"model.language_model.layers.4.mlp.shared_expert.gate_proj",
	"model.language_model.layers.4.mlp.shared_expert.up_proj",
	"model.language_model.layers.4.mlp.shared_expert_gate",
	"model.language_model.layers.4.mlp_hyper_connection.block_inject_weight",
	"model.language_model.layers.4.mlp_hyper_connection.input_mix_weight_down",
	"model.language_model.layers.4.mlp_hyper_connection.input_mix_weight_up",
	"model.language_model.layers.5.attn_hyper_connection.block_inject_weight",
	"model.language_model.layers.5.attn_hyper_connection.input_mix_weight_down",
	"model.language_model.layers.5.attn_hyper_connection.input_mix_weight_up",
	"model.language_model.layers.5.linear_attn.conv1d",
	"model.language_model.layers.5.linear_attn.in_proj_a",
	"model.language_model.layers.5.linear_attn.in_proj_b",
	"model.language_model.layers.5.linear_attn.in_proj_qkv",
	"model.language_model.layers.5.linear_attn.in_proj_z",
	"model.language_model.layers.5.linear_attn.out_proj",
	"model.language_model.layers.5.mlp.gate",
	"model.language_model.layers.5.mlp.shared_expert.down_proj",
	"model.language_model.layers.5.mlp.shared_expert.gate_proj",
	"model.language_model.layers.5.mlp.shared_expert.up_proj",
	"model.language_model.layers.5.mlp.shared_expert_gate",
	"model.language_model.layers.5.mlp_hyper_connection.block_inject_weight",
	"model.language_model.layers.5.mlp_hyper_connection.input_mix_weight_down",
	"model.language_model.layers.5.mlp_hyper_connection.input_mix_weight_up",
	"model.language_model.layers.6.attn_hyper_connection.block_inject_weight",
	"model.language_model.layers.6.attn_hyper_connection.input_mix_weight_down",
	"model.language_model.layers.6.attn_hyper_connection.input_mix_weight_up",
	"model.language_model.layers.6.linear_attn.conv1d",
	"model.language_model.layers.6.linear_attn.in_proj_a",
	"model.language_model.layers.6.linear_attn.in_proj_b",
	"model.language_model.layers.6.linear_attn.in_proj_qkv",
	"model.language_model.layers.6.linear_attn.in_proj_z",
	"model.language_model.layers.6.linear_attn.out_proj",
	"model.language_model.layers.6.mlp.gate",
	"model.language_model.layers.6.mlp.shared_expert.down_proj",
	"model.language_model.layers.6.mlp.shared_expert.gate_proj",
	"model.language_model.layers.6.mlp.shared_expert.up_proj",
	"model.language_model.layers.6.mlp.shared_expert_gate",
	"model.language_model.layers.6.mlp_hyper_connection.block_inject_weight",
	"model.language_model.layers.6.mlp_hyper_connection.input_mix_weight_down",
	"model.language_model.layers.6.mlp_hyper_connection.input_mix_weight_up",
	"model.language_model.layers.7.attn_hyper_connection.block_inject_weight",
	"model.language_model.layers.7.attn_hyper_connection.input_mix_weight_down",
	"model.language_model.layers.7.attn_hyper_connection.input_mix_weight_up",
	"model.language_model.layers.7.mlp.gate",
	"model.language_model.layers.7.mlp.shared_expert.down_proj",
	"model.language_model.layers.7.mlp.shared_expert.gate_proj",
	"model.language_model.layers.7.mlp.shared_expert.up_proj",
	"model.language_model.layers.7.mlp.shared_expert_gate",
	"model.language_model.layers.7.mlp_hyper_connection.block_inject_weight",
	"model.language_model.layers.7.mlp_hyper_connection.input_mix_weight_down",
	"model.language_model.layers.7.mlp_hyper_connection.input_mix_weight_up",
	"model.language_model.layers.7.self_attn.indexer.index_qk_proj",
	"model.language_model.layers.7.self_attn.k_proj",
	"model.language_model.layers.7.self_attn.o_proj",
	"model.language_model.layers.7.self_attn.q_proj",
	"model.language_model.layers.7.self_attn.v_proj",
	"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",
	"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",
	"model.visual.merger.linear_fc1",
	"model.visual.merger.linear_fc2",
	"model.visual.patch_embed.proj",
	"model.visual.pos_embed",
	"mtp.fc_embedding",
	"mtp.fc_hidden",
	"mtp.hyper_connection_mixer.input_mix_weight_down",
	"mtp.hyper_connection_mixer.input_mix_weight_up",
	"mtp.layers.0.attn_hyper_connection.block_inject_weight",
	"mtp.layers.0.attn_hyper_connection.input_mix_weight_down",
	"mtp.layers.0.attn_hyper_connection.input_mix_weight_up",
	"mtp.layers.0.mlp.gate",
	"mtp.layers.0.mlp.shared_expert.down_proj",
	"mtp.layers.0.mlp.shared_expert.gate_proj",
	"mtp.layers.0.mlp.shared_expert.up_proj",
	"mtp.layers.0.mlp.shared_expert_gate",
	"mtp.layers.0.mlp_hyper_connection.block_inject_weight",
	"mtp.layers.0.mlp_hyper_connection.input_mix_weight_down",
	"mtp.layers.0.mlp_hyper_connection.input_mix_weight_up",
	"mtp.layers.0.self_attn.indexer.index_qk_proj",
	"mtp.layers.0.self_attn.k_proj",
	"mtp.layers.0.self_attn.o_proj",
	"mtp.layers.0.self_attn.q_proj",
	"mtp.layers.0.self_attn.v_proj"
	],
	"modules_to_convert": [
	"ple.ple_embedding.ngram_embedding"
	]
	}
	}