Instructions to use MiniMaxAI/MiniMax-M3.1-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MiniMaxAI/MiniMax-M3.1-Flash with Transformers:

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

pipe = pipeline("image-text-to-text", model="MiniMaxAI/MiniMax-M3.1-Flash", trust_remote_code=True)
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("MiniMaxAI/MiniMax-M3.1-Flash", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("MiniMaxAI/MiniMax-M3.1-Flash", trust_remote_code=True, 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]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MiniMaxAI/MiniMax-M3.1-Flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MiniMaxAI/MiniMax-M3.1-Flash"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MiniMaxAI/MiniMax-M3.1-Flash",
		"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/MiniMaxAI/MiniMax-M3.1-Flash

SGLang

How to use MiniMaxAI/MiniMax-M3.1-Flash 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 "MiniMaxAI/MiniMax-M3.1-Flash" \
    --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": "MiniMaxAI/MiniMax-M3.1-Flash",
		"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 "MiniMaxAI/MiniMax-M3.1-Flash" \
        --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": "MiniMaxAI/MiniMax-M3.1-Flash",
		"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 MiniMaxAI/MiniMax-M3.1-Flash with Docker Model Runner:
```
docker model run hf.co/MiniMaxAI/MiniMax-M3.1-Flash
```

MiniMax-M3.1-Flash / dspark /model.safetensors.index.json

Init MiniMaxAI/MiniMax-M3.1-Flash

54e4e69 10 days ago

Raw History Blame Contribute Delete

11.4 kB

{
  "metadata": {
    "total_size": 2301852674
  },
  "weight_map": {
    "language_model.model.dspark.confidence_head.proj.bias": "model-dspark-00001.safetensors",
    "language_model.model.dspark.confidence_head.proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.fc.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.final_norm.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.hidden_norm.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.0.decoder_layer.input_layernorm.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.0.decoder_layer.mlp.down_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.0.decoder_layer.mlp.down_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.0.decoder_layer.mlp.gate_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.0.decoder_layer.mlp.gate_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.0.decoder_layer.mlp.up_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.0.decoder_layer.mlp.up_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.0.decoder_layer.post_attention_layernorm.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.0.decoder_layer.self_attn.k_norm.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.0.decoder_layer.self_attn.k_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.0.decoder_layer.self_attn.k_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.0.decoder_layer.self_attn.o_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.0.decoder_layer.self_attn.o_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.0.decoder_layer.self_attn.q_norm.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.0.decoder_layer.self_attn.q_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.0.decoder_layer.self_attn.q_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.0.decoder_layer.self_attn.v_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.0.decoder_layer.self_attn.v_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.1.decoder_layer.input_layernorm.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.1.decoder_layer.mlp.down_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.1.decoder_layer.mlp.down_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.1.decoder_layer.mlp.gate_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.1.decoder_layer.mlp.gate_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.1.decoder_layer.mlp.up_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.1.decoder_layer.mlp.up_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.1.decoder_layer.post_attention_layernorm.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.1.decoder_layer.self_attn.k_norm.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.1.decoder_layer.self_attn.k_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.1.decoder_layer.self_attn.k_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.1.decoder_layer.self_attn.o_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.1.decoder_layer.self_attn.o_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.1.decoder_layer.self_attn.q_norm.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.1.decoder_layer.self_attn.q_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.1.decoder_layer.self_attn.q_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.1.decoder_layer.self_attn.v_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.1.decoder_layer.self_attn.v_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.2.decoder_layer.input_layernorm.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.2.decoder_layer.mlp.down_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.2.decoder_layer.mlp.down_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.2.decoder_layer.mlp.gate_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.2.decoder_layer.mlp.gate_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.2.decoder_layer.mlp.up_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.2.decoder_layer.mlp.up_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.2.decoder_layer.post_attention_layernorm.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.2.decoder_layer.self_attn.k_norm.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.2.decoder_layer.self_attn.k_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.2.decoder_layer.self_attn.k_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.2.decoder_layer.self_attn.o_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.2.decoder_layer.self_attn.o_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.2.decoder_layer.self_attn.q_norm.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.2.decoder_layer.self_attn.q_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.2.decoder_layer.self_attn.q_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.2.decoder_layer.self_attn.v_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.2.decoder_layer.self_attn.v_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.3.decoder_layer.input_layernorm.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.3.decoder_layer.mlp.down_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.3.decoder_layer.mlp.down_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.3.decoder_layer.mlp.gate_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.3.decoder_layer.mlp.gate_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.3.decoder_layer.mlp.up_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.3.decoder_layer.mlp.up_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.3.decoder_layer.post_attention_layernorm.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.3.decoder_layer.self_attn.k_norm.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.3.decoder_layer.self_attn.k_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.3.decoder_layer.self_attn.k_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.3.decoder_layer.self_attn.o_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.3.decoder_layer.self_attn.o_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.3.decoder_layer.self_attn.q_norm.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.3.decoder_layer.self_attn.q_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.3.decoder_layer.self_attn.q_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.3.decoder_layer.self_attn.v_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.3.decoder_layer.self_attn.v_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.4.decoder_layer.input_layernorm.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.4.decoder_layer.mlp.down_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.4.decoder_layer.mlp.down_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.4.decoder_layer.mlp.gate_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.4.decoder_layer.mlp.gate_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.4.decoder_layer.mlp.up_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.4.decoder_layer.mlp.up_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.4.decoder_layer.post_attention_layernorm.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.4.decoder_layer.self_attn.k_norm.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.4.decoder_layer.self_attn.k_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.4.decoder_layer.self_attn.k_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.4.decoder_layer.self_attn.o_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.4.decoder_layer.self_attn.o_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.4.decoder_layer.self_attn.q_norm.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.4.decoder_layer.self_attn.q_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.4.decoder_layer.self_attn.q_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.4.decoder_layer.self_attn.v_proj.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.layers.4.decoder_layer.self_attn.v_proj.weight_scale_inv": "model-dspark-00001.safetensors",
    "language_model.model.dspark.markov_head.markov_w1.weight": "model-dspark-00001.safetensors",
    "language_model.model.dspark.markov_head.markov_w2.weight": "model-dspark-00001.safetensors"
  }
}

	{
	"metadata": {
	"total_size": 2301852674
	},
	"weight_map": {
	"language_model.model.dspark.confidence_head.proj.bias": "model-dspark-00001.safetensors",
	"language_model.model.dspark.confidence_head.proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.fc.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.final_norm.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.hidden_norm.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.0.decoder_layer.input_layernorm.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.0.decoder_layer.mlp.down_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.0.decoder_layer.mlp.down_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.0.decoder_layer.mlp.gate_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.0.decoder_layer.mlp.gate_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.0.decoder_layer.mlp.up_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.0.decoder_layer.mlp.up_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.0.decoder_layer.post_attention_layernorm.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.0.decoder_layer.self_attn.k_norm.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.0.decoder_layer.self_attn.k_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.0.decoder_layer.self_attn.k_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.0.decoder_layer.self_attn.o_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.0.decoder_layer.self_attn.o_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.0.decoder_layer.self_attn.q_norm.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.0.decoder_layer.self_attn.q_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.0.decoder_layer.self_attn.q_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.0.decoder_layer.self_attn.v_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.0.decoder_layer.self_attn.v_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.1.decoder_layer.input_layernorm.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.1.decoder_layer.mlp.down_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.1.decoder_layer.mlp.down_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.1.decoder_layer.mlp.gate_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.1.decoder_layer.mlp.gate_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.1.decoder_layer.mlp.up_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.1.decoder_layer.mlp.up_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.1.decoder_layer.post_attention_layernorm.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.1.decoder_layer.self_attn.k_norm.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.1.decoder_layer.self_attn.k_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.1.decoder_layer.self_attn.k_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.1.decoder_layer.self_attn.o_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.1.decoder_layer.self_attn.o_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.1.decoder_layer.self_attn.q_norm.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.1.decoder_layer.self_attn.q_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.1.decoder_layer.self_attn.q_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.1.decoder_layer.self_attn.v_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.1.decoder_layer.self_attn.v_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.2.decoder_layer.input_layernorm.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.2.decoder_layer.mlp.down_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.2.decoder_layer.mlp.down_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.2.decoder_layer.mlp.gate_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.2.decoder_layer.mlp.gate_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.2.decoder_layer.mlp.up_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.2.decoder_layer.mlp.up_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.2.decoder_layer.post_attention_layernorm.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.2.decoder_layer.self_attn.k_norm.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.2.decoder_layer.self_attn.k_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.2.decoder_layer.self_attn.k_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.2.decoder_layer.self_attn.o_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.2.decoder_layer.self_attn.o_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.2.decoder_layer.self_attn.q_norm.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.2.decoder_layer.self_attn.q_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.2.decoder_layer.self_attn.q_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.2.decoder_layer.self_attn.v_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.2.decoder_layer.self_attn.v_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.3.decoder_layer.input_layernorm.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.3.decoder_layer.mlp.down_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.3.decoder_layer.mlp.down_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.3.decoder_layer.mlp.gate_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.3.decoder_layer.mlp.gate_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.3.decoder_layer.mlp.up_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.3.decoder_layer.mlp.up_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.3.decoder_layer.post_attention_layernorm.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.3.decoder_layer.self_attn.k_norm.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.3.decoder_layer.self_attn.k_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.3.decoder_layer.self_attn.k_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.3.decoder_layer.self_attn.o_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.3.decoder_layer.self_attn.o_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.3.decoder_layer.self_attn.q_norm.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.3.decoder_layer.self_attn.q_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.3.decoder_layer.self_attn.q_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.3.decoder_layer.self_attn.v_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.3.decoder_layer.self_attn.v_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.4.decoder_layer.input_layernorm.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.4.decoder_layer.mlp.down_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.4.decoder_layer.mlp.down_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.4.decoder_layer.mlp.gate_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.4.decoder_layer.mlp.gate_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.4.decoder_layer.mlp.up_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.4.decoder_layer.mlp.up_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.4.decoder_layer.post_attention_layernorm.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.4.decoder_layer.self_attn.k_norm.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.4.decoder_layer.self_attn.k_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.4.decoder_layer.self_attn.k_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.4.decoder_layer.self_attn.o_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.4.decoder_layer.self_attn.o_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.4.decoder_layer.self_attn.q_norm.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.4.decoder_layer.self_attn.q_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.4.decoder_layer.self_attn.q_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.4.decoder_layer.self_attn.v_proj.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.layers.4.decoder_layer.self_attn.v_proj.weight_scale_inv": "model-dspark-00001.safetensors",
	"language_model.model.dspark.markov_head.markov_w1.weight": "model-dspark-00001.safetensors",
	"language_model.model.dspark.markov_head.markov_w2.weight": "model-dspark-00001.safetensors"
	}
	}