Instructions to use yujiepan/mistral-large-4-tiny-random with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yujiepan/mistral-large-4-tiny-random with Transformers:

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

pipe = pipeline("image-text-to-text", model="yujiepan/mistral-large-4-tiny-random")
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("yujiepan/mistral-large-4-tiny-random")
model = AutoModelForMultimodalLM.from_pretrained("yujiepan/mistral-large-4-tiny-random", 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 yujiepan/mistral-large-4-tiny-random with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yujiepan/mistral-large-4-tiny-random"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yujiepan/mistral-large-4-tiny-random",
		"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/yujiepan/mistral-large-4-tiny-random

SGLang

How to use yujiepan/mistral-large-4-tiny-random 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 "yujiepan/mistral-large-4-tiny-random" \
    --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": "yujiepan/mistral-large-4-tiny-random",
		"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 "yujiepan/mistral-large-4-tiny-random" \
        --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": "yujiepan/mistral-large-4-tiny-random",
		"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 yujiepan/mistral-large-4-tiny-random with Docker Model Runner:
```
docker model run hf.co/yujiepan/mistral-large-4-tiny-random
```

mistral-large-4-tiny-random / params.json

yujiepan

Duplicate from tiny-random/mistral-large-4

57dbcb4 about 20 hours ago

Raw History Blame Contribute Delete

2.4 kB

{
  "dim": 128,
  "n_layers": 12,
  "head_dim": 32,
  "hidden_dim": 128,
  "n_heads": 4,
  "n_kv_heads": 4,
  "rope_theta": 10000.0,
  "norm_eps": 1e-05,
  "vocab_size": 204800,
  "tied_embeddings": true,
  "max_position_embeddings": 1048576,
  "ragged_attention": null,
  "nope": "rope,rope,rope,nope",
  "softmax_tanh_gating": 30.0,
  "llama_4_scaling": null,
  "q_lora_rank": null,
  "qk_rope_head_dim": 64,
  "qk_nope_head_dim": 64,
  "kv_lora_rank": 512,
  "v_head_dim": 128,
  "ssmax_scaling": true,
  "lerope": true,
  "dsa": {
    "topk": 128,
    "n_heads": 4,
    "head_dim": 128,
    "rope_head_dim": 64,
    "match_nope": true,
    "ssmax_scaling": true,
    "norm_eps": 1e-06,
    "sharing": "full,full,full,full,full,full,shared,shared,full,full,shared,shared",
    "fp8_indexer": true,
    "fp8_kv_cache": true
  },
  "quantization": {
    "qscheme_act": "BLOCK",
    "qformat_weight": "fp8_e4m3",
    "qdynamic_act": true,
    "qscheme_weight": "BLOCK",
    "use_ue8m0_for_qscales": true,
    "block_size_out": 64,
    "block_size_in": 64,
    "quantize_kv_a": false
  },
  "yarn": {
    "original_max_position_embeddings": 512,
    "factor": 2048,
    "apply_scale": false,
    "beta": 32,
    "alpha": 1
  },
  "kv_sharing": {
    "source_layers_str": "0,1,2,3,4,5,6,3,8,9,10,3"
  },
  "moe": {
    "expert_parallel": 1,
    "expert_model_parallel": 1,
    "route_every_n": 1,
    "first_k_dense_replace": 1,
    "num_experts": 32,
    "num_experts_per_tok": 4,
    "num_expert_groups": 1,
    "num_expert_groups_per_tok": 1,
    "routed_scale": 1.0,
    "expert_hidden_dim": 128,
    "num_shared_experts": 1
  },
  "vision_encoder": {
    "image_token_id": 10,
    "image_break_token_id": 12,
    "image_end_token_id": 13,
    "intermediate_size": 128,
    "num_hidden_layers": 4,
    "num_attention_heads": 2,
    "mm_projector_id": "patch_merge",
    "spatial_merge_size": 2,
    "hidden_size": 64,
    "num_channels": 3,
    "image_size": 1540,
    "max_image_size": 1540,
    "patch_size": 14,
    "rope_theta": 10000.0,
    "add_pre_mm_projector_layer_norm": true,
    "adapter_bias": false
  },
  "mtp": {
    "n_layers": 3,
    "depth": 3,
    "ragged_attention": "32,32,32",
    "target_activation_layers": "1,4,7,10,11",
    "norm_strategy": "eagle",
    "dspark": {
      "markov_rank": 4,
      "head_type": "rnn",
      "draft_input": "position_specific"
    }
  }
}

	{
	"dim": 128,
	"n_layers": 12,
	"head_dim": 32,
	"hidden_dim": 128,
	"n_heads": 4,
	"n_kv_heads": 4,
	"rope_theta": 10000.0,
	"norm_eps": 1e-05,
	"vocab_size": 204800,
	"tied_embeddings": true,
	"max_position_embeddings": 1048576,
	"ragged_attention": null,
	"nope": "rope,rope,rope,nope",
	"softmax_tanh_gating": 30.0,
	"llama_4_scaling": null,
	"q_lora_rank": null,
	"qk_rope_head_dim": 64,
	"qk_nope_head_dim": 64,
	"kv_lora_rank": 512,
	"v_head_dim": 128,
	"ssmax_scaling": true,
	"lerope": true,
	"dsa": {
	"topk": 128,
	"n_heads": 4,
	"head_dim": 128,
	"rope_head_dim": 64,
	"match_nope": true,
	"ssmax_scaling": true,
	"norm_eps": 1e-06,
	"sharing": "full,full,full,full,full,full,shared,shared,full,full,shared,shared",
	"fp8_indexer": true,
	"fp8_kv_cache": true
	},
	"quantization": {
	"qscheme_act": "BLOCK",
	"qformat_weight": "fp8_e4m3",
	"qdynamic_act": true,
	"qscheme_weight": "BLOCK",
	"use_ue8m0_for_qscales": true,
	"block_size_out": 64,
	"block_size_in": 64,
	"quantize_kv_a": false
	},
	"yarn": {
	"original_max_position_embeddings": 512,
	"factor": 2048,
	"apply_scale": false,
	"beta": 32,
	"alpha": 1
	},
	"kv_sharing": {
	"source_layers_str": "0,1,2,3,4,5,6,3,8,9,10,3"
	},
	"moe": {
	"expert_parallel": 1,
	"expert_model_parallel": 1,
	"route_every_n": 1,
	"first_k_dense_replace": 1,
	"num_experts": 32,
	"num_experts_per_tok": 4,
	"num_expert_groups": 1,
	"num_expert_groups_per_tok": 1,
	"routed_scale": 1.0,
	"expert_hidden_dim": 128,
	"num_shared_experts": 1
	},
	"vision_encoder": {
	"image_token_id": 10,
	"image_break_token_id": 12,
	"image_end_token_id": 13,
	"intermediate_size": 128,
	"num_hidden_layers": 4,
	"num_attention_heads": 2,
	"mm_projector_id": "patch_merge",
	"spatial_merge_size": 2,
	"hidden_size": 64,
	"num_channels": 3,
	"image_size": 1540,
	"max_image_size": 1540,
	"patch_size": 14,
	"rope_theta": 10000.0,
	"add_pre_mm_projector_layer_norm": true,
	"adapter_bias": false
	},
	"mtp": {
	"n_layers": 3,
	"depth": 3,
	"ragged_attention": "32,32,32",
	"target_activation_layers": "1,4,7,10,11",
	"norm_strategy": "eagle",
	"dspark": {
	"markov_rank": 4,
	"head_type": "rnn",
	"draft_input": "position_specific"
	}
	}
	}