Instructions to use DronE900/collegihein with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DronE900/collegihein with Transformers:

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

pipe = pipeline("image-text-to-text", model="DronE900/collegihein")
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("DronE900/collegihein")
model = AutoModelForMultimodalLM.from_pretrained("DronE900/collegihein", 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 DronE900/collegihein with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DronE900/collegihein"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DronE900/collegihein",
		"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/DronE900/collegihein

SGLang

How to use DronE900/collegihein 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 "DronE900/collegihein" \
    --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": "DronE900/collegihein",
		"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 "DronE900/collegihein" \
        --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": "DronE900/collegihein",
		"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 DronE900/collegihein with Docker Model Runner:
```
docker model run hf.co/DronE900/collegihein
```

collegihein / config.json

DronE900

juliendenize

Duplicate from mistralai/Mistral-Large-4-1T-A52B

c72ed9e 4 days ago

Raw History Blame Contribute Delete

8.22 kB

{
  "architectures": ["MistralLarge4ForConditionalGeneration"],
  "dtype": "bfloat16",
  "image_token_index": 10,
  "model_type": "mistral_large4",
  "multimodal_projector_bias": false,
  "projector_hidden_act": "gelu",
  "quantization_config": {
    "activation_scheme": "dynamic",
    "modules_to_not_convert": [
      "model.vision_tower",
      "model.multi_modal_projector",
      "lm_head",
      "kv_b_proj",
      "indexer.wk",
      "indexer.weights_proj",
      "kv_a_proj_with_mqa"
    ],
    "quant_method": "fp8",
    "weight_block_size": [
      128,
      128
    ]
  },
  "spatial_merge_size": 2,
  "text_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 1,
    "eos_token_id": 2,
    "final_logit_softcapping": 30.0,
    "first_k_dense_replace": 1,
    "head_dim": 64,
    "hidden_act": "silu",
    "hidden_size": 6144,
    "index_head_dim": 128,
    "index_n_heads": 32,
    "index_topk": 2048,
    "indexer_types": [
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "full",
      "shared",
      "shared",
      "full",
      "full",
      "shared",
      "shared",
      "full",
      "full",
      "shared",
      "shared",
      "full",
      "full",
      "shared",
      "shared",
      "full",
      "full",
      "shared",
      "shared",
      "full",
      "full",
      "shared",
      "shared",
      "full",
      "full",
      "shared",
      "shared",
      "full",
      "full",
      "shared",
      "shared",
      "full",
      "full",
      "shared",
      "shared",
      "full",
      "full",
      "shared",
      "shared",
      "full",
      "full",
      "shared",
      "shared",
      "full",
      "full",
      "shared",
      "shared",
      "full",
      "full",
      "shared",
      "shared",
      "full",
      "full",
      "shared",
      "shared",
      "full"
    ],
    "initializer_range": 0.02,
    "intermediate_size": 24576,
    "kv_lora_rank": 512,
    "kv_source_layers": [
      0,
      1,
      2,
      3,
      4,
      5,
      6,
      7,
      8,
      9,
      10,
      11,
      12,
      13,
      14,
      15,
      16,
      17,
      18,
      19,
      20,
      21,
      22,
      23,
      24,
      25,
      26,
      27,
      28,
      29,
      30,
      31,
      32,
      33,
      34,
      35,
      36,
      37,
      38,
      35,
      40,
      41,
      42,
      35,
      44,
      45,
      46,
      35,
      48,
      49,
      50,
      35,
      52,
      53,
      54,
      35,
      56,
      57,
      58,
      35,
      60,
      61,
      62,
      35,
      64,
      65,
      66,
      35,
      68,
      69,
      70,
      35
    ],
    "layer_types": [
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention",
      "indexed_attention"
    ],
    "max_position_embeddings": 1048576,
    "mlp_layer_types": [
      "dense",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse",
      "sparse"
    ],
    "model_type": "mistral_large4_text",
    "moe_intermediate_size": 6144,
    "n_group": 1,
    "n_routed_experts": 128,
    "n_shared_experts": 1,
    "no_rope_layer_interval": 4,
    "no_rope_layers": [
      1,
      1,
      1,
      0,
      1,
      1,
      1,
      0,
      1,
      1,
      1,
      0,
      1,
      1,
      1,
      0,
      1,
      1,
      1,
      0,
      1,
      1,
      1,
      0,
      1,
      1,
      1,
      0,
      1,
      1,
      1,
      0,
      1,
      1,
      1,
      0,
      1,
      1,
      1,
      0,
      1,
      1,
      1,
      0,
      1,
      1,
      1,
      0,
      1,
      1,
      1,
      0,
      1,
      1,
      1,
      0,
      1,
      1,
      1,
      0,
      1,
      1,
      1,
      0,
      1,
      1,
      1,
      0,
      1,
      1,
      1,
      0
    ],
    "num_attention_heads": 64,
    "num_experts_per_tok": 4,
    "num_hidden_layers": 72,
    "num_key_value_heads": 64,
    "output_router_logits": false,
    "pad_token_id": null,
    "qk_head_dim": 128,
    "qk_nope_head_dim": 64,
    "qk_rope_head_dim": 64,
    "rms_norm_eps": 1e-05,
    "rope_parameters": {
      "attention_factor": 1.0,
      "beta_fast": 32,
      "beta_slow": 1,
      "factor": 2048,
      "original_max_position_embeddings": 512,
      "rope_theta": 10000.0,
      "rope_type": "yarn"
    },
    "routed_scaling_factor": 1.0,
    "tie_word_embeddings": false,
    "topk_group": 1,
    "use_cache": true,
    "v_head_dim": 128,
    "vocab_size": 204800
  },
  "tie_word_embeddings": false,
  "transformers_version": "5.21.0.dev0",
  "transformers_weights": "consolidated.safetensors.index.json",
  "vision_config": {
    "attention_dropout": 0.0,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 2048,
    "image_size": 1540,
    "initializer_range": 0.02,
    "intermediate_size": 6144,
    "model_type": "pixtral",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 30,
    "patch_size": 14,
    "rope_parameters": {
      "rope_theta": 10000.0,
      "rope_type": "axial"
    }
  },
  "vision_feature_layer": -1
}

	{
	"architectures": ["MistralLarge4ForConditionalGeneration"],
	"dtype": "bfloat16",
	"image_token_index": 10,
	"model_type": "mistral_large4",
	"multimodal_projector_bias": false,
	"projector_hidden_act": "gelu",
	"quantization_config": {
	"activation_scheme": "dynamic",
	"modules_to_not_convert": [
	"model.vision_tower",
	"model.multi_modal_projector",
	"lm_head",
	"kv_b_proj",
	"indexer.wk",
	"indexer.weights_proj",
	"kv_a_proj_with_mqa"
	],
	"quant_method": "fp8",
	"weight_block_size": [
	128,
	128
	]
	},
	"spatial_merge_size": 2,
	"text_config": {
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 1,
	"eos_token_id": 2,
	"final_logit_softcapping": 30.0,
	"first_k_dense_replace": 1,
	"head_dim": 64,
	"hidden_act": "silu",
	"hidden_size": 6144,
	"index_head_dim": 128,
	"index_n_heads": 32,
	"index_topk": 2048,
	"indexer_types": [
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"full",
	"shared",
	"shared",
	"full",
	"full",
	"shared",
	"shared",
	"full",
	"full",
	"shared",
	"shared",
	"full",
	"full",
	"shared",
	"shared",
	"full",
	"full",
	"shared",
	"shared",
	"full",
	"full",
	"shared",
	"shared",
	"full",
	"full",
	"shared",
	"shared",
	"full",
	"full",
	"shared",
	"shared",
	"full",
	"full",
	"shared",
	"shared",
	"full",
	"full",
	"shared",
	"shared",
	"full",
	"full",
	"shared",
	"shared",
	"full",
	"full",
	"shared",
	"shared",
	"full",
	"full",
	"shared",
	"shared",
	"full",
	"full",
	"shared",
	"shared",
	"full"
	],
	"initializer_range": 0.02,
	"intermediate_size": 24576,
	"kv_lora_rank": 512,
	"kv_source_layers": [
	0,
	1,
	2,
	3,
	4,
	5,
	6,
	7,
	8,
	9,
	10,
	11,
	12,
	13,
	14,
	15,
	16,
	17,
	18,
	19,
	20,
	21,
	22,
	23,
	24,
	25,
	26,
	27,
	28,
	29,
	30,
	31,
	32,
	33,
	34,
	35,
	36,
	37,
	38,
	35,
	40,
	41,
	42,
	35,
	44,
	45,
	46,
	35,
	48,
	49,
	50,
	35,
	52,
	53,
	54,
	35,
	56,
	57,
	58,
	35,
	60,
	61,
	62,
	35,
	64,
	65,
	66,
	35,
	68,
	69,
	70,
	35
	],
	"layer_types": [
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention",
	"indexed_attention"
	],
	"max_position_embeddings": 1048576,
	"mlp_layer_types": [
	"dense",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse",
	"sparse"
	],
	"model_type": "mistral_large4_text",
	"moe_intermediate_size": 6144,
	"n_group": 1,
	"n_routed_experts": 128,
	"n_shared_experts": 1,
	"no_rope_layer_interval": 4,
	"no_rope_layers": [
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0,
	1,
	1,
	1,
	0
	],
	"num_attention_heads": 64,
	"num_experts_per_tok": 4,
	"num_hidden_layers": 72,
	"num_key_value_heads": 64,
	"output_router_logits": false,
	"pad_token_id": null,
	"qk_head_dim": 128,
	"qk_nope_head_dim": 64,
	"qk_rope_head_dim": 64,
	"rms_norm_eps": 1e-05,
	"rope_parameters": {
	"attention_factor": 1.0,
	"beta_fast": 32,
	"beta_slow": 1,
	"factor": 2048,
	"original_max_position_embeddings": 512,
	"rope_theta": 10000.0,
	"rope_type": "yarn"
	},
	"routed_scaling_factor": 1.0,
	"tie_word_embeddings": false,
	"topk_group": 1,
	"use_cache": true,
	"v_head_dim": 128,
	"vocab_size": 204800
	},
	"tie_word_embeddings": false,
	"transformers_version": "5.21.0.dev0",
	"transformers_weights": "consolidated.safetensors.index.json",
	"vision_config": {
	"attention_dropout": 0.0,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 2048,
	"image_size": 1540,
	"initializer_range": 0.02,
	"intermediate_size": 6144,
	"model_type": "pixtral",
	"num_attention_heads": 16,
	"num_channels": 3,
	"num_hidden_layers": 30,
	"patch_size": 14,
	"rope_parameters": {
	"rope_theta": 10000.0,
	"rope_type": "axial"
	}
	},
	"vision_feature_layer": -1
	}