Instructions to use CowCorpus/Cluster3-Takeover-Llava with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CowCorpus/Cluster3-Takeover-Llava with Transformers:

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

pipe = pipeline("text-generation", model="CowCorpus/Cluster3-Takeover-Llava")
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("CowCorpus/Cluster3-Takeover-Llava")
model = AutoModelForMultimodalLM.from_pretrained("CowCorpus/Cluster3-Takeover-Llava", 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 CowCorpus/Cluster3-Takeover-Llava with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CowCorpus/Cluster3-Takeover-Llava"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CowCorpus/Cluster3-Takeover-Llava",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CowCorpus/Cluster3-Takeover-Llava

SGLang

How to use CowCorpus/Cluster3-Takeover-Llava 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 "CowCorpus/Cluster3-Takeover-Llava" \
    --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": "CowCorpus/Cluster3-Takeover-Llava",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "CowCorpus/Cluster3-Takeover-Llava" \
        --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": "CowCorpus/Cluster3-Takeover-Llava",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CowCorpus/Cluster3-Takeover-Llava with Docker Model Runner:
```
docker model run hf.co/CowCorpus/Cluster3-Takeover-Llava
```

Cluster3-Takeover-Llava / config.json

oaishi

Add SFT checkpoint (Llava 8B on CowCorpus)

1619bf1 verified 10 months ago

Raw History Blame Contribute Delete

1.95 kB

{
  "architectures": [
    "LlavaNextForConditionalGeneration"
  ],
  "hidden_size": 4096,
  "ignore_index": -100,
  "image_grid_pinpoints": [
    [
      336,
      672
    ],
    [
      672,
      336
    ],
    [
      672,
      672
    ],
    [
      1008,
      336
    ],
    [
      336,
      1008
    ]
  ],
  "image_seq_length": 576,
  "image_token_index": 128256,
  "model_type": "llava_next",
  "multimodal_projector_bias": true,
  "projector_hidden_act": "gelu",
  "text_config": {
    "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
    "architectures": [
      "LlamaForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 128000,
    "eos_token_id": 128009,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "initializer_range": 0.02,
    "intermediate_size": 14336,
    "max_position_embeddings": 8192,
    "mlp_bias": false,
    "model_type": "llama",
    "num_attention_heads": 32,
    "num_hidden_layers": 32,
    "num_key_value_heads": 8,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 500000.0,
    "torch_dtype": "float32",
    "use_cache": false,
    "vocab_size": 128320
  },
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.50.0",
  "use_cache": false,
  "use_image_newline_parameter": true,
  "vision_config": {
    "attention_dropout": 0.0,
    "hidden_act": "quick_gelu",
    "hidden_size": 1024,
    "image_size": 336,
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "layer_norm_eps": 1e-05,
    "model_type": "clip_vision_model",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 24,
    "patch_size": 14,
    "projection_dim": 768,
    "torch_dtype": "float32",
    "vocab_size": 32000
  },
  "vision_feature_layer": -2,
  "vision_feature_select_strategy": "default"
}

	{
	"architectures": [
	"LlavaNextForConditionalGeneration"
	],
	"hidden_size": 4096,
	"ignore_index": -100,
	"image_grid_pinpoints": [
	[
	336,
	672
	],
	[
	672,
	336
	],
	[
	672,
	672
	],
	[
	1008,
	336
	],
	[
	336,
	1008
	]
	],
	"image_seq_length": 576,
	"image_token_index": 128256,
	"model_type": "llava_next",
	"multimodal_projector_bias": true,
	"projector_hidden_act": "gelu",
	"text_config": {
	"_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
	"architectures": [
	"LlamaForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 128000,
	"eos_token_id": 128009,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 14336,
	"max_position_embeddings": 8192,
	"mlp_bias": false,
	"model_type": "llama",
	"num_attention_heads": 32,
	"num_hidden_layers": 32,
	"num_key_value_heads": 8,
	"pretraining_tp": 1,
	"rms_norm_eps": 1e-05,
	"rope_scaling": null,
	"rope_theta": 500000.0,
	"torch_dtype": "float32",
	"use_cache": false,
	"vocab_size": 128320
	},
	"tie_word_embeddings": false,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.50.0",
	"use_cache": false,
	"use_image_newline_parameter": true,
	"vision_config": {
	"attention_dropout": 0.0,
	"hidden_act": "quick_gelu",
	"hidden_size": 1024,
	"image_size": 336,
	"initializer_factor": 1.0,
	"initializer_range": 0.02,
	"intermediate_size": 4096,
	"layer_norm_eps": 1e-05,
	"model_type": "clip_vision_model",
	"num_attention_heads": 16,
	"num_channels": 3,
	"num_hidden_layers": 24,
	"patch_size": 14,
	"projection_dim": 768,
	"torch_dtype": "float32",
	"vocab_size": 32000
	},
	"vision_feature_layer": -2,
	"vision_feature_select_strategy": "default"
	}