Instructions to use nyanko7/llava-v1.6-34b-finetune with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nyanko7/llava-v1.6-34b-finetune with Transformers:

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

pipe = pipeline("text-generation", model="nyanko7/llava-v1.6-34b-finetune")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("nyanko7/llava-v1.6-34b-finetune")
model = AutoModelForCausalLM.from_pretrained("nyanko7/llava-v1.6-34b-finetune", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
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 nyanko7/llava-v1.6-34b-finetune with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nyanko7/llava-v1.6-34b-finetune"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nyanko7/llava-v1.6-34b-finetune",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nyanko7/llava-v1.6-34b-finetune

SGLang

How to use nyanko7/llava-v1.6-34b-finetune 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 "nyanko7/llava-v1.6-34b-finetune" \
    --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": "nyanko7/llava-v1.6-34b-finetune",
		"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 "nyanko7/llava-v1.6-34b-finetune" \
        --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": "nyanko7/llava-v1.6-34b-finetune",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nyanko7/llava-v1.6-34b-finetune with Docker Model Runner:
```
docker model run hf.co/nyanko7/llava-v1.6-34b-finetune
```

llava-v1.6-34b-finetune / config.json

nyanko7

Super-squash branch 'main' using huggingface_hub

8b5e2a1 verified over 2 years ago

Raw History Blame Contribute Delete

1.81 kB

{
  "_name_or_path": "liuhaotian/llava-v1.6-34b",
  "architectures": [
    "LlavaLlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 7,
  "freeze_backbone": false,
  "freeze_mm_mlp_adapter": false,
  "freeze_mm_vision_resampler": false,
  "hidden_act": "silu",
  "hidden_size": 7168,
  "image_aspect_ratio": "anyres",
  "image_crop_resolution": 224,
  "image_grid_pinpoints": [
    [
      336,
      672
    ],
    [
      672,
      336
    ],
    [
      672,
      672
    ],
    [
      1008,
      336
    ],
    [
      336,
      1008
    ]
  ],
  "image_split_resolution": 224,
  "image_token_index": 64002,
  "initializer_range": 0.02,
  "intermediate_size": 20480,
  "max_position_embeddings": 4096,
  "mm_hidden_size": 1024,
  "mm_patch_merge_type": "spatial_unpad",
  "mm_projector_lr": 2e-05,
  "mm_projector_type": "mlp2x_gelu",
  "mm_resampler_type": null,
  "mm_use_im_patch_token": false,
  "mm_use_im_start_end": false,
  "mm_vision_select_feature": "patch",
  "mm_vision_select_layer": -2,
  "mm_vision_tower": "openai/clip-vit-large-patch14-336",
  "mm_vision_tower_lr": 2e-06,
  "model_type": "llava",
  "num_attention_heads": 56,
  "num_hidden_layers": 60,
  "num_key_value_heads": 8,
  "pad_token_id": 0,
  "pretrain_mm_mlp_adapter": null,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 5000000.0,
  "tie_word_embeddings": false,
  "tokenizer_model_max_length": 4096,
  "tokenizer_padding_side": "right",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.39.2",
  "tune_mm_mlp_adapter": false,
  "tune_mm_vision_resampler": false,
  "tune_mm_vision_tower": true,
  "unfreeze_mm_vision_tower": true,
  "use_cache": true,
  "use_mm_proj": true,
  "vocab_size": 64000
}

	{
	"_name_or_path": "liuhaotian/llava-v1.6-34b",
	"architectures": [
	"LlavaLlamaForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 1,
	"eos_token_id": 7,
	"freeze_backbone": false,
	"freeze_mm_mlp_adapter": false,
	"freeze_mm_vision_resampler": false,
	"hidden_act": "silu",
	"hidden_size": 7168,
	"image_aspect_ratio": "anyres",
	"image_crop_resolution": 224,
	"image_grid_pinpoints": [
	[
	336,
	672
	],
	[
	672,
	336
	],
	[
	672,
	672
	],
	[
	1008,
	336
	],
	[
	336,
	1008
	]
	],
	"image_split_resolution": 224,
	"image_token_index": 64002,
	"initializer_range": 0.02,
	"intermediate_size": 20480,
	"max_position_embeddings": 4096,
	"mm_hidden_size": 1024,
	"mm_patch_merge_type": "spatial_unpad",
	"mm_projector_lr": 2e-05,
	"mm_projector_type": "mlp2x_gelu",
	"mm_resampler_type": null,
	"mm_use_im_patch_token": false,
	"mm_use_im_start_end": false,
	"mm_vision_select_feature": "patch",
	"mm_vision_select_layer": -2,
	"mm_vision_tower": "openai/clip-vit-large-patch14-336",
	"mm_vision_tower_lr": 2e-06,
	"model_type": "llava",
	"num_attention_heads": 56,
	"num_hidden_layers": 60,
	"num_key_value_heads": 8,
	"pad_token_id": 0,
	"pretrain_mm_mlp_adapter": null,
	"pretraining_tp": 1,
	"rms_norm_eps": 1e-05,
	"rope_scaling": null,
	"rope_theta": 5000000.0,
	"tie_word_embeddings": false,
	"tokenizer_model_max_length": 4096,
	"tokenizer_padding_side": "right",
	"torch_dtype": "bfloat16",
	"transformers_version": "4.39.2",
	"tune_mm_mlp_adapter": false,
	"tune_mm_vision_resampler": false,
	"tune_mm_vision_tower": true,
	"unfreeze_mm_vision_tower": true,
	"use_cache": true,
	"use_mm_proj": true,
	"vocab_size": 64000
	}