Instructions to use shi-labs/vpt_OLA-VLM-CLIP-ConvNeXT-Llama3-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shi-labs/vpt_OLA-VLM-CLIP-ConvNeXT-Llama3-8b with Transformers:

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

pipe = pipeline("image-text-to-text", model="shi-labs/vpt_OLA-VLM-CLIP-ConvNeXT-Llama3-8b")
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)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("shi-labs/vpt_OLA-VLM-CLIP-ConvNeXT-Llama3-8b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use shi-labs/vpt_OLA-VLM-CLIP-ConvNeXT-Llama3-8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shi-labs/vpt_OLA-VLM-CLIP-ConvNeXT-Llama3-8b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shi-labs/vpt_OLA-VLM-CLIP-ConvNeXT-Llama3-8b",
		"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/shi-labs/vpt_OLA-VLM-CLIP-ConvNeXT-Llama3-8b

SGLang

How to use shi-labs/vpt_OLA-VLM-CLIP-ConvNeXT-Llama3-8b 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 "shi-labs/vpt_OLA-VLM-CLIP-ConvNeXT-Llama3-8b" \
    --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": "shi-labs/vpt_OLA-VLM-CLIP-ConvNeXT-Llama3-8b",
		"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 "shi-labs/vpt_OLA-VLM-CLIP-ConvNeXT-Llama3-8b" \
        --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": "shi-labs/vpt_OLA-VLM-CLIP-ConvNeXT-Llama3-8b",
		"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 shi-labs/vpt_OLA-VLM-CLIP-ConvNeXT-Llama3-8b with Docker Model Runner:
```
docker model run hf.co/shi-labs/vpt_OLA-VLM-CLIP-ConvNeXT-Llama3-8b
```

vpt_OLA-VLM-CLIP-ConvNeXT-Llama3-8b / config.json

praeclarumjj3

Upload LlavaLlamaForCausalLM

3af2662 verified over 1 year ago

Raw

History Blame Contribute Delete

3 kB

	{
	"_name_or_path": "/mnt/projects4jw/jiteshjain_sherlock/models/ABLATE/seed42/SUBMISSION/v_pt_d8-20_s10-18_g12-20_lossd0.5_s0.5_g0.5_textTrue_gen-depth-seg_CLIP-convnext_xxlarge-laion2B-s34B-b82K-augreg-soup-res768_llama3-8b_contw_0.3_lr2e-5_contrastiveTrue_ceFalse_oneformer_attn_causal_n8",
	"architectures": [
	"LlavaLlamaForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attn_mask_type": "causal",
	"aux_mode": "gen-depth-seg",
	"bos_token_id": 128000,
	"contrastive_loss_weight": 0.3,
	"depth_estimator": "/mnt/projects4jw/jiteshjain_sherlock/depth_anything_v2_vitl.pth",
	"eos_token_id": 128009,
	"freeze_mm_mlp_adapter": false,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"image_aspect_ratio": "pad",
	"image_depth": {
	"depth": 1,
	"depth_layer_indices": "8-20",
	"depth_loss_weight": 0.5,
	"dim_head": 32,
	"ff_mult": 1,
	"num_heads": 4,
	"num_tokens": 576,
	"output_dim": 1024,
	"use_intermediate_depth": false
	},
	"image_gen": {
	"depth": 1,
	"dim_head": 32,
	"ff_mult": 1,
	"img_layer_indices": "12-20",
	"img_loss_weight": 0.5,
	"num_heads": 4,
	"num_tokens": 1,
	"output_dim": 1024
	},
	"image_generator": "/mnt/projects4jw/jiteshjain_sherlock/stable-diffusion-2-1-unclip",
	"image_grid_pinpoints": [
	[
	336,
	672
	],
	[
	672,
	336
	],
	[
	672,
	672
	],
	[
	1008,
	336
	],
	[
	336,
	1008
	]
	],
	"image_seg": {
	"depth": 1,
	"dim_head": 32,
	"ff_mult": 1,
	"num_heads": 4,
	"num_tokens": 576,
	"output_dim": 1536,
	"seg_layer_indices": "10-18",
	"seg_loss_weight": 0.5,
	"seg_teacher": "oneformer"
	},
	"image_segmentor": "/mnt/projects4jw/jiteshjain_sherlock/oneformer_coco_swin_large",
	"initializer_range": 0.02,
	"intermediate_size": 14336,
	"max_position_embeddings": 8192,
	"mlp_bias": false,
	"mm_hidden_size": 3072,
	"mm_patch_merge_type": "flat",
	"mm_projector_lr": null,
	"mm_projector_type": "mlp2x_gelu",
	"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": "/mnt/projects4jw/jiteshjain_sherlock/CLIP-convnext_xxlarge-laion2B-s34B-b82K-augreg-soup-res768",
	"model_type": "llava_llama",
	"num_attention_heads": 32,
	"num_hidden_layers": 32,
	"num_key_value_heads": 8,
	"num_task_tokens": 8,
	"pass_text_to_aux": true,
	"pretraining_tp": 1,
	"rms_norm_eps": 1e-05,
	"rope_scaling": null,
	"rope_theta": 500000.0,
	"s2_scales": "336,1008",
	"sample_tokens": false,
	"task_token_format": "expand_emb",
	"tie_word_embeddings": false,
	"tokenizer_model_max_length": 4096,
	"tokenizer_padding_side": "right",
	"torch_dtype": "float32",
	"transformers_version": "4.41.1",
	"tune_mm_mlp_adapter": false,
	"use_cache": true,
	"use_ce": false,
	"use_contrastive": true,
	"use_mm_proj": true,
	"use_s2": false,
	"vocab_size": 128257
	}