Instructions to use TheBloke/llava-v1.5-13B-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/llava-v1.5-13B-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/llava-v1.5-13B-GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/llava-v1.5-13B-GPTQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/llava-v1.5-13B-GPTQ")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TheBloke/llava-v1.5-13B-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/llava-v1.5-13B-GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/llava-v1.5-13B-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/llava-v1.5-13B-GPTQ

SGLang

How to use TheBloke/llava-v1.5-13B-GPTQ 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 "TheBloke/llava-v1.5-13B-GPTQ" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/llava-v1.5-13B-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "TheBloke/llava-v1.5-13B-GPTQ" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/llava-v1.5-13B-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/llava-v1.5-13B-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/llava-v1.5-13B-GPTQ
```

No GGUF Quatization?

by Goldenblood56 - opened Oct 25, 2023

Discussion

Goldenblood56

Oct 25, 2023

Is there a reason this does not get a GGUF quantization? Thanks for providing it in GPTQ I don't want to sound ungrateful. Thanks for the hard work TheBloke.

dackdel

Oct 26, 2023

What does it take to GGUF export it

TheBloke

Owner Oct 26, 2023

I didn't make GGUFs because I don't believe it's possible to use Llava with GGUF at this time. To get the image processing aspects, requires other components which are not supported in GGUF yet.

Izard

Oct 26, 2023

Actually llama.cpp/llava works with llava.gguf

zhicwu

Oct 27, 2023

LLaVA 1.5

BakLLaVA 1 - https://huggingface.co/mys/ggml_bakllava-1

Handgun1773

Nov 6, 2023

Obsidian-3B-V0.5 - https://huggingface.co/nisten/obsidian-3b-multimodal-q6-gguf
Needs a llama.cpp fork tho (because StableLM-3B-4e1t base), instructions in model card.

dyoung

Jan 16, 2024

Found this: https://huggingface.co/jartine/llava-v1.5-7B-GGUF
It's related to a llamafile project from Mozilla:

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment