Instructions to use liuhaotian/llava-336px-pretrain-vicuna-7b-v1.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use liuhaotian/llava-336px-pretrain-vicuna-7b-v1.3 with Transformers:

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

pipe = pipeline("text-generation", model="liuhaotian/llava-336px-pretrain-vicuna-7b-v1.3")

# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("liuhaotian/llava-336px-pretrain-vicuna-7b-v1.3")
model = AutoModelForCausalLM.from_pretrained("liuhaotian/llava-336px-pretrain-vicuna-7b-v1.3", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use liuhaotian/llava-336px-pretrain-vicuna-7b-v1.3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "liuhaotian/llava-336px-pretrain-vicuna-7b-v1.3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "liuhaotian/llava-336px-pretrain-vicuna-7b-v1.3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/liuhaotian/llava-336px-pretrain-vicuna-7b-v1.3

SGLang

How to use liuhaotian/llava-336px-pretrain-vicuna-7b-v1.3 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 "liuhaotian/llava-336px-pretrain-vicuna-7b-v1.3" \
    --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": "liuhaotian/llava-336px-pretrain-vicuna-7b-v1.3",
		"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 "liuhaotian/llava-336px-pretrain-vicuna-7b-v1.3" \
        --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": "liuhaotian/llava-336px-pretrain-vicuna-7b-v1.3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use liuhaotian/llava-336px-pretrain-vicuna-7b-v1.3 with Docker Model Runner:
```
docker model run hf.co/liuhaotian/llava-336px-pretrain-vicuna-7b-v1.3
```

Error loading model

by kopsahlong - opened Dec 27, 2023

Discussion

kopsahlong

Dec 27, 2023

Hi there! I'm trying to download this model using the code provided by "Use in Transformers".

from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("liuhaotian/llava-336px-pretrain-vicuna-13b-v1.3")
model = AutoModelForCausalLM.from_pretrained("liuhaotian/llava-336px-pretrain-vicuna-13b-v1.3")

I'm currently getting an error when I run this code:

OSError: liuhaotian/llava-336px-pretrain-vicuna-13b-v1.3 does not appear to have a file named preprocessor_config.json. Checkout 'https://huggingface.co/liuhaotian/llava-336px-pretrain-vicuna-13b-v1.3/main' for available files.

When I just run this line model = AutoModelForCausalLM.from_pretrained("liuhaotian/llava-336px-pretrain-vicuna-13b-v1.3"), I get this error:

ValueError: Unrecognized configuration class <class 'transformers.models.llava.configuration_llava.LlavaConfig'> for this kind of AutoModel: AutoModelForCausalLM.
Model type should be one of BartConfig, BertConfig, BertGenerationConfig, BigBirdConfig, BigBirdPegasusConfig, BioGptConfig, BlenderbotConfig, BlenderbotSmallConfig, BloomConfig, CamembertConfig, LlamaConfig, CodeGenConfig, CpmAntConfig, CTRLConfig, Data2VecTextConfig, ElectraConfig, ErnieConfig, FalconConfig, FuyuConfig, GitConfig, GPT2Config, GPT2Config, GPTBigCodeConfig, GPTNeoConfig, GPTNeoXConfig, GPTNeoXJapaneseConfig, GPTJConfig, LlamaConfig, MarianConfig, MBartConfig, MegaConfig, MegatronBertConfig, MistralConfig, MixtralConfig, MptConfig, MusicgenConfig, MvpConfig, OpenLlamaConfig, OpenAIGPTConfig, OPTConfig, PegasusConfig, PersimmonConfig, PhiConfig, PLBartConfig, ProphetNetConfig, QDQBertConfig, ReformerConfig, RemBertConfig, RobertaConfig, RobertaPreLayerNormConfig, RoCBertConfig, RoFormerConfig, RwkvConfig, Speech2Text2Config, TransfoXLConfig, TrOCRConfig, WhisperConfig, XGLMConfig, XLMConfig, XLMProphetNetConfig, XLMRobertaConfig, XLMRobertaXLConfig, XLNetConfig, XmodConfig.

I'm using transformers version 4.36.2.

Any thoughts on what might be going wrong here and how to fix it?

Thanks in advance for the help!

kopsahlong

Dec 27, 2023

Update that I tried updating my transformers version to the following commit: pip install git+https://github.com/huggingface/transformers.git@cae78c46, but am now getting the following error:

  File "/home/kopsahlong/miniconda3/envs/test2/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 926, in from_pretrained
    config_class = CONFIG_MAPPING[config_dict["model_type"]]
  File "/home/kopsahlong/miniconda3/envs/test2/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 632, in __getitem__
    raise KeyError(key)
KeyError: 'llava'

liuhaotian

Owner Dec 28, 2023

this is just a pretrained projector and is not the full model.

if you want to use the latest transformers to directly load the model, please use : https://huggingface.co/llava-hf/llava-1.5-7b-hf or https://huggingface.co/llava-hf/llava-1.5-13b-hf

otherwise, use our code base and https://huggingface.co/collections/liuhaotian/llava-15-653aac15d994e992e2677a7e

thanks.

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