Instructions to use FreedomIntelligence/LongLLaVA-53B-A13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FreedomIntelligence/LongLLaVA-53B-A13B with Transformers:

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

pipe = pipeline("image-text-to-text", model="FreedomIntelligence/LongLLaVA-53B-A13B", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("FreedomIntelligence/LongLLaVA-53B-A13B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FreedomIntelligence/LongLLaVA-53B-A13B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FreedomIntelligence/LongLLaVA-53B-A13B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FreedomIntelligence/LongLLaVA-53B-A13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FreedomIntelligence/LongLLaVA-53B-A13B

SGLang

How to use FreedomIntelligence/LongLLaVA-53B-A13B 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 "FreedomIntelligence/LongLLaVA-53B-A13B" \
    --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": "FreedomIntelligence/LongLLaVA-53B-A13B",
		"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 "FreedomIntelligence/LongLLaVA-53B-A13B" \
        --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": "FreedomIntelligence/LongLLaVA-53B-A13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FreedomIntelligence/LongLLaVA-53B-A13B with Docker Model Runner:
```
docker model run hf.co/FreedomIntelligence/LongLLaVA-53B-A13B
```

Failed to load the model

by amanpatkar - opened Sep 10, 2024

Discussion

amanpatkar

Sep 10, 2024

Hi There,
I have tried to load the model using the below code. But I believe there must be another file by the name of "configuration_jamba.py".
Due to this, I am getting the following error.
[os Error] Could not locate the configuration_jamba.py inside FreedomIntelligence/LongLLaVA.

code to load the model -
model_id = "FreedomIntelligence/LongLLaVA"
tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=True, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype=torch.bfloat16, trust_remote_code=True)
model.generation_config = GenerationConfig.from_pretrained(model_id)

Xidong

FreedomAI org Sep 10, 2024

Hi there, sorry for the confusion, the configuration file is in https://github.com/FreedomIntelligence/LongLLaVA/tree/main/llava/model/language_model/Jamba.
We are still preparing the code and will release it soon.

amanpatkar

Sep 11, 2024

Hi,
Thanks for your quick reply. I want to load the model using transformer library. Can you make it work on that? That will be very helpful.

Xidong

FreedomAI org Sep 18, 2024

We have updated the code, please try again, we are looking forward for your feedback.

awx1

Nov 25, 2024

Only for the 9B has the configuration_jamba.py been updated. When will the configuration_jamba.py be released for the 53B model?

Xidong

FreedomAI org Nov 28, 2024

We have updated it, thank you for your reminder. We apologize for not including these two files directly in the model repo. In fact, the relevant files are in the code repo (https://github.com/FreedomIntelligence/LongLLaVA/tree/main/llava/model/language_model/Jamba). We are very sorry.

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