Instructions to use gordonhu/MQT-LLaVA-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use gordonhu/MQT-LLaVA-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="gordonhu/MQT-LLaVA-7b")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("gordonhu/MQT-LLaVA-7b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use gordonhu/MQT-LLaVA-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "gordonhu/MQT-LLaVA-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "gordonhu/MQT-LLaVA-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/gordonhu/MQT-LLaVA-7b
- SGLang
How to use gordonhu/MQT-LLaVA-7b 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 "gordonhu/MQT-LLaVA-7b" \ --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": "gordonhu/MQT-LLaVA-7b", "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 "gordonhu/MQT-LLaVA-7b" \ --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": "gordonhu/MQT-LLaVA-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use gordonhu/MQT-LLaVA-7b with Docker Model Runner:
docker model run hf.co/gordonhu/MQT-LLaVA-7b
Commit ·
089bfb3
1
Parent(s): ba24912
init
Browse files
README.md
CHANGED
|
@@ -15,7 +15,7 @@ MQT-LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-g
|
|
| 15 |
It is an auto-regressive language model, based on the transformer architecture.
|
| 16 |
|
| 17 |
**Model date:**
|
| 18 |
-
MQT-LLaVA-7B was trained in May 2024. [Paper](https://arxiv.org/abs/)
|
| 19 |
|
| 20 |
<!-- **Paper or resources for more information:**
|
| 21 |
https:// -->
|
|
|
|
| 15 |
It is an auto-regressive language model, based on the transformer architecture.
|
| 16 |
|
| 17 |
**Model date:**
|
| 18 |
+
MQT-LLaVA-7B was trained in May 2024. [Paper](https://arxiv.org/abs/2405.19315)
|
| 19 |
|
| 20 |
<!-- **Paper or resources for more information:**
|
| 21 |
https:// -->
|