Instructions to use openbmb/RLHF-V with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openbmb/RLHF-V with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="openbmb/RLHF-V")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("openbmb/RLHF-V", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use openbmb/RLHF-V with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "openbmb/RLHF-V" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "openbmb/RLHF-V", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/openbmb/RLHF-V
- SGLang
How to use openbmb/RLHF-V 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 "openbmb/RLHF-V" \ --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": "openbmb/RLHF-V", "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 "openbmb/RLHF-V" \ --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": "openbmb/RLHF-V", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use openbmb/RLHF-V with Docker Model Runner:
docker model run hf.co/openbmb/RLHF-V
Error when loading this model
#5
by psp-dada - opened
With the latest transformers version transformers==4.46.2, when I try to load this model by using:
model_name = "openbmb/RLHF-V"
model = AutoModelForCausalLM.from_pretrained(
model_name,
cache_dir=self.model_dir,
torch_dtype=self.torch_dtype,
low_cpu_mem_usage=True,
device_map=self.device,
attn_implementation="flash_attention_2" if "cuda" in str(self.device) else None,
).eval()
An error occured:
ValueError: The checkpoint you are trying to load has model type `beit3_llava` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.
psp-dada changed discussion title from Error when load this model to Error when loading this model
psp-dada changed discussion status to closed