Instructions to use LiqunMa/FBI-LLM_7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LiqunMa/FBI-LLM_7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="LiqunMa/FBI-LLM_7B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("LiqunMa/FBI-LLM_7B") model = AutoModelForCausalLM.from_pretrained("LiqunMa/FBI-LLM_7B") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use LiqunMa/FBI-LLM_7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "LiqunMa/FBI-LLM_7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LiqunMa/FBI-LLM_7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/LiqunMa/FBI-LLM_7B
- SGLang
How to use LiqunMa/FBI-LLM_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 "LiqunMa/FBI-LLM_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": "LiqunMa/FBI-LLM_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 "LiqunMa/FBI-LLM_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": "LiqunMa/FBI-LLM_7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use LiqunMa/FBI-LLM_7B with Docker Model Runner:
docker model run hf.co/LiqunMa/FBI-LLM_7B
HIP out of memory
I have cloned the github page , and 7B huggingface repository and tried to load model.
Shouldn't it have smaller memory footprint since its a binary model ?
I am on 7600 XT ROCM on archlinux (text generation webui and comfyui and all custom models I tried has worked so far on this setup)
OutOfMemoryError: HIP out of memory. Tried to allocate 64.00 MiB. GPU 0 has a total capacity of 15.98 GiB of which 40.00 MiB is free. Of the allocated memory 15.75 GiB is allocated by PyTorch, and 1.37 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_HIP_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
What can I do about this ?