Instructions to use openkg/ailawyer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openkg/ailawyer with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="openkg/ailawyer")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("openkg/ailawyer") model = AutoModelForCausalLM.from_pretrained("openkg/ailawyer", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use openkg/ailawyer with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "openkg/ailawyer" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "openkg/ailawyer", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/openkg/ailawyer
- SGLang
How to use openkg/ailawyer 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 "openkg/ailawyer" \ --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": "openkg/ailawyer", "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 "openkg/ailawyer" \ --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": "openkg/ailawyer", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use openkg/ailawyer with Docker Model Runner:
docker model run hf.co/openkg/ailawyer
Download adapter_config.json from openkg/ailawyer: direct link, hf CLI and curl.
- Browser
- Download file 401 Bytes
-
https://huggingface.co/openkg/ailawyer/resolve/main/adapter_config.json
- Command line
-
hf download hf://openkg/ailawyer/adapter_config.json
-
curl -L -o adapter_config.json https://huggingface.co/openkg/ailawyer/resolve/main/adapter_config.json
401 Bytes
| { | |
| "base_model_name_or_path": "/data1/bisheng/.hfcache/hub/llama-alpaca-chinese-expend-13B/", | |
| "bias": "none", | |
| "enable_lora": null, | |
| "fan_in_fan_out": false, | |
| "inference_mode": true, | |
| "lora_alpha": 16, | |
| "lora_dropout": 0.05, | |
| "merge_weights": false, | |
| "modules_to_save": null, | |
| "peft_type": "LORA", | |
| "r": 8, | |
| "target_modules": [ | |
| "q_proj", | |
| "v_proj" | |
| ], | |
| "task_type": "CAUSAL_LM" | |
| } |