Instructions to use aixk/fastplus-44m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use aixk/fastplus-44m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="aixk/fastplus-44m")# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("aixk/fastplus-44m", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use aixk/fastplus-44m with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "aixk/fastplus-44m" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "aixk/fastplus-44m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/aixk/fastplus-44m
- SGLang
How to use aixk/fastplus-44m 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 "aixk/fastplus-44m" \ --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": "aixk/fastplus-44m", "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 "aixk/fastplus-44m" \ --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": "aixk/fastplus-44m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use aixk/fastplus-44m with Docker Model Runner:
docker model run hf.co/aixk/fastplus-44m
Commit History
-
Create README.md
Verified signature7e9c814 -
Upload model_fastplus_40m_4bit.vlite with huggingface_hub
Verified signatureb49faed -
Upload model_fastplus_40m.vlite with huggingface_hub
Verified signaturea97ccbe -
FastPlus-40M Relativistic SVO Dynamic-Soft-Pooling Model Train Completed Safely
Verified signature8df2e5e -
System: Prune old checkpoint folder checkpoint-400 to save space
22ddab6 -
FastPlus40m Backup checkpoint-726 at global step 726
0a45af4 -
Upload folder using huggingface_hub
cd114f4 -
Upload folder using huggingface_hub
bccea45 -
System: Prune old checkpoint folder checkpoint-242 to save space
fbecb6e -
FastPlus40m Backup checkpoint-600 at global step 600
7a90a0a -
Upload folder using huggingface_hub
151b76b -
System: Prune old checkpoint folder checkpoint-200 to save space
338d4b7 -
FastPlus40m Backup checkpoint-400 at global step 400
1d21e40 -
Upload folder using huggingface_hub
f776a41 -
Upload model_fastplus_40m_4bit.vlite with huggingface_hub
354f6ef -
Upload model_fastplus_40m.vlite with huggingface_hub
9225ab6 -
FastPlus-40M Relativistic SVO Dynamic-Soft-Pooling Model Train Completed Safely
9908da9 -
FastPlus40m Backup checkpoint-242 at global step 242
eccd1ee -
FastPlus40m Backup checkpoint-200 at global step 200
33d902a -
Upload folder using huggingface_hub
31807dc -
initial commit
09d0fc1