Text Generation
MLX
English
structured-generation
parallel-decoding
constrained-decoding
apple-silicon
classification
json
Instructions to use botp/Qwen-2.5-1B-RLCD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use botp/Qwen-2.5-1B-RLCD with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("botp/Qwen-2.5-1B-RLCD") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use botp/Qwen-2.5-1B-RLCD with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "botp/Qwen-2.5-1B-RLCD" --prompt "Once upon a time"
- Atomic Chat
Download server/main.py from botp/Qwen-2.5-1B-RLCD: direct link, hf CLI and curl.
- Browser
- Download file 530 Bytes
-
https://huggingface.co/botp/Qwen-2.5-1B-RLCD/resolve/main/server/main.py
- Command line
-
hf download hf://botp/Qwen-2.5-1B-RLCD/server/main.py
-
curl -L -o main.py https://huggingface.co/botp/Qwen-2.5-1B-RLCD/resolve/main/server/main.py
530 Bytes
| """ | |
| Entry point to run the FastAPI server persistently. | |
| """ | |
| import sys | |
| import os | |
| import uvicorn | |
| # Ensure project root is in PYTHONPATH | |
| sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) | |
| if __name__ == "__main__": | |
| host = os.environ.get("HOST", "0.0.0.0" if "SPACE_ID" in os.environ else "127.0.0.1") | |
| port = int(os.environ.get("PORT", 7860 if "SPACE_ID" in os.environ else 8000)) | |
| uvicorn.run( | |
| "server.app:app", | |
| host=host, | |
| port=port, | |
| log_level="info" | |
| ) | |