Text Generation
MLX
English
structured-generation
parallel-decoding
constrained-decoding
apple-silicon
classification
json
Instructions to use harshatheg/Qwen-2.5-1B-RLCD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use harshatheg/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("harshatheg/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 harshatheg/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 "harshatheg/Qwen-2.5-1B-RLCD" --prompt "Once upon a time"
- Atomic Chat
Download run.sh from harshatheg/Qwen-2.5-1B-RLCD: direct link, hf CLI and curl.
- Browser
- Download file 462 Bytes
-
https://huggingface.co/harshatheg/Qwen-2.5-1B-RLCD/resolve/main/run.sh
- Command line
-
hf download hf://harshatheg/Qwen-2.5-1B-RLCD/run.sh
-
curl -L -o run.sh https://huggingface.co/harshatheg/Qwen-2.5-1B-RLCD/resolve/main/run.sh
462 Bytes
| set -e | |
| DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )" | |
| cd "$DIR" | |
| echo "=================================================================" | |
| echo " Starting Parallel Constrained Decision Engine (Local Apple Silicon)" | |
| echo " URL: http://localhost:8000" | |
| echo "=================================================================" | |
| export PYTHONPATH="$DIR:$PYTHONPATH" | |
| python3 -m uvicorn server.app:app --host 0.0.0.0 --port 8000 --reload | |