Text Generation
MLX
Safetensors
English
pretraining
from-scratch
small-language-model
post-training
silicon
Instructions to use OpenSML/OpenSML-150M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use OpenSML/OpenSML-150M 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("OpenSML/OpenSML-150M") 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 OpenSML/OpenSML-150M with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "OpenSML/OpenSML-150M" --prompt "Once upon a time"
- Atomic Chat
Download CLEAN_DOWNLOAD_VERIFICATION.json from OpenSML/OpenSML-150M: direct link, hf CLI and curl.
- Browser
- Download file 790 Bytes
-
https://huggingface.co/OpenSML/OpenSML-150M/resolve/main/CLEAN_DOWNLOAD_VERIFICATION.json
- Command line
-
hf download hf://OpenSML/OpenSML-150M/CLEAN_DOWNLOAD_VERIFICATION.json
-
curl -L -o CLEAN_DOWNLOAD_VERIFICATION.json https://huggingface.co/OpenSML/OpenSML-150M/resolve/main/CLEAN_DOWNLOAD_VERIFICATION.json
790 Bytes
| { | |
| "repository": "wzebrowski/OpenSML-150M", | |
| "revision": "27ba9cd101492c0dbfeb6cea0147e429a86d8648", | |
| "download": "Fresh force-download of 17 release files with no authentication", | |
| "hashes": "All SHA256SUMS entries verified", | |
| "working_directory": "/private/tmp (outside original project)", | |
| "environment": "Separate temporary virtual environment; published requirements installed from PyPI", | |
| "mlx": "0.32.2", | |
| "mlx-metal": "0.32.2", | |
| "tokenizers": "0.22.2", | |
| "generation": { | |
| "text": " I am a student.", | |
| "token_ids": [ | |
| 345, | |
| 768, | |
| 261, | |
| 2560, | |
| 17, | |
| 1 | |
| ], | |
| "stop_reason": "eos", | |
| "prompt_tokens": 13, | |
| "generated_tokens": 6 | |
| }, | |
| "scope": "Strict loading and short inference test; no benchmark rerun or broad quality claim." | |
| } | |