Text Generation
MLX
Safetensors
English
base-model
pretrained
small-language-model
apple-silicon
from-scratch
research
Instructions to use OpenSML/OpenSML-Base-175M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use OpenSML/OpenSML-Base-175M 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-Base-175M") 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-Base-175M 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-Base-175M" --prompt "Once upon a time"
- Atomic Chat
Download checkpoint_provenance.json from OpenSML/OpenSML-Base-175M: direct link, hf CLI and curl.
- Browser
- Download file 759 Bytes
-
https://huggingface.co/OpenSML/OpenSML-Base-175M/resolve/main/checkpoint_provenance.json
- Command line
-
hf download hf://OpenSML/OpenSML-Base-175M/checkpoint_provenance.json
-
curl -L -o checkpoint_provenance.json https://huggingface.co/OpenSML/OpenSML-Base-175M/resolve/main/checkpoint_provenance.json
759 Bytes
| { | |
| "model": "OpenSML-Base-175M", | |
| "stage": "Stage A pretraining continuation", | |
| "step": 132005, | |
| "tokens": 17300111360, | |
| "model_file": "model.safetensors", | |
| "weight_bytes": 351242342, | |
| "weight_sha256": "5151567e266244c9e32fd6e01775192633abe227320269ecdefe28ce43e9ccc3", | |
| "original_checkpoint_metadata_sha256": "15a0e3b511b97503a611c0da838a7fde1c06ebed34c7103f7cda1782cc6378a4", | |
| "tokenizer_fingerprint": "1194292c6d906ac19e6f01c6ad2b42825143fad426a22aa8856d903776701ecb", | |
| "initialization": "normal-0.02-residual-scaled-v1", | |
| "post_training": false, | |
| "descendant": "OpenSML/OpenSML-JSONLite-175M", | |
| "model_weight_license": "not yet assigned", | |
| "scope": "The pretrained ancestor; no QA/extraction SFT or JSON adapter is part of these weights." | |
| } | |