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 config.json from OpenSML/OpenSML-150M: direct link, hf CLI and curl.
- Browser
- Download file 616 Bytes
-
https://huggingface.co/OpenSML/OpenSML-150M/resolve/main/config.json
- Command line
-
hf download hf://OpenSML/OpenSML-150M/config.json
-
curl -L -o config.json https://huggingface.co/OpenSML/OpenSML-150M/resolve/main/config.json
616 Bytes
| { | |
| "model_name": "OpenSML-150M", | |
| "format": "opensml-native-mlx-v1", | |
| "model": { | |
| "attention_impl": "vanilla", | |
| "bias": false, | |
| "ce_impl": "reference", | |
| "d_model": 768, | |
| "ffn_impl": "reference", | |
| "loss_dtype": "float32", | |
| "max_seq_len": 2048, | |
| "mlp_multiple_of": 256, | |
| "mlp_ratio": 4.0, | |
| "n_heads": 12, | |
| "n_kv_heads": 4, | |
| "n_layers": 20, | |
| "qk_norm": true, | |
| "vocab_size": 32000 | |
| }, | |
| "training_format": "plain-user-assistant-eos-v1", | |
| "dtype": "float32", | |
| "context_length": 2048, | |
| "weights_sha256": "cbd3e3fb4ada74d7264371b79cee7598f513b7b950f1f141ef9f1a43bd2e1b4e" | |
| } | |