Text Generation
MLX
Safetensors
English
base-model
pretrained
small-language-model
apple-silicon
from-scratch
research
Instructions to use wzebrowski/OpenSML-Base-175M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use wzebrowski/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("wzebrowski/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 wzebrowski/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 "wzebrowski/OpenSML-Base-175M" --prompt "Once upon a time"
- Atomic Chat
Download config.json from wzebrowski/OpenSML-Base-175M: direct link, hf CLI and curl.
- Browser
- Download file 753 Bytes
-
https://huggingface.co/wzebrowski/OpenSML-Base-175M/resolve/main/config.json
- Command line
-
hf download hf://wzebrowski/OpenSML-Base-175M/config.json
-
curl -L -o config.json https://huggingface.co/wzebrowski/OpenSML-Base-175M/resolve/main/config.json
753 Bytes
| { | |
| "model_name": "OpenSML-Base-175M", | |
| "parameters": 175611648, | |
| "model": { | |
| "attention_impl": "fast", | |
| "bias": false, | |
| "ce_impl": "metal", | |
| "d_model": 768, | |
| "ffn_impl": "packed-metal", | |
| "loss_dtype": "float32", | |
| "max_seq_len": 2048, | |
| "mlp_multiple_of": 256, | |
| "mlp_ratio": 4.0, | |
| "n_heads": 12, | |
| "n_kv_heads": 4, | |
| "n_layers": 24, | |
| "qk_norm": true, | |
| "vocab_size": 32000, | |
| "rope_base": 10000.0 | |
| }, | |
| "weight_sha256": "5151567e266244c9e32fd6e01775192633abe227320269ecdefe28ce43e9ccc3", | |
| "weight_format": "BF16 safetensors", | |
| "context_limit": 2048, | |
| "serialization": "raw document-prefix completion", | |
| "supported_runtime": "native MLX on Apple Silicon; not a Transformers or mlx-lm auto-loading export" | |
| } | |