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
Commit History
2 days ago
-
Document JSONLite descendant training and main-checkpoint results
Verified signatureDocumentation only; original base model weights, tokenizer and inference runtime remain unchanged.1815fb1
6 days ago
-
Update JSONLite descendant training and current evaluation metrics
Verified signature7844703
7 days ago
-
Document main JSONLite continuation and matched evaluation
Verified signatureDocumentation-only update. Base weights, tokenizer, native runner and source bundle are unchanged.1cfc9ba
8 days ago
-
Document native JSON SFT descendant and updated evaluation results
Verified signatureDocument the new native JSON fine-tune, its source-schema-target data, lineage and measured results. The Base-175M repository continues to contain the original pretrained weights and completion runtime.661bae5 -
Add base model card, tokenizer, native runner and pretraining records
Verified signatureed99a2e