4-bit Open on Hugging Face
Parameters
2.8B
Weights (est.)
≈ 1.8 GB
Mac memory (est.)
8 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/zephyr-7b-gemma-v0.1-4bit --prompt "Hello"
Details
- Base model
- HuggingFaceH4/zephyr-7b-gemma-sft-v0.1 (finetune)
- Vendor
- HuggingFaceH4
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- gemma-terms-of-use
- Downloads
- 56 in the last 30 days · 646 all time · 0 likes
- Published
- 2024-03-02 · updated 2024-03-02 (2y ago)
- Tags
- gemma, alignment-handbook, generated_from_trainer, model-index