MLX models
Collection
Quantized (4bits) qlora fine-tuned model based on Llama3 Instruct. MLX (Apple Silicon) compatible. • 3 items • Updated
Fine-tuned model for RetrieverApp to predict data_type and organism for GEO entries.
Based on Llama3.2 3B-IT. Converted to mlx (for Apple Silicon) format. Quantized (4bits).
- Downloads last month
- -
Model size
0.5B params
Tensor type
BF16
·
U32 ·
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for biomisc/mlx_retrieverapp_orig_3B
Base model
meta-llama/Llama-3.2-3B-Instruct