bha6kar/finance-lora-deepseek-r1-8b
LoRA adapter fine-tuning mlx-community/DeepSeek-R1-Distill-Llama-8B-4bit on the gbharti/finance-alpaca financial instruction dataset with MLX.
- Test perplexity: 11.148 (base) to 7.464 (tuned), across 3 seed(s).
Use
from mlx_lm import load, generate
model, tok = load("mlx-community/DeepSeek-R1-Distill-Llama-8B-4bit", adapter_path="<downloaded-adapter-dir>")
Produced by slm-training.
Hardware compatibility
Log In to add your hardware
Quantized
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for bha6kar/finance-lora-deepseek-r1-8b
Base model
deepseek-ai/DeepSeek-R1-Distill-Llama-8B