bha6kar/finance-lora-smollm2-1.7b
LoRA adapter fine-tuning mlx-community/SmolLM2-1.7B-Instruct on the gbharti/finance-alpaca financial instruction dataset with MLX.
- Test perplexity: 5.821 (base) to 5.072 (tuned), across 3 seed(s).
Use
from mlx_lm import load, generate
model, tok = load("mlx-community/SmolLM2-1.7B-Instruct", 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-smollm2-1.7b
Base model
HuggingFaceTB/SmolLM2-1.7B Quantized
HuggingFaceTB/SmolLM2-1.7B-Instruct Finetuned
mlx-community/SmolLM2-1.7B-Instruct