Model Card for Model ID
This is a LoRA adapter for Mistral-Instruct-v0.2
Base Model: Mistral-Instruct-v0.2 Dataset: TokenBender/code_instructions_122k_alpaca_style
Test run, trained on subsample of 5k examples for 1 epoch using QLoRa technique.
Final loss: 0.394200
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("sadaisystems/mistral-inst-v0.2-code40k", dtype="auto")