---
base_model:
- unsloth/SmolLM2-1.7B-Instruct-bnb-4bit
- HuggingFaceTB/SmolLM2-1.7B-Instruct
tags:
- text-generation-inference
- transformers
- unsloth
- trl
- sft
license: apache-2.0
language:
- en
datasets:
- AI-MO/NuminaMath-TIR
---

# Uploaded  model

- **Developed by:** Qurtana
- **License:** apache-2.0
- **Finetuned from model :** unsloth/SmolLM2-1.7B-Instruct-bnb-4bit

This model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.

Trained using rank-stablized QLoRA with r = 64 and alpha = 5 for one epoch using the "ChatML" data prep.

The following heads were targeted: "q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj", "embed_tokens", and "lm_head".

I strongly believe that this should achieve better performance than the original, particularly in math and reasoning. Hopefully the MUSR and MATH Lvl 5 evaluations reflect this.

[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)