metadata

base_model:
  - ShubhamSinghCodes/PyNanoLM-big
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl
  - sft
  - python
license: apache-2.0
language:
  - en
datasets:
  - AI-MO/NuminaMath-CoT
  - TIGER-Lab/MathInstruct
  - Vezora/Tested-143k-Python-Alpaca
  - glaiveai/glaive-code-assistant-v2
pipeline_tag: text-generation

Uploaded model

Developed by: ShubhamSinghCodes
License: apache-2.0
Distilled from model : ShubhamSinghCodes/PyNanoLM-big

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library. A fast, lite, not entirely stupid model that assists in Python programming. It is a very small, 3.5M parameter model finetuned and distilled from SmolLM. (WIP)