metadata

base_model: unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - qwen2
  - trl
license: apache-2.0
language:
  - en
datasets:
  - Vezora/Tested-143k-Python-Alpaca
  - iamtarun/python_code_instructions_18k_alpaca
  - jtatman/python-code-dataset-500k
  - flytech/python-codes-25k
  - fxmeng/CodeFeedback-Python105K

A finetuned model trained on 5 datasets with a total of 876000 rows. This model was an experiment, as I wanted to train a model with a lot of python code and see the results.

Uploaded model

Developed by: Vo1dAbyss
License: apache-2.0
Finetuned from model : unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.