metadata
base_model: unsloth/deepseek-r1-distill-llama-8b-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
license: apache-2.0
language:
- en
Uploaded model
This model is a fine-tuned version of unsloth/deepseek-r1-distill-llama-8b-unsloth-bnb-4bit, trained using synthetic data generated with a Descartes-inspired approach. It focuses on logical reasoning and abstract thinking.
this model is based on a synthetically generated dataset: descartes-philosophical-cot.
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
