Reason_Qwen / README.md
paradox44's picture
Update README.md
134c2f5 verified
|
raw
history blame
496 Bytes
metadata
metadata:
  license: mit
tags:
  - unsloth
  - text-generation
  - transformers
  - conversational
  - text-generation-inference
  - Inference Endpoints
datasets:
  - teknium/OpenHermes-2.5
  - KingNish/reasoning-base-20k
  - reasoning-machines/gsm-hard
  - ProlificAI/social-reasoning-rlhf
  - arcee-ai/reasoning-sharegpt
base_model:
  - unsloth/Qwen2.5-7B-Instruct

Your Model Name

Reason_Qwen

Model Description

Model is finetuned version of unsloth/Qwen2.5-7B-Instruct. It is finetuned to reason better.