t1-7b-qwen-64k-128r-t-9-orpo-8000 / README.md

patrickrho

Trained with Unsloth

680bd9f verified 5 months ago

preview code

raw

history blame contribute delete

574 Bytes

metadata

base_model: t1-7b-qwen-32k-64r-t-9
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - qwen2
  - trl
  - orpo
license: apache-2.0
language:
  - en

Uploaded model

Developed by: patrickrho
License: apache-2.0
Finetuned from model : t1-7b-qwen-32k-64r-t-9

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