metadata
base_model: RP3-AI/RP3-1b-1.1
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
license: apache-2.0
language:
- en
datasets:
- yahma/alpaca-cleaned
- HuggingFaceH4/ultrachat_200k
- openai/gsm8k
Uploaded model
- Developed by: RP3-AI
- License: apache-2.0
- Finetuned from model : RP3-AI/RP3-1b-1.1
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.