| Quantization made by Richard Erkhov. | |
| [Github](https://github.com/RichardErkhov) | |
| [Discord](https://discord.gg/pvy7H8DZMG) | |
| [Request more models](https://github.com/RichardErkhov/quant_request) | |
| OPT-1.3B-SFT-DSChatLoRA - AWQ | |
| - Model creator: https://huggingface.co/kaitchup/ | |
| - Original model: https://huggingface.co/kaitchup/OPT-1.3B-SFT-DSChatLoRA/ | |
| Original model description: | |
| --- | |
| license: cc-by-nc-sa-4.0 | |
| datasets: | |
| - Dahoas/rm-static | |
| - Dahoas/synthetic-instruct-gptj-pairwise | |
| - Anthropic/hh-rlhf | |
| language: | |
| - en | |
| --- | |
| # Model Card for Model ID | |
| This a model is a fine-tuned with SFT using DeepSpeed Chat. | |
| It is based on OPT-1.3M.B | |
| ## Model Details | |
| ### Model Description | |
| - **Developed by:** [The Kaitchup](https://kaitchup.substack.com/) | |
| - **Model type:** Causal | |
| - **Language(s) (NLP):** English | |
| - **License:** cc-by-nc-sa-4.0 | |
| - **Finetuned from model:** [facebook/opt-1.3b](https://huggingface.co/facebook/opt-1.3b) | |
| ### Model Sources | |
| The model has been trained with the procedure described in this article: | |
| [Train Instruct LLMs On Your GPU with DeepSpeed Chat — Step #1: Supervised Fine-tuning](https://kaitchup.substack.com/p/train-instruct-llms-on-your-gpu-with) | |