Downloads · 30 days
0
DS-Archive/llama-2-supercot-lora
llama-2-supercot-lora is a text generation model from DS-Archive. Use it when you need the model to write or continue text. The card lists the license as mit.
Standard 8bit lora trained using axolotl on the supercot dataset using Alpaca instruct format at 4096 context:
Downloads · 30 days
0
Access
Public
Updated Sep 27, 2023
Repo size
1.5 GB
Likes
0
Public
Click a slice to open those files.
.bin1.5 GB · 100%
From the Hugging Face model README
Standard 8bit lora trained using axolotl on the supercot dataset using Alpaca instruct format at 4096 context:
Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instruction:
<instruction>
### Input:
<any additional context. Remove this if it's not neccesary>
### Response:
<make sure to leave a single new-line here for optimal results>
The model will show biases similar to those exhibited by the base model. It is not intended for supplying factual information or advice in any form.