|
--- |
|
license: cc-by-sa-4.0 |
|
datasets: |
|
- acrastt/EverythingLM-V3-ShareGPT |
|
language: |
|
- en |
|
library_name: transformers |
|
pipeline_tag: text-generation |
|
--- |
|
<a href="https://www.buymeacoffee.com/acrastt" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a> |
|
|
|
This is [StableLM 3B 4E1T](https://huggingface.co/stabilityai/stablelm-3b-4e1t) finetuned on [EverythingLM Data V3(ShareGPT Format)](https://huggingface.co/datasets/acrastt/EverythingLM-V3-ShareGPT) for 2 epochs using [QLoRA](https://arxiv.org/abs/2305.14314). |
|
|
|
Prompt template: |
|
``` |
|
### HUMAN: |
|
{prompt} |
|
|
|
### RESPONSE: |
|
``` |
|
|
|
Note that this model have the EOS token of `<|endoftext|>` instead of `<\s>`. |
|
|
|
## Attribution |
|
[StableLM 3B 4E1T](https://huggingface.co/stabilityai/stablelm-3b-4e1t) by [Stability AI](https://stability.ai/) is licensed under [CC BY-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/). |
|
|
|
Modifications: |
|
- Instruction tuned on dataset [EverythingLM Data V3(ShareGPT Format)](https://huggingface.co/datasets/acrastt/EverythingLM-V3-ShareGPT) for 2 epochs using [QLoRA](https://arxiv.org/abs/2305.14314). |
|
- Added `"_name_or_path"`, changed `"torch_dtype"` and `"transformers_version"` in [`config.json`](https://huggingface.co/acrastt/Marx-3B-V3/blob/main/config.json). |
|
- Changes to [`README.MD`](https://huggingface.co/acrastt/Marx-3B-V3/blob/main/README.md). |
