|
|
--- |
|
|
license: other |
|
|
--- |
|
|
# Llama-3 chat vector |
|
|
|
|
|
This is 'modelified' version of _chat vector_ from the paper [Chat Vector: A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New Languages](https://arxiv.org/abs/2310.04799). So this is not a model, its just weight diff, just for ease to use myself(or you too)! |
|
|
|
|
|
What I understand here: |
|
|
'Chat vector method' is a merging method that utilizes the difference between the base model, the continuously pre-trained (usually language transferred) model, and the chat model; so the recipe is |
|
|
|
|
|
`model(base) + weight_diff(continous pretrained) + weight_diff(instruct)` or |
|
|
|
|
|
`model(base) + weight_diff(continous pretrained + fine-tuned) + weight_diff(instruct)`. |
|
|
|
|
|
So before (my) initial purpose in comparing which method is better, `llama3 → CP + chat vector → FT` vs. `llama3 → CP → FT + chat vector`, it seems reasonable to compare it with other methods in [Mergekit](https://github.com/arcee-ai/mergekit). |
|
|
|
|
|
| Model | Merge Method | Score(but what?) | |
|
|
|---|---|---| |
|
|
| [beomi/Llama-3-Open-Ko-8B-Instruct-preview](https://huggingface.co/beomi/Llama-3-Open-Ko-8B-Instruct-preview) | chat vector | - | |
|
|
| [kuotient/Llama-3-Ko-8B-ties](https://huggingface.co/kuotient/Llama-3-Ko-8B-ties) | Ties | - | |
|
|
| [kuotient/Llama-3-Ko-8B-dare-ties](https://huggingface.co/kuotient/Llama-3-Ko-8B-dare-ties) | Dare-ties | - | |
|
|
| [kuotient/Llama-3-Ko-8B-TA](https://huggingface.co/kuotient/Llama-3-Ko-8B-TA) | Task Arithmetic(maybe...? not sure about this) | - | |
|
|
| WIP | Model stock(I don't read this paper yet but still) | - | |
|
|
| [kuotient/Llama-3-Ko-8B-EMM](https://huggingface.co/kuotient/Llama-3-Ko-8B-EMM) | Evolutionary Model Merging | - | |
|
|
|
|
|
All that aside, I'd like to thank @[beomi](https://huggingface.co/beomi) for creating such an awesome korean-based model. |
|
|
|
|
|
|
