|
--- |
|
license: other |
|
--- |
|
# Llama-3 chat vector |
|
|
|
- Update 0426: A small problem with the deployment of the model 'Llama-3-Seagull-Evo-8B', but we hope to have it back in good time! |
|
- Update 0526: Check our newest EMM model, [Alpha-Ko-8B-Instruct](https://huggingface.co/allganize/Llama-3-Alpha-Ko-8B-Instruct) |
|
|
|
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 | Method | Kobest(f1) | Haerae(acc) | |
|
|---|---|---|---| |
|
| [beomi/Llama-3-Open-Ko-8B-Instruct-preview](https://huggingface.co/beomi/Llama-3-Open-Ko-8B-Instruct-preview) | chat vector | 0.4368 | 0.439 | |
|
| [kuotient/Llama-3-Ko-8B-ties](https://huggingface.co/kuotient/Llama-3-Ko-8B-ties) | Ties | 0.4821 | 0.5160 | |
|
| [kuotient/Llama-3-Ko-8B-dare-ties](https://huggingface.co/kuotient/Llama-3-Ko-8B-dare-ties) | Dare-ties | 0.4950 | 0.5399 | |
|
| [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-Seagull-Evo-8B | Evolutionary Model Merging | **0.6139** | **0.5344** | |
|
|---|---|---|---| |
|
| [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) | Base | - | - | |
|
| [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) | - | 0.4239 | 0.4931 | |
|
| [beomi/Llama-3-Open-Ko-8B](https://huggingface.co/beomi/Llama-3-Open-Ko-8B) | Korean Base | 0.4374 | 0.3813 | |
|
|
|
|
|
All that aside, I'd like to thank @[beomi](https://huggingface.co/beomi) for creating such an awesome korean-based model. |
|
|
|
|
