Downloads · 30 days
9
22% of all-time downloads
llama3-8b-dpo
mxz/llama3-8b-dpo
llama3-8b-dpo is a text generation model from mxz. Use it when you need the model to write or continue text. It is set up for transformers.
--- datasets: \ - mxz/CValuesDPO \ language: \ - zh \ - en \ metrics: \ - perplexity \ pipelinetag: \ - text-generation \ tags: \ - DPO \ - fintune \ - alignment \ - LoRA \ - Llama-3 ---
All-time downloads
41
Public
Parameters
8B
17.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors17.4 GB · 100%
Parameter types
How the weights are stored.
BF167.4B · 92%
Try a prompt
Model card
From the Hugging Face model README
dataset Intruction
datasets: \
- mxz/CValues_DPO
language: \ - zh \
- en
metrics: \ - perplexity
pipeline_tag: \ - text-generation
tags: \ - DPO \
- fintune \
- alignment \
- LoRA \
- Llama-3
About mxz-llama-3-8B-sft
This model trained by SFT and PPO.
It's have coding, reasoing, chinese QA .
evaluation
Result:
| Model | MMLU | C-EVAL | C-MMLU |
|---|---|---|---|
| Llama-3-8B | 55.5 | 47.0 | 48.0 |
| Llama-3-8B-Instruct | 60.1 | 49.7 | 49.3 |
| Llama-3-8B-dpo | 62.2 | 49.9 | 49.4 |
- Llama-3-8B evaluation result from ymcui/Chinese-LLaMA-Alpaca-3
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- Created
- Jul 26, 2024
- Updated
- Jul 28, 2024