|
--- |
|
license: mit |
|
language: |
|
- en |
|
--- |
|
# **Introduction** |
|
MoMo-70B-lora-1.8.6-DPO is a Direct Preference Optimization([DPO](https://arxiv.org/abs/2305.18290)) version trained from MoMo-70B-LoRA-V1.4 as a base model, with several optimizations in hyperparameters. |
|
MoMo-70B-LoRA-V1.4 is trained via Supervised Fine-Tuning (SFT) using [LoRA](https://arxiv.org/abs/2106.09685), with the QWEN-72B model as its base-model. |
|
Note that we did not exploit any form of weight merge. |
|
For leaderboard submission, the trained weight is realigned for compatibility with llama. |
|
MoMo-70B is trained using **[Moreh](https://moreh.io/)**'s [MoAI platform](https://moreh.io/product), which simplifies the training of large-scale models, and AMD's MI250 GPU. |
|
|
|
|
|
## Details |
|
### Used Librarys |
|
- torch |
|
- peft |
|
### Used Datasets |
|
- [slimorca](Open-Orca/SlimOrca) |
|
- [truthy](https://huggingface.co/datasets/jondurbin/truthy-dpo-v0.1) |
|
- [orca_dpo_pairs](https://huggingface.co/datasets/Intel/orca_dpo_pairs) |
|
- No other dataset was used |
|
- No benchmark test set or the training set are used |
|
- [data contamination check](https://github.com/swj0419/detect-pretrain-code-contamination) result |
|
|
|
| Model | ARC | MMLU | TruthfulQA | GSM8K | |
|
|------------------------------|-------|-------|-------|-------| |
|
| **V1.8.6(result < 0.1, %)**| TBU |TBU | 0.73 | TBU | |
|
### Used Environments |
|
- AMD MI250 & MoAI platform |
|
- Please visit https://moreh.io/product for more information about MoAI platform |
|
- Or, contact us directly [[email protected]](mailto:[email protected]) |
|
|
|
## How to use |
|
|
|
```python |
|
# pip install transformers==4.35.2 |
|
import torch |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("moreh/MoMo-70B-LoRA-V1.8.6") |
|
model = AutoModelForCausalLM.from_pretrained( |
|
"moreh/MoMo-70B-LoRA-V1.8.6" |
|
) |
|
``` |
