|
--- |
|
tags: |
|
- text-generation |
|
license: cc-by-nc-sa-4.0 |
|
language: |
|
- ko |
|
base_model: megastudy/M-SOLAR-10.7B-v1.3 |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
# **DataVortexS-10.7B-dpo-v1.5** |
|
|
|
<img src="./DataVortex.png" alt="DataVortex" style="height: 8em;"> |
|
|
|
## Our Team |
|
|
|
| Research & Engineering | Product Management | |
|
| :--------------------: | :----------------: | |
|
| Kwangseok Yang | Seunghyun Choi | |
|
| Jeongwon Choi | Hyoseok Choi | |
|
|
|
## **Model Details** |
|
|
|
### **Base Model** |
|
|
|
[megastudy/M-SOLAR-10.7B-v1.3](https://huggingface.co/megastudy/M-SOLAR-10.7B-v1.3) |
|
|
|
### **Trained On** |
|
|
|
- **OS**: Ubuntu 22.04 |
|
- **GPU**: H100 80GB 4ea |
|
- **transformers**: v4.36.2 |
|
|
|
### **Instruction format** |
|
|
|
It follows **ChatML** format. |
|
|
|
E.g. |
|
|
|
```python |
|
text = """\ |
|
<|im_start|>system |
|
λΉμ μ μ¬λλ€μ΄ μ 보λ₯Ό μ°Ύμ μ μλλ‘ λμμ£Όλ μΈκ³΅μ§λ₯ λΉμμ
λλ€.<|im_end|> |
|
<|im_start|>user |
|
λνλ―Όκ΅μ μλλ μ΄λμΌ?<|im_end|> |
|
<|im_start|>assistant |
|
λνλ―Όκ΅μ μλλ μμΈμ
λλ€.<|im_end|> |
|
<|im_start|>user |
|
μμΈ μΈκ΅¬λ μ΄ λͺ λͺ
μ΄μΌ?<|im_end|> |
|
<|im_start|>assistant |
|
""" |
|
``` |
|
|
|
## **Model Benchmark** |
|
|
|
### **[Ko LM Eval Harness](https://github.com/Beomi/ko-lm-evaluation-harness)** |
|
|
|
| Task | 0-shot | 5-shot | 10-shot | 50-shot | |
|
| :--------------- | -----------: | -----------: | -----------: | -----------: | |
|
| kobest_boolq | 0.34687 | 0.930158 | 0.943013 | 0.938029 | |
|
| kobest_copa | 0.693351 | 0.751805 | 0.75772 | 0.771704 | |
|
| kobest_hellaswag | 0.480736 | 0.470852 | 0.474766 | 0.478576 | |
|
| kobest_sentineg | 0.789423 | 0.962208 | 0.967241 | 0.964717 | |
|
| **Average** | **0.577595** | **0.778756** | **0.785685** | **0.788257** | |
|
|
|
### **[Ko-LLM-Leaderboard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard)** |
|
|
|
| Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 | |
|
| ------: | -----: | -----------: | ------: | ------------: | --------------: | |
|
| 55.32 | 52.13 | 61.27 | 53.99 | 49.71 | 59.5 | |
|
|
|
## **Implementation Code** |
|
|
|
This model contains the chat_template instruction format. |
|
You can use the code below. |
|
|
|
```python |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
device = "cuda" # the device to load the model onto |
|
|
|
model = AutoModelForCausalLM.from_pretrained("Edentns/DataVortexS-10.7B-dpo-v1.5") |
|
tokenizer = AutoTokenizer.from_pretrained("Edentns/DataVortexS-10.7B-dpo-v1.5") |
|
|
|
messages = [ |
|
{"role": "system", "content": "λΉμ μ μ¬λλ€μ΄ μ 보λ₯Ό μ°Ύμ μ μλλ‘ λμμ£Όλ μΈκ³΅μ§λ₯ λΉμμ
λλ€."}, |
|
{"role": "user", "content": "λνλ―Όκ΅μ μλλ μ΄λμΌ?"}, |
|
{"role": "assistant", "content": "λνλ―Όκ΅μ μλλ μμΈμ
λλ€."}, |
|
{"role": "user", "content": "μμΈ μΈκ΅¬λ μ΄ λͺ λͺ
μ΄μΌ?"} |
|
] |
|
|
|
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt") |
|
|
|
model_inputs = encodeds.to(device) |
|
model.to(device) |
|
|
|
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True) |
|
decoded = tokenizer.batch_decode(generated_ids) |
|
print(decoded[0]) |
|
``` |
|
|
|
## **License** |
|
|
|
The model is licensed under the [cc-by-nc-sa-4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/) license, which allows others to copy, modify, and share the work non-commercially, as long as they give appropriate credit and distribute any derivative works under the same license. |
|
|
|
<div align="center"> |
|
<a href="https://edentns.com/"> |
|
<img src="./Logo.png" alt="Logo" style="height: 3em;"> |
|
</a> |
|
</div> |
|
|
