JeongwonChoi's picture
Update README.md
fadf0ac verified
---
tags:
- text-generation
license: cc-by-nc-sa-4.0
language:
- ko
base_model: LDCC/LDCC-SOLAR-10.7B
pipeline_tag: text-generation
---
# **DataVortexS-10.7B-dpo-v1.6**
<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**
[LDCC/LDCC-SOLAR-10.7B](https://huggingface.co/LDCC/LDCC-SOLAR-10.7B)
### **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
당신은 μ‚¬λžŒλ“€μ΄ 정보λ₯Ό 찾을 수 μžˆλ„λ‘ λ„μ™€μ£ΌλŠ” 인곡지λŠ₯ λΉ„μ„œμž…λ‹ˆλ‹€.<|im_end|>
<|im_start|>user
λŒ€ν•œλ―Όκ΅­μ˜ μˆ˜λ„λŠ” μ–΄λ””μ•Ό?<|im_end|>
<|im_start|>assistant
λŒ€ν•œλ―Όκ΅­μ˜ μˆ˜λ„λŠ” μ„œμšΈμž…λ‹ˆλ‹€.<|im_end|>
<|im_start|>user
μ„œμšΈ μΈκ΅¬λŠ” 총 λͺ‡ λͺ…이야?<|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 | 0.920118 | 0.92442 | 0.929443 | 0.927317 |
| kobest_copa | 0.727263 | 0.778936 | 0.804812 | 0.815761 |
| kobest_hellaswag | 0.433039 | 0.465922 | 0.459741 | 0.471022 |
| kobest_sentineg | 0.764909 | 0.93946 | 0.937002 | 0.931962 |
| **Average** | **0.711332** | **0.777185** | **0.78275** | **0.786516** |
### **[Ko-LLM-Leaderboard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard)**
| Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
| ------: | -----: | -----------: | ------: | ------------: | --------------: |
| 59.22 | 53.84 | 67.9 | 52.37 | 64.6 | 57.38 |
## **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-v1.6")
tokenizer = AutoTokenizer.from_pretrained("Edentns/DataVortexS-10.7B-dpo-v1.6")
messages = [
{"role": "system", "content": "당신은 μ‚¬λžŒλ“€μ΄ 정보λ₯Ό 찾을 수 μžˆλ„λ‘ λ„μ™€μ£ΌλŠ” 인곡지λŠ₯ λΉ„μ„œμž…λ‹ˆλ‹€."},
{"role": "user", "content": "λŒ€ν•œλ―Όκ΅­μ˜ μˆ˜λ„λŠ” μ–΄λ””μ•Ό?"},
{"role": "assistant", "content": "λŒ€ν•œλ―Όκ΅­μ˜ μˆ˜λ„λŠ” μ„œμšΈμž…λ‹ˆλ‹€."},
{"role": "user", "content": "μ„œμšΈ μΈκ΅¬λŠ” 총 λͺ‡ λͺ…이야?"}
]
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>