jieunhan's picture
Update README.md
11dcf2d verified
---
license: apache-2.0
tags:
- moe
- frankenmoe
- merge
- mergekit
- lazymergekit
- beomi/OPEN-SOLAR-KO-10.7B
- hyeogi/SOLAR-10.7B-dpo-v1
base_model:
- beomi/OPEN-SOLAR-KO-10.7B
- hyeogi/SOLAR-10.7B-dpo-v1
---
# solar_merge_test_1
## ๐Ÿงฉ Configuration
```yaml
base_model: beomi/OPEN-SOLAR-KO-10.7B
dtype: float16
experts:
- source_model: beomi/OPEN-SOLAR-KO-10.7B
positive_prompts: ["๋‹น์‹ ์€ ์นœ์ ˆํ•œ ๋ณดํŽธ์ ์ธ ์–ด์‹œ์Šคํ„ดํŠธ์ด๋‹ค."]
- source_model: hyeogi/SOLAR-10.7B-dpo-v1
positive_prompts: ["๋‹น์‹ ์€ ์˜ณ์€ ์‚ฌ์‹ค๋งŒ์„ ๋งํ•˜๋Š” ์–ด์‹œ์Šคํ„ดํŠธ์ด๋‹ค."]
gate_mode: cheap_embed
tokenizer_source: base
```
## ๐Ÿ’ป Usage
```python
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "jieunhan/solar_merge_test_1-1"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)
messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```