39 lines
1.0 KiB
Markdown
39 lines
1.0 KiB
Markdown
|
|
||
|
|
---
|
||
|
|
license: apache-2.0
|
||
|
|
datasets:
|
||
|
|
- Intel/orca_dpo_pairs
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
---
|
||
|
|
|
||
|
|
# NeuralPipe-7B-slerp-DPO
|
||
|
|
|
||
|
|
NeuralPipe-7B-slerp is a Direct Preference Optimized version of [Samee-ur/NeuralPipe-7B-slerp](https://huggingface.co/Samee-ur/NeuralPipe-7B-slerp).
|
||
|
|
I performed Direct Preference Optimization on the [Intel/orca_dpo_pairs dataset](https://huggingface.co/datasets/Intel/orca_dpo_pairs)
|
||
|
|
|
||
|
|
|
||
|
|
## 💻 Usage
|
||
|
|
|
||
|
|
```python
|
||
|
|
!pip install -qU transformers accelerate
|
||
|
|
|
||
|
|
from transformers import AutoTokenizer
|
||
|
|
import transformers
|
||
|
|
import torch
|
||
|
|
|
||
|
|
model = "Samee-ur/NeuralPipe-7B-slerp-DPO"
|
||
|
|
messages = [{"role": "user", "content": "What is a large language model?"}]
|
||
|
|
|
||
|
|
tokenizer = AutoTokenizer.from_pretrained(model)
|
||
|
|
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||
|
|
pipeline = transformers.pipeline(
|
||
|
|
"text-generation",
|
||
|
|
model=model,
|
||
|
|
torch_dtype=torch.float16,
|
||
|
|
device_map="auto",
|
||
|
|
)
|
||
|
|
|
||
|
|
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"])
|
||
|
|
```
|