Mistral-Quantum-dpo / README.md
librarian-bot's picture
Librarian Bot: Add base_model metadata to model
d875fbf verified
|
raw
history blame
1.03 kB
metadata
license: apache-2.0
tags:
  - merge
base_model:
  - quantumaikr/quantum-dpo-v0.1
  - mncai/mistral-7b-dpo-v6

Mistral-Quantum-dpo

Mistral-Quantum-dpo is a merge of the following models


## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Yash21/Mistral-Quantum-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"])