Technoculture/BioMistral-Hermes-Dare

models:
  - model: BioMistral/BioMistral-7B-DARE
    parameters:
      weight: 1.0
  - model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO
    parameters:
      weight: 0.6
merge_method: linear
dtype: float16

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Technoculture/BioMistral-Hermes-Dare"
messages = [{"role": "user", "content": "I am feeling sleepy these days"}]

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"])