base_model: teknium/OpenHermes-2.5-Mistral-7B
dtype: float16
merge_method: dare_ties
parameters:
  density: 0.6

slices:
  - sources:
    - model: NousResearch/Hermes-2-Pro-Mistral-7B
      layer_range: [0, 32]
      parameters:
        weight: 0.65
        density: 0.7
    - model: teknium/OpenHermes-2.5-Mistral-7B
      layer_range: [0, 32]  
      parameters:
        weight: 0.35
        density: 0.6

💻 Usage

python

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "alantcoding/TranscriptAnalyzer-Open-7B"
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"])