README.md

metadata

tags:
  - merge
  - mergekit
  - lazymergekit
  - OpenPipe/mistral-ft-optimized-1218
  - mlabonne/NeuralHermes-2.5-Mistral-7B
base_model:
  - OpenPipe/mistral-ft-optimized-1218
  - mlabonne/NeuralHermes-2.5-Mistral-7B

MERGEMODEL-7B-slerp

• OpenPipe/mistral-ft-optimized-1218
• mlabonne/NeuralHermes-2.5-Mistral-7B

🧩 Configuration

slices:

     - sources:
          - model: OpenPipe/mistral-ft-optimized-1218
            layer_range: [0,32]
          - model: mlabonne/NeuralHermes-2.5-Mistral-7B
            layer_range: [0,32]
merge_method: slerp
base_model: OpenPipe/mistral-ft-optimized-1218
parameters:

     t:
     
          - filter: self_attn
            value: [0,0.5,0.3,0.7,1]
          - filter: mlp
            value: [1,0.5,0.7,0.3,0]
          - value: 0.5
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "jS84/MERGEMODEL-7B-slerp"
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"])