mychen76's picture
Update README.md
573eceb verified
metadata
license: apache-2.0
tags:
  - merge

mistral-7b-merged-ties

mistral-7b-merged-ties is a merge of the following models:

🧩 Configuration

models:
    - model: mistralai/Mistral-7B-v0.1  
    - model: OpenPipe/mistral-ft-optimized-1218
      parameters:
        density: 0.5  # density gradient
        weight: 0.3
    - model: mlabonne/NeuralHermes-2.5-Mistral-7B
      parameters:
        density: 0.5
        weight: 0.3  # weight gradient
merge_method: ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
  normalize: true
dtype: bfloat16

💻 Usage

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mychen76/mistral-7b-merged-ties"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)

messages = [{"role": "user", "content": "Why the sky is blue"}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
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"])

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 71.37
AI2 Reasoning Challenge (25-Shot) 67.92
HellaSwag (10-Shot) 85.93
MMLU (5-Shot) 64.07
TruthfulQA (0-shot) 61.31
Winogrande (5-shot) 80.03
GSM8k (5-shot) 68.54