README.md

metadata

license: apache-2.0
tags:
  - merge

mistral-7b-merged-dare-v2

mistral-7b-merged-dare-v2 is a merge of the following models:

🧩 Configuration

models:
  - model: mistralai/Mistral-7B-v0.1
  - model: samir-fama/SamirGPT-v1
    parameters:
      density: 0.53
      weight: 0.4
  - model: abacusai/Slerp-CM-mist-dpo
    parameters:
      density: 0.53
      weight: 0.3
  - model: EmbeddedLLM/Mistral-7B-Merge-14-v0.2
    parameters:
      density: 0.53
      weight: 0.3
  - model: Weyaxi/Einstein-v4-7B
    parameters:
      density: 0.53
      weight: 0.3            
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
  int8_mask: true
dtype: bfloat16

💻 Usage

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mistral-7b-merged-dare_6x7"

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.	73.46
AI2 Reasoning Challenge (25-Shot)	69.62
HellaSwag (10-Shot)	87.04
MMLU (5-Shot)	65.18
TruthfulQA (0-shot)	66.98
Winogrande (5-shot)	80.58
GSM8k (5-shot)	71.34