README.md

metadata

license: apache-2.0
tags:
  - merge
  - mergekit
  - lazymergekit
model-index:
  - name: TriMistral-7B-MODELSTOCK
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: AI2 Reasoning Challenge (25-Shot)
          type: ai2_arc
          config: ARC-Challenge
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: acc_norm
            value: 64.68
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Muhammad2003/TriMistral-7B-MODELSTOCK
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HellaSwag (10-Shot)
          type: hellaswag
          split: validation
          args:
            num_few_shot: 10
        metrics:
          - type: acc_norm
            value: 85.64
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Muhammad2003/TriMistral-7B-MODELSTOCK
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU (5-Shot)
          type: cais/mmlu
          config: all
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 64.21
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Muhammad2003/TriMistral-7B-MODELSTOCK
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: TruthfulQA (0-shot)
          type: truthful_qa
          config: multiple_choice
          split: validation
          args:
            num_few_shot: 0
        metrics:
          - type: mc2
            value: 57.24
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Muhammad2003/TriMistral-7B-MODELSTOCK
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Winogrande (5-shot)
          type: winogrande
          config: winogrande_xl
          split: validation
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 78.69
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Muhammad2003/TriMistral-7B-MODELSTOCK
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GSM8k (5-shot)
          type: gsm8k
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 52.46
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Muhammad2003/TriMistral-7B-MODELSTOCK
          name: Open LLM Leaderboard

TriMistral-7B-MODELSTOCK

TriMistral-7B-MODELSTOCK is a merge of the following models using LazyMergekit: Special thanks to Charles Goddard for the quick implementation!

🧩 Configuration

models:
  - model: HuggingFaceH4/zephyr-7b-beta
  - model: NousResearch/Hermes-2-Pro-Mistral-7B
  - model: instructlab/merlinite-7b-lab
merge_method: model_stock
base_model: HuggingFaceH4/zephyr-7b-beta
dtype: float16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Muhammad2003/TriMistral-7B-MODELSTOCK"
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"])

🏆 Evaluation

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	67.15
AI2 Reasoning Challenge (25-Shot)	64.68
HellaSwag (10-Shot)	85.64
MMLU (5-Shot)	64.21
TruthfulQA (0-shot)	57.24
Winogrande (5-shot)	78.69
GSM8k (5-shot)	52.46