README.md

metadata

license: apache-2.0
tags:
  - merge
  - mergekit
  - lazymergekit
  - Open-Orca/Mistral-7B-OpenOrca
  - openchat/openchat-3.5-0106
  - WizardLM/WizardMath-7B-V1.1
model-index:
  - name: TIES-Merging
    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: 58.11
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Cartinoe5930/TIES-Merging
          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: 75.74
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Cartinoe5930/TIES-Merging
          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: 51.57
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Cartinoe5930/TIES-Merging
          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: 41.25
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Cartinoe5930/TIES-Merging
          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: 72.38
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Cartinoe5930/TIES-Merging
          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: 19.41
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Cartinoe5930/TIES-Merging
          name: Open LLM Leaderboard

TIES-Merging

TIES-Merging is a merge of the following models using LazyMergekit:

• Open-Orca/Mistral-7B-OpenOrca
• openchat/openchat-3.5-0106
• WizardLM/WizardMath-7B-V1.1

🧩 Configuration

models:
  - model: mistralai/Mistral-7B-Instruct-v0.2
    # no parameters necessary for base model
  - model: Open-Orca/Mistral-7B-OpenOrca
    parameters:
      density: 0.5
      weight: 0.5
  - model: openchat/openchat-3.5-0106
    parameters:
      density: 0.5
      weight: 0.5
  - model: WizardLM/WizardMath-7B-V1.1
    parameters:
      density: 0.5
      weight: 0.5
merge_method: ties
base_model: mistralai/Mistral-7B-Instruct-v0.2
parameters:
  normalize: true
dtype: float16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Cartinoe5930/TIES-Merging"
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"])

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	53.08
AI2 Reasoning Challenge (25-Shot)	58.11
HellaSwag (10-Shot)	75.74
MMLU (5-Shot)	51.57
TruthfulQA (0-shot)	41.25
Winogrande (5-shot)	72.38
GSM8k (5-shot)	19.41