Gille's picture
Adding Evaluation Results (#1)
0196ec7 verified
metadata
license: apache-2.0
tags:
  - merge
  - mergekit
  - lazymergekit
  - WizardLM/WizardMath-7B-V1.1
  - AurelPx/Percival_01-7b-slerp
  - Weyaxi/Einstein-v4-7B
  - Kukedlc/NeuralMaths-Experiment-7b
  - Gille/StrangeMerges_35-7B-slerp
base_model:
  - WizardLM/WizardMath-7B-V1.1
  - AurelPx/Percival_01-7b-slerp
  - Weyaxi/Einstein-v4-7B
  - Kukedlc/NeuralMaths-Experiment-7b
  - Gille/StrangeMerges_35-7B-slerp
model-index:
  - name: StrangeMerges_52-7B-dare_ties
    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: 69.03
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/StrangeMerges_52-7B-dare_ties
          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: 87.15
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/StrangeMerges_52-7B-dare_ties
          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: 64.94
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/StrangeMerges_52-7B-dare_ties
          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: 65.76
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/StrangeMerges_52-7B-dare_ties
          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: 81.93
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/StrangeMerges_52-7B-dare_ties
          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: 72.25
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/StrangeMerges_52-7B-dare_ties
          name: Open LLM Leaderboard

StrangeMerges_52-7B-dare_ties

StrangeMerges_52-7B-dare_ties is a merge of the following models using LazyMergekit:

🧩 Configuration

models:
  - model: Gille/StrangeMerges_51-7B-dare_ties
    # No parameters necessary for base model
  - model: WizardLM/WizardMath-7B-V1.1
    parameters:
      density: 0.66
      weight: 0.2
  - model: AurelPx/Percival_01-7b-slerp
    parameters:
      density: 0.55
      weight: 0.2
  - model: Weyaxi/Einstein-v4-7B
    parameters:
      density: 0.55
      weight: 0.2
  - model: Kukedlc/NeuralMaths-Experiment-7b
    parameters:
      density: 0.44
      weight: 0.2
  - model: Gille/StrangeMerges_35-7B-slerp
    parameters:
      density: 0.66
      weight: 0.2
merge_method: dare_ties
base_model: Gille/StrangeMerges_51-7B-dare_ties
parameters:
  int8_mask: true
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Gille/StrangeMerges_52-7B-dare_ties"
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. 73.51
AI2 Reasoning Challenge (25-Shot) 69.03
HellaSwag (10-Shot) 87.15
MMLU (5-Shot) 64.94
TruthfulQA (0-shot) 65.76
Winogrande (5-shot) 81.93
GSM8k (5-shot) 72.25