README.md

metadata

base_model:
  - meta-llama/Llama-3.1-8B
  - grimjim/SauerHuatuoSkywork-o1-Llama-3.1-8B
  - deepseek-ai/DeepSeek-R1-Distill-Llama-8B
library_name: transformers
pipeline_tag: text-generation
tags:
  - mergekit
  - merge
license: llama3.1
model-index:
  - name: DeepSauerHuatuoSkywork-R1-o1-Llama-3.1-8B
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: IFEval (0-Shot)
          type: wis-k/instruction-following-eval
          split: train
          args:
            num_few_shot: 0
        metrics:
          - type: inst_level_strict_acc and prompt_level_strict_acc
            value: 47.97
            name: averaged accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=grimjim%2FDeepSauerHuatuoSkywork-R1-o1-Llama-3.1-8B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BBH (3-Shot)
          type: SaylorTwift/bbh
          split: test
          args:
            num_few_shot: 3
        metrics:
          - type: acc_norm
            value: 32.77
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=grimjim%2FDeepSauerHuatuoSkywork-R1-o1-Llama-3.1-8B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MATH Lvl 5 (4-Shot)
          type: lighteval/MATH-Hard
          split: test
          args:
            num_few_shot: 4
        metrics:
          - type: exact_match
            value: 21.98
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=grimjim%2FDeepSauerHuatuoSkywork-R1-o1-Llama-3.1-8B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GPQA (0-shot)
          type: Idavidrein/gpqa
          split: train
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 11.74
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=grimjim%2FDeepSauerHuatuoSkywork-R1-o1-Llama-3.1-8B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MuSR (0-shot)
          type: TAUR-Lab/MuSR
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 14.1
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=grimjim%2FDeepSauerHuatuoSkywork-R1-o1-Llama-3.1-8B
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU-PRO (5-shot)
          type: TIGER-Lab/MMLU-Pro
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 32.85
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=grimjim%2FDeepSauerHuatuoSkywork-R1-o1-Llama-3.1-8B
          name: Open LLM Leaderboard

DeepSauerHuatuoSkywork-R1-o1-Llama-3.1-8B

This is a merge of pre-trained language models created using mergekit.

DeepSeek-R1-Distill-Llama-8B has been merged in at low weight in hopes of increasing the reasoning capability of the resulting model.

Built with Llama.

Merge Details

Merge Method

This model was merged using the task arithmetic merge method using meta-llama/Llama-3.1-8B as a base.

Models Merged

The following models were included in the merge:

• grimjim/SauerHuatuoSkywork-o1-Llama-3.1-8B
• deepseek-ai/DeepSeek-R1-Distill-Llama-8B

Configuration

The following YAML configuration was used to produce this model:

base_model: meta-llama/Llama-3.1-8B
dtype: bfloat16
merge_method: task_arithmetic
parameters:
  normalize: true
models:
  - model: meta-llama/Llama-3.1-8B
  - model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
    parameters:
      weight: 0.1
  - model: grimjim/SauerHuatuoSkywork-o1-Llama-3.1-8B
    parameters:
      weight: 0.9

Open LLM Leaderboard Evaluation Results

Detailed results can be found here! Summarized results can be found here!

Metric	Value (%)
Average	26.90
IFEval (0-Shot)	47.97
BBH (3-Shot)	32.77
MATH Lvl 5 (4-Shot)	21.98
GPQA (0-shot)	11.74
MuSR (0-shot)	14.10
MMLU-PRO (5-shot)	32.85