README.md

metadata

license: llama3.2
library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - NousResearch/Hermes-3-Llama-3.2-3B
  - prithivMLmods/Llama-Thinker-3B-Preview2
model-index:
  - name: Hermes-Llama-3.2-CoT
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: IFEval (0-Shot)
          type: HuggingFaceH4/ifeval
          args:
            num_few_shot: 0
        metrics:
          - type: inst_level_strict_acc and prompt_level_strict_acc
            value: 41.78
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Hermes-Llama-3.2-CoT
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BBH (3-Shot)
          type: BBH
          args:
            num_few_shot: 3
        metrics:
          - type: acc_norm
            value: 23.8
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Hermes-Llama-3.2-CoT
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MATH Lvl 5 (4-Shot)
          type: hendrycks/competition_math
          args:
            num_few_shot: 4
        metrics:
          - type: exact_match
            value: 9.14
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Hermes-Llama-3.2-CoT
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GPQA (0-shot)
          type: Idavidrein/gpqa
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 3.91
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Hermes-Llama-3.2-CoT
          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: 5.09
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Hermes-Llama-3.2-CoT
          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: 21.63
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Hermes-Llama-3.2-CoT
          name: Open LLM Leaderboard

Merge

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

Merge Details

Hermes with some Chain of Thought running though its veins.

Quant: https://huggingface.co/Triangle104/Hermes-Llama-3.2-CoT-Q4_K_M-GGUF

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• NousResearch/Hermes-3-Llama-3.2-3B
• prithivMLmods/Llama-Thinker-3B-Preview2

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: NousResearch/Hermes-3-Llama-3.2-3B
  - model: prithivMLmods/Llama-Thinker-3B-Preview2
merge_method: slerp
base_model: NousResearch/Hermes-3-Llama-3.2-3B
dtype: bfloat16
parameters:
  t: [0, 0.5, 0.7, 1, 0.7, 0.5, 0]

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	17.56
IFEval (0-Shot)	41.78
BBH (3-Shot)	23.80
MATH Lvl 5 (4-Shot)	9.14
GPQA (0-shot)	3.91
MuSR (0-shot)	5.09
MMLU-PRO (5-shot)	21.63