Original model description:

library_name: transformers tags: - mergekit - merge base_model: - bunnycore/Llama-3.2-3B-Long-Think - huihui-ai/Llama-3.2-3B-Instruct-abliterated - bunnycore/Llama-3.2-3B-Pure-RP model-index: - name: Llama-3.2-3B-Mix-Skill 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: 64.04 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-Mix-Skill 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: 23.78 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-Mix-Skill 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: 12.69 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-Mix-Skill 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: 1.57 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-Mix-Skill 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: 2.75 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-Mix-Skill 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: 23.56 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-Mix-Skill name: Open LLM Leaderboard

This language model is a merged version of several pre-trained models, designed to excel in roleplay, long-form question answering, and prompt following tasks. It was created using the TIES merge method with huihui-ai/Llama-3.2-3B-Instruct-abliterated as the base model.

Intended Use:

This model is suitable for a variety of applications, including:

Creative Writing: Generating stories, poems, scripts, and other forms of creative text.
Question Answering: Providing comprehensive and informative answers to a wide range of questions.
Role-Playing: Engaging in interactive role-playing scenarios with users.
Prompt Following: Completing tasks and generating text based on specific prompts or instructions.

merge

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

Merge Details

Merge Method

This model was merged using the TIES merge method using huihui-ai/Llama-3.2-3B-Instruct-abliterated as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: bunnycore/Llama-3.2-3B-Long-Think
    parameters:
      density: 0.5
      weight: 0.5
  - model: bunnycore/Llama-3.2-3B-Pure-RP
    parameters:
      density: 0.5
      weight: 0.5

merge_method: ties
base_model: huihui-ai/Llama-3.2-3B-Instruct-abliterated
parameters:
  normalize: false
  int8_mask: true
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	21.40
IFEval (0-Shot)	64.04
BBH (3-Shot)	23.78
MATH Lvl 5 (4-Shot)	12.69
GPQA (0-shot)	1.57
MuSR (0-shot)	2.75
MMLU-PRO (5-shot)	23.56