mergekit
merge base_model:
huihui-ai/Llama-3.2-3B-Instruct-abliterated
bunnycore/Llama-3.2-3B-Long-Think-lora_model model-index:
name: Llama-3.2-3B-Long-Think 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: 54.73 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-Long-Think 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: 24.23 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-Long-Think 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: 12.92 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-Long-Think 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: 1.45 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-Long-Think 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: 1.21 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-Long-Think 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: 22.75 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.2-3B-Long-Think name: Open LLM Leaderboard

merge

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

Merge Details

Merge Method

This model was merged using the passthrough merge method using huihui-ai/Llama-3.2-3B-Instruct-abliterated + bunnycore/Llama-3.2-3B-Long-Think-lora_model as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml

base_model: huihui-ai/Llama-3.2-3B-Instruct-abliterated+bunnycore/Llama-3.2-3B-Long-Think-lora_model
dtype: bfloat16
merge_method: passthrough
models:
  - model: huihui-ai/Llama-3.2-3B-Instruct-abliterated+bunnycore/Llama-3.2-3B-Long-Think-lora_model

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	19.55
IFEval (0-Shot)	54.73
BBH (3-Shot)	24.23
MATH Lvl 5 (4-Shot)	12.92
GPQA (0-shot)	1.45
MuSR (0-shot)	1.21
MMLU-PRO (5-shot)	22.75

RichardErkhov/bunnycore_-_Llama-3.2-3B-Long-Think-8bits

Original model description: