Quantization made by Richard Erkhov.

LLaMa-3.2-Instruct-JankMixBread-v0.1-3B - GGUF

Model creator: https://huggingface.co/PJMixers-Dev/
Original model: https://huggingface.co/PJMixers-Dev/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B/

Name	Quant method	Size
LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q2_K.gguf	Q2_K	1.27GB
LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.IQ3_XS.gguf	IQ3_XS	1.38GB
LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.IQ3_S.gguf	IQ3_S	1.44GB
LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q3_K_S.gguf	Q3_K_S	1.44GB
LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.IQ3_M.gguf	IQ3_M	1.49GB
LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q3_K.gguf	Q3_K	1.57GB
LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q3_K_M.gguf	Q3_K_M	1.57GB
LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q3_K_L.gguf	Q3_K_L	1.69GB
LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.IQ4_XS.gguf	IQ4_XS	1.71GB
LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q4_0.gguf	Q4_0	1.79GB
LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.IQ4_NL.gguf	IQ4_NL	1.79GB
LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q4_K_S.gguf	Q4_K_S	1.8GB
LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q4_K.gguf	Q4_K	1.88GB
LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q4_K_M.gguf	Q4_K_M	1.88GB
LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q4_1.gguf	Q4_1	1.95GB
LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q5_0.gguf	Q5_0	2.11GB
LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q5_K_S.gguf	Q5_K_S	2.11GB
LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q5_K.gguf	Q5_K	2.16GB
LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q5_K_M.gguf	Q5_K_M	2.16GB
LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q5_1.gguf	Q5_1	2.28GB
LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q6_K.gguf	Q6_K	2.46GB
LLaMa-3.2-Instruct-JankMixBread-v0.1-3B.Q8_0.gguf	Q8_0	3.19GB

Original model description:

license: llama3.2 library_name: transformers tags: - mergekit - merge base_model: - meta-llama/Llama-3.2-3B - meta-llama/Llama-3.2-3B-Instruct - PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B model-index: - name: LLaMa-3.2-Instruct-JankMixBread-v0.1-3B 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: 50.41 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PJMixers-Dev/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B 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: 22.76 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PJMixers-Dev/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B 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: 10.73 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PJMixers-Dev/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B 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: 4.36 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PJMixers-Dev/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B 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: 4.68 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PJMixers-Dev/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B 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: 23.15 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=PJMixers-Dev/LLaMa-3.2-Instruct-JankMixBread-v0.1-3B name: Open LLM Leaderboard

LLaMa-3.2-Instruct-JankMixBread-v0.1-3B

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

Merge Details

Merge Method

This model was merged using the breadcrumbs_ties merge method using meta-llama/Llama-3.2-3B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: breadcrumbs_ties
base_model: meta-llama/Llama-3.2-3B
tokenizer_source: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B
dtype: bfloat16
parameters:
  normalize: true
models:
  - model: meta-llama/Llama-3.2-3B-Instruct
    parameters:
      weight: 1
      density: 0.9
      gamma: 0.01
  - model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B
    parameters:
      weight: 1
      density: 0.9
      gamma: 0.01

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	19.35
IFEval (0-Shot)	50.41
BBH (3-Shot)	22.76
MATH Lvl 5 (4-Shot)	10.73
GPQA (0-shot)	4.36
MuSR (0-shot)	4.68
MMLU-PRO (5-shot)	23.15

Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more quants, at much higher speed, than I would otherwise be able to.