RichardErkhov/djuna_-_G2-GSHT-4bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

G2-GSHT - bnb 4bits

• Model creator: https://huggingface.co/djuna/
• Original model: https://huggingface.co/djuna/G2-GSHT/

Original model description:

library_name: transformers tags: - mergekit - merge base_model: - TheDrummer/Gemmasutra-9B-v1 - Nekuromento/Hematoma-Gemma-Model-Stock-9B model-index: - name: G2-GSHT 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: 56.3 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/G2-GSHT 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: 30.99 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/G2-GSHT 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: 3.17 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/G2-GSHT 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: 10.07 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/G2-GSHT 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: 8.17 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/G2-GSHT 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: 23.0 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/G2-GSHT 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 SLERP merge method.

Models Merged

The following models were included in the merge:

• TheDrummer/Gemmasutra-9B-v1
• Nekuromento/Hematoma-Gemma-Model-Stock-9B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Nekuromento/Hematoma-Gemma-Model-Stock-9B
  - model: TheDrummer/Gemmasutra-9B-v1
merge_method: slerp
base_model: TheDrummer/Gemmasutra-9B-v1
parameters:
  t:
    - filter: self_attn
      value: [0.3, 0.4, 0.3, 0.5, 0.6]
    - filter: mlp
      value: [0.6, 0.5, 0.6, 0.5, 0.5, 0.4, 0.5]
    - value: [0.6, 0.6, 0.4, 0.6, 0.7, 0.4, 0.4]
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	21.95
IFEval (0-Shot)	56.30
BBH (3-Shot)	30.99
MATH Lvl 5 (4-Shot)	3.17
GPQA (0-shot)	10.07
MuSR (0-shot)	8.17
MMLU-PRO (5-shot)	23.00