zelk12_-_MT3-Gen2-gemma-2-9B-4bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

MT3-Gen2-gemma-2-9B - bnb 4bits

• Model creator: https://huggingface.co/zelk12/
• Original model: https://huggingface.co/zelk12/MT3-Gen2-gemma-2-9B/

Original model description:

library_name: transformers tags:

• mergekit
• merge base_model:
• zelk12/MT3-Gen2-GMM-gemma-2-9B
• zelk12/MT3-Gen2-IMUBMA-gemma-2-9B model-index:
• name: MT3-Gen2-gemma-2-9B 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: 78.43 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zelk12/MT3-Gen2-gemma-2-9B 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: 43.94 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zelk12/MT3-Gen2-gemma-2-9B 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: 2.04 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zelk12/MT3-Gen2-gemma-2-9B 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: 14.32 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zelk12/MT3-Gen2-gemma-2-9B 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: 10.02 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zelk12/MT3-Gen2-gemma-2-9B 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: 37.03 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zelk12/MT3-Gen2-gemma-2-9B name: Open LLM Leaderboard

---

Quants

Provided by @mradermacher

GGUF Static: https://huggingface.co/mradermacher/MT3-Gen2-gemma-2-9B-GGUF

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:

• zelk12/MT3-Gen2-GMM-gemma-2-9B
• zelk12/MT3-Gen2-IMUBMA-gemma-2-9B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: zelk12/MT3-Gen2-GMM-gemma-2-9B
  - model: zelk12/MT3-Gen2-IMUBMA-gemma-2-9B
merge_method: slerp
base_model: zelk12/MT3-Gen2-GMM-gemma-2-9B
dtype: bfloat16
parameters:
  t: 0.25

Open LLM Leaderboard Evaluation Results

Detailed results can be found here