theprint_-_ReWiz-Worldbuilder-7B-4bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

ReWiz-Worldbuilder-7B - bnb 4bits

• Model creator: https://huggingface.co/theprint/
• Original model: https://huggingface.co/theprint/ReWiz-Worldbuilder-7B/

Original model description:

library_name: transformers tags:

• mergekit
• merge base_model:
• theprint/WorldBuilder-7B
• theprint/ReWiz-7B model-index:
• name: ReWiz-Worldbuilder-7B 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: 25.1 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/ReWiz-Worldbuilder-7B 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: 25.08 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/ReWiz-Worldbuilder-7B 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: 2.95 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/ReWiz-Worldbuilder-7B 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: 2.57 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/ReWiz-Worldbuilder-7B 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: 16.39 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/ReWiz-Worldbuilder-7B 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: 21.9 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=theprint/ReWiz-Worldbuilder-7B name: Open LLM Leaderboard

---

<img src="https://huggingface.co/theprint/ReWiz-Llama-3.2-3B/resolve/main/ReWiz_banner.png">

Half the data was geared towards better reasoning (EvolKit-20k and reasoning-base-20k), the other half will help to de-censor the model (WizardLM data set).

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:

• theprint/WorldBuilder-7B
• theprint/ReWiz-7B

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: theprint/ReWiz-7B
        layer_range: [0, 32]
      - model: theprint/WorldBuilder-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: theprint/ReWiz-7B
parameters:
  t:
    - filter: self_attn
      value: [0.1, 0.5, 0.3, 0.7, 0.9]
    - filter: mlp
      value: [0.9, 0.5, 0.7, 0.3, 0.1]
    - value: 0.5
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here