README.md

metadata

library_name: transformers
tags:
  - mergekit
  - merge
base_model: []
model-index:
  - name: L3-Stheno-v3.2-12.2B-Instruct
    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: 40.28
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DavidAU/L3-Stheno-v3.2-12.2B-Instruct
          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: 27.37
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DavidAU/L3-Stheno-v3.2-12.2B-Instruct
          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: 4.98
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DavidAU/L3-Stheno-v3.2-12.2B-Instruct
          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: 3.36
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DavidAU/L3-Stheno-v3.2-12.2B-Instruct
          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: 10.31
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DavidAU/L3-Stheno-v3.2-12.2B-Instruct
          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: 26.06
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DavidAU/L3-Stheno-v3.2-12.2B-Instruct
          name: Open LLM Leaderboard

L3-Stheno-v3.2-12.2B-Instruct - Float32

This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats. The source code can also be used directly.

For full information about this model, including:

• Details about this model and its use case(s).
• Context limits
• Special usage notes / settings.
• Any model(s) used to create this model.
• Template(s) used to access/use this model.
• Example generation(s)
• GGUF quants of this model

Please go to:

[ https://huggingface.co/DavidAU/L3-Stheno-v3.2-12.2B-INSTRUCT-ULTRA-F32-GGUF ]

Additional Quants:

Imatrix GGUFs:

[ https://huggingface.co/mradermacher/L3-Stheno-v3.2-12.2B-Instruct-i1-GGUF ]

GGUFS:

[ https://huggingface.co/mradermacher/L3-Stheno-v3.2-12.2B-Instruct-GGUF ]

---

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.

Models Merged

The following models were included in the merge:

• G:/7B/L3-8B-Stheno-v3.2
• G:/7B/Meta-Llama-3-8B-Instruct

Configuration

The following YAML configuration was used to produce this model:

slices:
 - sources:
   - model: G:/7B/Meta-Llama-3-8B-Instruct
     layer_range: [0, 12]
 - sources:
   - model: G:/7B/L3-8B-Stheno-v3.2
     layer_range: [6, 19]
     parameters:
       scale:
         - filter: o_proj
           value: 1
         - filter: down_proj
           value: 1
         - value: 1
 - sources:
   - model: G:/7B/Meta-Llama-3-8B-Instruct
     layer_range: [12, 18]
     parameters:
       scale:
         - filter: o_proj
           value: .5
         - filter: down_proj
           value: .5
         - value: 1
 - sources:
   - model: G:/7B/Meta-Llama-3-8B-Instruct
     layer_range: [18, 25]
     parameters:
       scale:
         - filter: o_proj
           value: .75
         - filter: down_proj
           value: .75
         - value: 1
 - sources:
   - model: G:/7B/L3-8B-Stheno-v3.2
     layer_range: [19, 32]
     parameters:
       scale:
         - filter: o_proj
           value: 1
         - filter: down_proj
           value: 1
         - value: 1
merge_method: passthrough
dtype: float32

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	18.73
IFEval (0-Shot)	40.28
BBH (3-Shot)	27.37
MATH Lvl 5 (4-Shot)	4.98
GPQA (0-shot)	3.36
MuSR (0-shot)	10.31
MMLU-PRO (5-shot)	26.06