README.md

metadata

license: cc-by-nc-4.0
library_name: transformers
tags:
  - mergekit
  - merge
  - alpaca
  - mistral
  - not-for-all-audiences
  - nsfw
model-index:
  - name: IceCaffeLatteRP-7b
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: AI2 Reasoning Challenge (25-Shot)
          type: ai2_arc
          config: ARC-Challenge
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: acc_norm
            value: 69.03
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceCaffeLatteRP-7b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HellaSwag (10-Shot)
          type: hellaswag
          split: validation
          args:
            num_few_shot: 10
        metrics:
          - type: acc_norm
            value: 86.7
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceCaffeLatteRP-7b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU (5-Shot)
          type: cais/mmlu
          config: all
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 64.34
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceCaffeLatteRP-7b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: TruthfulQA (0-shot)
          type: truthful_qa
          config: multiple_choice
          split: validation
          args:
            num_few_shot: 0
        metrics:
          - type: mc2
            value: 61.16
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceCaffeLatteRP-7b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Winogrande (5-shot)
          type: winogrande
          config: winogrande_xl
          split: validation
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 81.29
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceCaffeLatteRP-7b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GSM8k (5-shot)
          type: gsm8k
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 64.06
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceCaffeLatteRP-7b
          name: Open LLM Leaderboard

IceCaffeLatteRP-7b

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

Merge Details

My last merge that I'm using. For feedback ST Discord model topic

• 4.2bpw-exl2

Thx riveRiPH for

• 3.17bpw-exl2
• 4.32bpw-exl2
• 5.32bpw-exl2
• 6.33bpw-exl2
• 8.04bpw-exl2

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• IceLatteRP-7b
• IceMochaccinoRP-7b

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: IceMochaccinoRP-7b
        layer_range: [0, 32]
      - model: IceLatteRP-7b 
        layer_range: [0, 32]

merge_method: slerp
base_model: IceLatteRP-7b 
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5 # fallback for rest of tensors
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	71.10
AI2 Reasoning Challenge (25-Shot)	69.03
HellaSwag (10-Shot)	86.70
MMLU (5-Shot)	64.34
TruthfulQA (0-shot)	61.16
Winogrande (5-shot)	81.29
GSM8k (5-shot)	64.06