README.md

metadata

license: cc-by-nc-4.0
library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - OpenPipe/mistral-ft-optimized-1218
  - macadeliccc/WestLake-7B-v2-laser-truthy-dpo
model-index:
  - name: LaserPipe-7B-SLERP
    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: 71.08
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BryanSwk/LaserPipe-7B-SLERP
          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: 87.89
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BryanSwk/LaserPipe-7B-SLERP
          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: 64.86
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BryanSwk/LaserPipe-7B-SLERP
          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: 65.38
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BryanSwk/LaserPipe-7B-SLERP
          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: 83.35
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BryanSwk/LaserPipe-7B-SLERP
          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: 72.78
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BryanSwk/LaserPipe-7B-SLERP
          name: Open LLM Leaderboard

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

I have provided a .gguf Q4_K_M for cpu inference as well.

This repository serves as a learning experience for myself to experiment with merged models & gguf conversions.

Credits:

• mergekit
• llama.cpp

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• OpenPipe/mistral-ft-optimized-1218
• macadeliccc/WestLake-7B-v2-laser-truthy-dpo

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: OpenPipe/mistral-ft-optimized-1218
        layer_range: [0, 32]
      - model: macadeliccc/WestLake-7B-v2-laser-truthy-dpo
        layer_range: [0, 32]
merge_method: slerp
base_model: OpenPipe/mistral-ft-optimized-1218
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
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	74.22
AI2 Reasoning Challenge (25-Shot)	71.08
HellaSwag (10-Shot)	87.89
MMLU (5-Shot)	64.86
TruthfulQA (0-shot)	65.38
Winogrande (5-shot)	83.35
GSM8k (5-shot)	72.78