metadata

language:
  - en
license: apache-2.0
library_name: transformers
tags:
  - moe
model-index:
  - name: Maixtchup-4x7b
    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: 62.54
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaitchup/Maixtchup-4x7b
          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: 83.83
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaitchup/Maixtchup-4x7b
          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: 61.28
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaitchup/Maixtchup-4x7b
          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: 56.13
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaitchup/Maixtchup-4x7b
          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: 76.01
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaitchup/Maixtchup-4x7b
          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: 54.81
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaitchup/Maixtchup-4x7b
          name: Open LLM Leaderboard

Model Card for Model ID

This is a mixture of experts created with mergekit and based on mistralai/Mistral-7B-v0.1.

Model Details

Model Description

Developed by: The Kaitchup
Model type: Causal
Language(s) (NLP): English
License: Apache 2.0

Model Sources

Created using mergekit with the following configuration:

base_model: mistralai/Mistral-7B-Instruct-v0.2
dtype: float16
gate_mode: cheap_embed
experts:
  - source_model: HuggingFaceH4/zephyr-7b-beta
    positive_prompts: ["You are an helpful general-pupose assistant."]
  - source_model: mistralai/Mistral-7B-Instruct-v0.2
    positive_prompts: ["You are helpful assistant."]
  - source_model: teknium/OpenHermes-2.5-Mistral-7B
    positive_prompts: ["You are helpful a coding assistant."]
  - source_model: meta-math/MetaMath-Mistral-7B
    positive_prompts: ["You are an assistant good at math."]

The method and code used to quantize the model is explained here: Maixtchup: Make Your Own Mixture of Experts with Mergekit

Uses

This model is pre-trained and not fine-tuned. You may fine-tune it with PEFT using adapters.

Model Card Contact

The Kaitchup

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	65.77
AI2 Reasoning Challenge (25-Shot)	62.54
HellaSwag (10-Shot)	83.83
MMLU (5-Shot)	61.28
TruthfulQA (0-shot)	56.13
Winogrande (5-shot)	76.01
GSM8k (5-shot)	54.81