README.md

metadata

license: apache-2.0
tags:
  - moe
  - frankenmoe
  - merge
  - mergekit
  - lazymergekit
  - flemmingmiguel/MBX-7B-v3
  - Kukedlc/NeuTrixOmniBe-7B-model-remix
  - PetroGPT/WestSeverus-7B-DPO
  - vanillaOVO/supermario_v4
  - TensorBlock
  - GGUF
base_model: jsfs11/MixtureofMerges-MoE-4x7b-v4
model-index:
  - name: MixtureofMerges-MoE-4x7b-v4
    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: 72.53
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jsfs11/MixtureofMerges-MoE-4x7b-v4
          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: 88.85
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jsfs11/MixtureofMerges-MoE-4x7b-v4
          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: 64.53
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jsfs11/MixtureofMerges-MoE-4x7b-v4
          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: 75.3
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jsfs11/MixtureofMerges-MoE-4x7b-v4
          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: 84.85
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jsfs11/MixtureofMerges-MoE-4x7b-v4
          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: 71.34
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jsfs11/MixtureofMerges-MoE-4x7b-v4
          name: Open LLM Leaderboard

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

jsfs11/MixtureofMerges-MoE-4x7b-v4 - GGUF

This repo contains GGUF format model files for jsfs11/MixtureofMerges-MoE-4x7b-v4.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Prompt template

Model file specification

Filename	Quant type	File Size	Description
MixtureofMerges-MoE-4x7b-v4-Q2_K.gguf	Q2_K	8.236 GB	smallest, significant quality loss - not recommended for most purposes
MixtureofMerges-MoE-4x7b-v4-Q3_K_S.gguf	Q3_K_S	9.717 GB	very small, high quality loss
MixtureofMerges-MoE-4x7b-v4-Q3_K_M.gguf	Q3_K_M	10.785 GB	very small, high quality loss
MixtureofMerges-MoE-4x7b-v4-Q3_K_L.gguf	Q3_K_L	11.683 GB	small, substantial quality loss
MixtureofMerges-MoE-4x7b-v4-Q4_0.gguf	Q4_0	12.688 GB	legacy; small, very high quality loss - prefer using Q3_K_M
MixtureofMerges-MoE-4x7b-v4-Q4_K_S.gguf	Q4_K_S	12.799 GB	small, greater quality loss
MixtureofMerges-MoE-4x7b-v4-Q4_K_M.gguf	Q4_K_M	13.607 GB	medium, balanced quality - recommended
MixtureofMerges-MoE-4x7b-v4-Q5_0.gguf	Q5_0	15.485 GB	legacy; medium, balanced quality - prefer using Q4_K_M
MixtureofMerges-MoE-4x7b-v4-Q5_K_S.gguf	Q5_K_S	15.485 GB	large, low quality loss - recommended
MixtureofMerges-MoE-4x7b-v4-Q5_K_M.gguf	Q5_K_M	15.958 GB	large, very low quality loss - recommended
MixtureofMerges-MoE-4x7b-v4-Q6_K.gguf	Q6_K	18.456 GB	very large, extremely low quality loss
MixtureofMerges-MoE-4x7b-v4-Q8_0.gguf	Q8_0	23.904 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/MixtureofMerges-MoE-4x7b-v4-GGUF --include "MixtureofMerges-MoE-4x7b-v4-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/MixtureofMerges-MoE-4x7b-v4-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'