README.md · bartowski/Magic-Dolphin-7b-exl2 at main

metadata

license: apache-2.0
base_model:
  - cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
  - Locutusque/Hyperion-1.5-Mistral-7B
  - ibm/merlinite-7b
library_name: transformers
tags:
  - mergekit
  - merge
  - code
model-index:
  - name: Magic-Dolphin-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: 65.78
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Magic-Dolphin-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: 85.61
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Magic-Dolphin-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: 64.64
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Magic-Dolphin-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: 58.01
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Magic-Dolphin-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: 79.64
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Magic-Dolphin-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: 51.18
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Magic-Dolphin-7b
          name: Open LLM Leaderboard
quantized_by: bartowski
pipeline_tag: text-generation

Exllama v2 Quantizations of Magic-Dolphin-7b

Using turboderp's ExLlamaV2 v0.0.14 for quantization.

The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)

Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.

Original model: https://huggingface.co/InferenceIllusionist/Magic-Dolphin-7b

Branch	Bits	lm_head bits	VRAM (4k)	VRAM (16k)	VRAM (32k)	Description
8_0	8.0	8.0	8.4 GB	9.8 GB	11.8 GB	Maximum quality that ExLlamaV2 can produce, near unquantized performance.
6_5	6.5	8.0	7.2 GB	8.6 GB	10.6 GB	Very similar to 8.0, good tradeoff of size vs performance, recommended.
5_0	5.0	6.0	6.0 GB	7.4 GB	9.4 GB	Slightly lower quality vs 6.5, but usable on 8GB cards.
4_25	4.25	6.0	5.3 GB	6.7 GB	8.7 GB	GPTQ equivalent bits per weight, slightly higher quality.
3_5	3.5	6.0	4.7 GB	6.1 GB	8.1 GB	Lower quality, only use if you have to.

Download instructions

With git:

git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Magic-Dolphin-7b-exl2 Magic-Dolphin-7b-exl2-6_5

With huggingface hub (credit to TheBloke for instructions):

pip3 install huggingface-hub

To download the main (only useful if you only care about measurement.json) branch to a folder called Magic-Dolphin-7b-exl2:

mkdir Magic-Dolphin-7b-exl2
huggingface-cli download bartowski/Magic-Dolphin-7b-exl2 --local-dir Magic-Dolphin-7b-exl2 --local-dir-use-symlinks False

To download from a different branch, add the --revision parameter:

Linux:

mkdir Magic-Dolphin-7b-exl2-6_5
huggingface-cli download bartowski/Magic-Dolphin-7b-exl2 --revision 6_5 --local-dir Magic-Dolphin-7b-exl2-6_5 --local-dir-use-symlinks False

Windows (which apparently doesn't like _ in folders sometimes?):

mkdir Magic-Dolphin-7b-exl2-6.5
huggingface-cli download bartowski/Magic-Dolphin-7b-exl2 --revision 6_5 --local-dir Magic-Dolphin-7b-exl2-6.5 --local-dir-use-symlinks False

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski