README.md

metadata

license: cc-by-4.0
tags:
  - merge
  - moe
model-index:
  - name: Open_Gpt4_8x7B
    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: 69.28
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rombodawg/Open_Gpt4_8x7B
          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: 86.77
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rombodawg/Open_Gpt4_8x7B
          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: 71.2
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rombodawg/Open_Gpt4_8x7B
          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: 70.39
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rombodawg/Open_Gpt4_8x7B
          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: 81.77
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rombodawg/Open_Gpt4_8x7B
          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: 59.21
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rombodawg/Open_Gpt4_8x7B
          name: Open LLM Leaderboard

Open_Gpt4 cc

---

VERSION 0.2 OUT NOW:

Fp16:

• https://huggingface.co/rombodawg/Open_Gpt4_8x7B_v0.2

q8_0.gguf:

• https://huggingface.co/rombodawg/Open_Gpt4_8x7B_v0.2_q8_0_gguf

---

This model is a TIES merger of notux-8x7b-v1 and UNAversal-8x7B-v1beta with MixtralOrochi8x7B being the Base model.

I was very impressed with MixtralOrochi8x7B performance and multifaceted usecases as it is already a merger of many usefull Mixtral models such as Mixtral instruct,

Noromaid-v0.1-mixtral, openbuddy-mixtral and possibly other models that were not named. My goal was to expand the models capabilities and make it even more useful of a model, maybe even competitive with closed source models like Gpt-4. But for that more testing is required. I hope the community can help me determine if its deserving of its name. 😊

Base model:

• https://huggingface.co/smelborp/MixtralOrochi8x7B

Merged models:

• https://huggingface.co/fblgit/UNAversal-8x7B-v1beta

• https://huggingface.co/argilla/notux-8x7b-v1

Instruct template: Alpaca

Merger config:

models:
  - model: notux-8x7b-v1
    parameters:
      density: .5
      weight: 1
  - model: UNAversal-8x7B-v1beta
    parameters:
      density: .5
      weight: 1


merge_method: ties
base_model: MixtralOrochi8x7B
parameters:
  normalize: true
  int8_mask: true
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	73.10
AI2 Reasoning Challenge (25-Shot)	69.28
HellaSwag (10-Shot)	86.77
MMLU (5-Shot)	71.20
TruthfulQA (0-shot)	70.39
Winogrande (5-shot)	81.77
GSM8k (5-shot)	59.21