README.md

metadata

license: cc-by-nc-nd-4.0
tags:
  - dpo
  - merge
  - mergekit
base_model:
  - mistralai/Mixtral-8x7B-Instruct-v0.1
model-index:
  - name: rizla-17
    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: 73.63
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rizla/rizla-17
          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: 89.72
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rizla/rizla-17
          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: 64.4
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rizla/rizla-17
          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: 76.93
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rizla/rizla-17
          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: 87.85
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rizla/rizla-17
          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: 61.49
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=rizla/rizla-17
          name: Open LLM Leaderboard

rizla been cooking while singing

This is an experimental model that I made by merging two 2expmixtrals The mergekitty is a tool that lets me mix and match different models into one big model, keeping all the smarts and skills of the original models. The llama70b is a huge language model that can make words for all kinds of things and ways, based on the GPT-4 thingy.

The merged model has 17 billion parraraameters and was made to run on 8gb of ram minimum in q3KL gguf.

Merge me baby one more time

Sending this contraption out straight to mergeland, wwhheeeeeeeeeeeee LFG 🚀

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	75.67
AI2 Reasoning Challenge (25-Shot)	73.63
HellaSwag (10-Shot)	89.72
MMLU (5-Shot)	64.40
TruthfulQA (0-shot)	76.93
Winogrande (5-shot)	87.85
GSM8k (5-shot)	61.49