README.md

---
license: apache-2.0
library_name: transformers
tags:
- Mixtral 8x7B
- Mistral
- merge
- moe
model-index:
- name: radiantloom-mixtral-8x7b-fusion-dpo
  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: 63.48
      name: normalized accuracy
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Radiantloom/radiantloom-mixtral-8x7b-fusion-dpo
      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: 82.49
      name: normalized accuracy
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Radiantloom/radiantloom-mixtral-8x7b-fusion-dpo
      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: 59.68
      name: accuracy
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Radiantloom/radiantloom-mixtral-8x7b-fusion-dpo
      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: 55.2
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Radiantloom/radiantloom-mixtral-8x7b-fusion-dpo
      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: 76.09
      name: accuracy
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Radiantloom/radiantloom-mixtral-8x7b-fusion-dpo
      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: 50.19
      name: accuracy
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=Radiantloom/radiantloom-mixtral-8x7b-fusion-dpo
      name: Open LLM Leaderboard
---

<img src="https://huggingface.co./aigeek0x0/radiantloom-mixtral-8x7b-fusion/resolve/main/Radiantloom-Mixtral-8x7B-Fusion.png" alt="Radiantloom Mixtral 8X7B Fusion" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>

## Radiantloom Mixtral 8X7B Fusion DPO

This model is a finetuned version of [Radiantloom Mixtral 8X7B Fusion](https://huggingface.co./Radiantloom/radiantloom-mixtral-8x7b-fusion). It was finetuned using Direct Preference Optimization (DPO).
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co./datasets/open-llm-leaderboard/details_Radiantloom__radiantloom-mixtral-8x7b-fusion-dpo)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |64.52|
|AI2 Reasoning Challenge (25-Shot)|63.48|
|HellaSwag (10-Shot)              |82.49|
|MMLU (5-Shot)                    |59.68|
|TruthfulQA (0-shot)              |55.20|
|Winogrande (5-shot)              |76.09|
|GSM8k (5-shot)                   |50.19|