README.md

metadata

language:
  - en
  - es
  - ca
license: apache-2.0
tags:
  - FLOR
  - bloom
  - spanish
  - catalan
  - english
datasets:
  - teknium/OpenHermes-2.5
pipeline_tag: text-generation
model-index:
  - name: OpenHermes-2.5-FLOR-6.3B
    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: 33.45
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=xaviviro/OpenHermes-2.5-FLOR-6.3B
          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: 54.53
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=xaviviro/OpenHermes-2.5-FLOR-6.3B
          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: 25.18
            name: accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=xaviviro/OpenHermes-2.5-FLOR-6.3B
          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: 46.12
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=xaviviro/OpenHermes-2.5-FLOR-6.3B
          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: 62.98
            name: accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=xaviviro/OpenHermes-2.5-FLOR-6.3B
          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: 0
            name: accuracy
        source:
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=xaviviro/OpenHermes-2.5-FLOR-6.3B
          name: Open LLM Leaderboard

OpenHermes-2.5-FLOR-6.3B

OpenHermes-2.5-FLOR-6.3B És el resultat de finetunejar el model FLOR-6.3B amb el fantàstic dataset OpenHermes v2.5.

La millor manera d'usar OpenHermes-2.5-FLOR-6.3B és amb el format ChatML

Quantitzats

Podeu trobar el model quantitzat i en format GGUF a OpenHermes-2.5-FLOR-6.3B-GGUF

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	37.04
AI2 Reasoning Challenge (25-Shot)	33.45
HellaSwag (10-Shot)	54.53
MMLU (5-Shot)	25.18
TruthfulQA (0-shot)	46.12
Winogrande (5-shot)	62.98
GSM8k (5-shot)	0.00