README.md

metadata

license: apache-2.0
model-index:
  - name: Synatra-RP-Orca-2-7b-v0.1
    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: 57.68
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=maywell/Synatra-RP-Orca-2-7b-v0.1
          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: 77.37
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=maywell/Synatra-RP-Orca-2-7b-v0.1
          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: 56.1
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=maywell/Synatra-RP-Orca-2-7b-v0.1
          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: 52.52
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=maywell/Synatra-RP-Orca-2-7b-v0.1
          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: 74.59
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=maywell/Synatra-RP-Orca-2-7b-v0.1
          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: 39.65
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=maywell/Synatra-RP-Orca-2-7b-v0.1
          name: Open LLM Leaderboard

Synatra-RP-Orca-2-7b-v0.1🐧

Support Me

Synatra is a personal project and is being developed with one person's resources. If you like the model, how about a little research funding?

Wanna be a sponser? (Please) Contact me on Telegram AlzarTakkarsen

Model Details

Base Model
microsoft/Orca-2-7b

Model Description It's a test RP sft model. Finetuned from microsoft/Orca-2-7b.

Trained On
A100 80GB * 1

Instruction format Alpaca(Better), ChatML

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	59.65
AI2 Reasoning Challenge (25-Shot)	57.68
HellaSwag (10-Shot)	77.37
MMLU (5-Shot)	56.10
TruthfulQA (0-shot)	52.52
Winogrande (5-shot)	74.59
GSM8k (5-shot)	39.65