README.md

metadata

language:
  - en
license: cc-by-nc-4.0
pipeline_tag: text-generation
model-index:
  - name: AISquare-Instruct-SOLAR-10.7b-v0.5.32
    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: 61.86
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kimwooglae/AISquare-Instruct-SOLAR-10.7b-v0.5.32
          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: 84.66
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kimwooglae/AISquare-Instruct-SOLAR-10.7b-v0.5.32
          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: 63.13
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kimwooglae/AISquare-Instruct-SOLAR-10.7b-v0.5.32
          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: 51.19
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kimwooglae/AISquare-Instruct-SOLAR-10.7b-v0.5.32
          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: 82.79
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kimwooglae/AISquare-Instruct-SOLAR-10.7b-v0.5.32
          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: 15.09
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kimwooglae/AISquare-Instruct-SOLAR-10.7b-v0.5.32
          name: Open LLM Leaderboard

AISquare-Instruct-SOLAR-10.7b-v0.5.32

Model Details

Developed by Inswave Systems UI Platform Team

Base Model upstage/SOLAR-10.7B-v1.0

Implementation Code

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

repo = "kimwooglae/AISquare-Instruct-SOLAR-10.7b-v0.5.32"
model = AutoModelForCausalLM.from_pretrained(
        repo,
        return_dict=True,
        torch_dtype=torch.float16,
        device_map='auto'
)
tokenizer = AutoTokenizer.from_pretrained(repo)

---

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	59.79
AI2 Reasoning Challenge (25-Shot)	61.86
HellaSwag (10-Shot)	84.66
MMLU (5-Shot)	63.13
TruthfulQA (0-shot)	51.19
Winogrande (5-shot)	82.79
GSM8k (5-shot)	15.09