vortex-3b-v2 / README.md
Abhaykoul's picture
Adding Evaluation Results
507c26b verified
metadata
language:
  - en
license: other
tags:
  - HelpingAI
  - vortex
datasets:
  - OEvortex/uncensored-vortex
license_name: hsul
license_link: https://huggingface.co/OEvortex/vortex-3b/raw/main/LICENSE.md
pipeline_tag: text-generation
model-index:
  - name: vortex-3b-v2
    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: 39.68
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/vortex-3b-v2
          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: 65.04
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/vortex-3b-v2
          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: 25.09
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/vortex-3b-v2
          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: 33.8
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/vortex-3b-v2
          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: 59.12
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/vortex-3b-v2
          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: 2.05
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=OEvortex/vortex-3b-v2
          name: Open LLM Leaderboard

Vortex 3b Model Overview

Vortex-3b-v2 is an upgraded version of the Vortex-3b model ie. a 2.78 billion parameter causal language model created by OEvortex that was derived from EleutherAI's Pythia-2.8b and trained on 79% of uncensored-vortex dataset

from transformers import pipeline

# Initialize the pipeline
pipe = pipeline("text-generation", model="OEvortex/vortex-3b-v2")

# Use the pipeline
text = "Once upon a time"
generated_text = pipe(text, max_length=100, do_sample=True)[0]['generated_text']

print(generated_text)
# Use a pipeline as a high-level helper
from transformers import pipeline

text = pipeline(model="OEvortex/vortex-3b-v2", torch_dtype=torch.bfloat16, device_map="auto")

res = text("Explain to me the difference between nuclear fission and fusion.")
print(res[0]["text"])

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 37.46
AI2 Reasoning Challenge (25-Shot) 39.68
HellaSwag (10-Shot) 65.04
MMLU (5-Shot) 25.09
TruthfulQA (0-shot) 33.80
Winogrande (5-shot) 59.12
GSM8k (5-shot) 2.05