README.md

metadata

base_model: Sakalti/tara-3.8B
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl
  - sft
license: mit
license_link: https://huggingface.co/microsoft/Phi-3.5-mini-instruct/resolve/main/LICENSE
language:
  - en
  - ja
library_name: transformers
inference: true
datasets:
  - llm-jp/oasst2-33k-ja
pipeline_tag: text-generation
widget:
  - messages:
      - role: user
        content: こんにちは！
  - messages:
      - role: user
        content: ドラゴンフルーツは何科ですか？
  - messages:
      - role: user
        content: hello!
  - messages:
      - role: user
        content: مرحبًا
model-index:
  - name: Tara-3.8B-v1.1
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: IFEval (0-Shot)
          type: wis-k/instruction-following-eval
          split: train
          args:
            num_few_shot: 0
        metrics:
          - type: inst_level_strict_acc and prompt_level_strict_acc
            value: 40.62
            name: averaged accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Sakalti%2FTara-3.8B-v1.1
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BBH (3-Shot)
          type: SaylorTwift/bbh
          split: test
          args:
            num_few_shot: 3
        metrics:
          - type: acc_norm
            value: 28.91
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Sakalti%2FTara-3.8B-v1.1
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MATH Lvl 5 (4-Shot)
          type: lighteval/MATH-Hard
          split: test
          args:
            num_few_shot: 4
        metrics:
          - type: exact_match
            value: 10.95
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Sakalti%2FTara-3.8B-v1.1
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GPQA (0-shot)
          type: Idavidrein/gpqa
          split: train
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 5.93
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Sakalti%2FTara-3.8B-v1.1
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MuSR (0-shot)
          type: TAUR-Lab/MuSR
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 19.44
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Sakalti%2FTara-3.8B-v1.1
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU-PRO (5-shot)
          type: TIGER-Lab/MMLU-Pro
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 25.35
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=Sakalti%2FTara-3.8B-v1.1
          name: Open LLM Leaderboard

Uploaded model

• Developed by: Sakalti
• License: apache-2.0
• Finetuned from model : Sakalti/tara-3.8B

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here! Summarized results can be found here!

Metric	Value (%)
Average	21.87
IFEval (0-Shot)	40.62
BBH (3-Shot)	28.91
MATH Lvl 5 (4-Shot)	10.95
GPQA (0-shot)	5.93
MuSR (0-shot)	19.44
MMLU-PRO (5-shot)	25.35