metadata

language:
  - en
license: other
library_name: transformers
datasets:
  - Open-Orca/SlimOrca
  - m-a-p/Code-Feedback
  - MaziyarPanahi/WizardLM_evol_instruct_V2_196k
  - camel-ai/math
  - camel-ai/physics
  - camel-ai/biology
  - camel-ai/chemistry
  - LDJnr/Capybara
  - jondurbin/airoboros-3.2
  - microsoft/orca-math-word-problems-200k
inference:
  parameters:
    do_sample: true
    temperature: 0.8
    top_p: 0.95
    top_k: 40
    max_new_tokens: 250
    repetition_penalty: 1.1
model-index:
  - name: Orca-2.0-Tau-1.8B
    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: 37.12
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/Orca-2.0-Tau-1.8B
          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: 61.13
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/Orca-2.0-Tau-1.8B
          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: 45.27
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/Orca-2.0-Tau-1.8B
          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: 39.1
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/Orca-2.0-Tau-1.8B
          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: 59.59
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/Orca-2.0-Tau-1.8B
          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: 28.96
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/Orca-2.0-Tau-1.8B
          name: Open LLM Leaderboard

Orca-2.0-Tau-1.8B

We fine-tuned tau-1.8B on a high quality mix for general-purpose assistants. A DPO version of this will be released soon. We use the ChatML prompt format.

Model Details

Model Description

This model has capabilities in math, coding, writing, and more. We fine-tuned it using a high quality mix for general-purpose assistants.

Developed by: M4-ai
Language(s) (NLP): English and maybe Chinese
License: tongyi-qianwen license
Finetuned from model: tau-1.8B

Uses

General purpose assistant, question answering, chain-of-thought, etc..

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

Evaluation

Coming soon

Training Details

Training Data

Open-Orca/SlimOrca
m-a-p/Code-Feedback
MaziyarPanahi/WizardLM_evol_instruct_V2_196k
camel-ai/math
camel-ai/physics
camel-ai/biology
camel-ai/chemistry
LDJnr/Capybara
jondurbin/airoboros-3.2
microsoft/orca-math-word-problems-200k

Evaluations

Tasks	Version	Filter	Metric	Value		Stderr
agieval_nous	N/A	none	acc	0.2537	±	0.0086
		none	acc_norm	0.2474	±	0.0085
- agieval_aqua_rat	1	none	acc	0.2283	±	0.0264
		none	acc_norm	0.2441	±	0.0270
- agieval_logiqa_en	1	none	acc	0.2750	±	0.0175
		none	acc_norm	0.3164	±	0.0182
- agieval_lsat_ar	1	none	acc	0.2087	±	0.0269
		none	acc_norm	0.1739	±	0.0250
- agieval_lsat_lr	1	none	acc	0.1843	±	0.0172
		none	acc_norm	0.2353	±	0.0188
- agieval_lsat_rc	1	none	acc	0.2602	±	0.0268
		none	acc_norm	0.1784	±	0.0234
- agieval_sat_en	1	none	acc	0.3544	±	0.0334
		none	acc_norm	0.2961	±	0.0319
- agieval_sat_en_without_passage	1	none	acc	0.3107	±	0.0323
		none	acc_norm	0.2282	±	0.0293
- agieval_sat_math	1	none	acc	0.2727	±	0.0301
		none	acc_norm	0.2091	±	0.0275
truthfulqa_mc2	2	none	acc	0.3923	±	0.0139

Training Hyperparameters

Training regime: bf16 non-mixed precision

Technical Specifications

Hardware

We used 8 Kaggle TPUs, and we trained at a global batch size of 128 and sequence length of 2048.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	45.20
AI2 Reasoning Challenge (25-Shot)	37.12
HellaSwag (10-Shot)	61.13
MMLU (5-Shot)	45.27
TruthfulQA (0-shot)	39.10
Winogrande (5-shot)	59.59
GSM8k (5-shot)	28.96