README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - conversational
datasets:
  - Intel/orca_dpo_pairs
  - Locutusque/Hercules-v3.0
inference:
  parameters:
    do_sample: true
    temperature: 0.8
    top_p: 0.95
    top_k: 40
    min_new_tokens: 2
    max_new_tokens: 250
    repetition_penalty: 1.1
widget:
  - text: Hello who are you?
    example_title: Identity
  - text: What can you do?
    example_title: Capabilities
  - text: Create a fastapi endpoint to retrieve the weather given a zip code.
    example_title: Coding
model-index:
  - name: NeuralReyna-Mini-1.8B-v0.2
    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: 37.8
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.2
          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: 60.51
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.2
          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: 45.04
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.2
          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: 37.75
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.2
          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: 60.93
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.2
          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: 27.07
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.2
          name: Open LLM Leaderboard

NeuralReyna-Mini-1.8B-v0.2

Description

Taken aloobun/Reyna-Mini-1.8B-v0.2 and further fine-tuned it using DPO using the Intel/orca_dpo_pairs dataset.

This model has capabilities in coding, math, science, roleplay, and function calling.

This model was trained on OpenAI's ChatML prompt format.

Evaluation

AGIEval:

GPT4ALL:

Tasks	Version	Filter	n-shot	Metric	Value		Stderr
arc_challenge	1	none	0	acc	0.3208	±	0.0136
		none	0	acc_norm	0.3336	±	0.0138
arc_easy	1	none	0	acc	0.6035	±	0.0100
		none	0	acc_norm	0.5833	±	0.0101
boolq	2	none	0	acc	0.6526	±	0.0083
hellaswag	1	none	0	acc	0.4556	±	0.0050
		none	0	acc_norm	0.6076	±	0.0049
openbookqa	1	none	0	acc	0.2600	±	0.0196
		none	0	acc_norm	0.3460	±	0.0213
piqa	1	none	0	acc	0.7236	±	0.0104
		none	0	acc_norm	0.7307	±	0.0104
winogrande	1	none	0	acc	0.6062	±	0.0137

Disclaimer

This model may have overfitted to the DPO training data, and may not perform well.

Contributions

Thanks to @aloobun and @Locutusque for their contributions to this model.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	44.85
AI2 Reasoning Challenge (25-Shot)	37.80
HellaSwag (10-Shot)	60.51
MMLU (5-Shot)	45.04
TruthfulQA (0-shot)	37.75
Winogrande (5-shot)	60.93
GSM8k (5-shot)	27.07