---
language:
- en
license: apache-2.0
datasets:
- argilla/OpenHermes2.5-dpo-binarized-alpha
- 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
model-index:
- name: NeuralReyna-Mini-1.8B-v0.3
  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: 35.58
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.3
      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/NeuralReyna-Mini-1.8B-v0.3
      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: 44.22
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.3
      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: 41.99
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.3
      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-v0.3
      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: 6.75
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.3
      name: Open LLM Leaderboard
---
# NeuralReyna-Mini-1.8B-v0.3
![Reyna image](https://th.bing.com/th/id/OIG3.8IBxuT77hh6Y_r1DZ6WK?dpr=2.6&pid=ImgDetMain)
# Description
Taken aloobun/Reyna-Mini-1.8B-v0.2 and further fine-tuned it using DPO using the argilla/OpenHermes2.5-dpo-binarized-alpha. 

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

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

# Quants

HQQ - https://huggingface.co/twoxfh/NeuralReyna-Mini-hqq-1.8B-v0.3

# Evaluation
Coming soon

# Contributions

Thanks to @aloobun and @Locutusque for their contributions to this model. 
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_M4-ai__NeuralReyna-Mini-1.8B-v0.3)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |41.77|
|AI2 Reasoning Challenge (25-Shot)|35.58|
|HellaSwag (10-Shot)              |61.13|
|MMLU (5-Shot)                    |44.22|
|TruthfulQA (0-shot)              |41.99|
|Winogrande (5-shot)              |60.93|
|GSM8k (5-shot)                   | 6.75|