README.md

metadata

base_model: M4-ai/NeuralReyna-Mini-1.8B-v0.3
datasets:
  - argilla/OpenHermes2.5-dpo-binarized-alpha
  - Locutusque/Hercules-v3.0
inference: false
language:
  - en
license: apache-2.0
model-index:
  - name: NeuralReyna-Mini-1.8B-v0.3
    results:
      - dataset:
          args:
            num_few_shot: 25
          config: ARC-Challenge
          name: AI2 Reasoning Challenge (25-Shot)
          split: test
          type: ai2_arc
        metrics:
          - name: normalized accuracy
            type: acc_norm
            value: 35.58
        source:
          name: Open LLM Leaderboard
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.3
        task:
          name: Text Generation
          type: text-generation
      - dataset:
          args:
            num_few_shot: 10
          name: HellaSwag (10-Shot)
          split: validation
          type: hellaswag
        metrics:
          - name: normalized accuracy
            type: acc_norm
            value: 61.13
        source:
          name: Open LLM Leaderboard
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.3
        task:
          name: Text Generation
          type: text-generation
      - dataset:
          args:
            num_few_shot: 5
          config: all
          name: MMLU (5-Shot)
          split: test
          type: cais/mmlu
        metrics:
          - name: accuracy
            type: acc
            value: 44.22
        source:
          name: Open LLM Leaderboard
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.3
        task:
          name: Text Generation
          type: text-generation
      - dataset:
          args:
            num_few_shot: 0
          config: multiple_choice
          name: TruthfulQA (0-shot)
          split: validation
          type: truthful_qa
        metrics:
          - type: mc2
            value: 41.99
        source:
          name: Open LLM Leaderboard
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.3
        task:
          name: Text Generation
          type: text-generation
      - dataset:
          args:
            num_few_shot: 5
          config: winogrande_xl
          name: Winogrande (5-shot)
          split: validation
          type: winogrande
        metrics:
          - name: accuracy
            type: acc
            value: 60.93
        source:
          name: Open LLM Leaderboard
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.3
        task:
          name: Text Generation
          type: text-generation
      - dataset:
          args:
            num_few_shot: 5
          config: main
          name: GSM8k (5-shot)
          split: test
          type: gsm8k
        metrics:
          - name: accuracy
            type: acc
            value: 6.75
        source:
          name: Open LLM Leaderboard
          url: >-
            https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/NeuralReyna-Mini-1.8B-v0.3
        task:
          name: Text Generation
          type: text-generation
model_creator: M4-ai
model_name: NeuralReyna-Mini-1.8B-v0.3
pipeline_tag: text-generation
quantized_by: afrideva
tags:
  - gguf
  - ggml
  - quantized
  - q2_k
  - q3_k_m
  - q4_k_m
  - q5_k_m
  - q6_k
  - q8_0

M4-ai/NeuralReyna-Mini-1.8B-v0.3-GGUF

Quantized GGUF model files for NeuralReyna-Mini-1.8B-v0.3 from M4-ai

Name	Quant method	Size
neuralreyna-mini-1.8b-v0.3.fp16.gguf	fp16	3.68 GB
neuralreyna-mini-1.8b-v0.3.q2_k.gguf	q2_k	846.57 MB
neuralreyna-mini-1.8b-v0.3.q3_k_m.gguf	q3_k_m	1.02 GB
neuralreyna-mini-1.8b-v0.3.q4_k_m.gguf	q4_k_m	1.22 GB
neuralreyna-mini-1.8b-v0.3.q5_k_m.gguf	q5_k_m	1.38 GB
neuralreyna-mini-1.8b-v0.3.q6_k.gguf	q6_k	1.58 GB
neuralreyna-mini-1.8b-v0.3.q8_0.gguf	q8_0	1.96 GB

Original Model Card:

NeuralReyna-Mini-1.8B-v0.3

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.

Evaluation

Coming soon

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.	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