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

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

Original Model Card:

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.

Coming soon

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

Detailed results can be found here

GGUF

Model size

1.84B params

Architecture

qwen2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Base model

Quantized

(3)

this model

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

35.580
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

61.130
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

44.220
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

41.990
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

60.930
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

6.750