You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Uploaded model

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Detailed results can be found here

Safetensors

Model size

1.1B params

Tensor type

BF16

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.

Base model

Finetuned

(197)

this model

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

37.200
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

61.320
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

25.700
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

38.720
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

61.250
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

1.900