This is OpenLLaMA 3B V2 finetuned on Puffin for 1 epochs.

Prompt template:

### HUMAN:
{prompt}

### RESPONSE:
<leave a newline for the model to answer>

GGML quants available here.
GPTQ quants available here.

Note: Don't expect this model to be good, I was just starting out to finetune. So don't roast me please!

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Detailed results can be found here

Safetensors

Model size

3.43B params

Tensor type

F32

FP16

Dataset used to train acrastt/Griffin-3B

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

41.810
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

72.300
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

26.360
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

38.330
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

67.010
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

0.990