MOLAR 10.7B

image/jpeg

Q-LoRA fine-tuned on kyujinpy/Sakura-SOLAR-Instruct with meta-math/MetaMathQA

Adapter model and normal model is available, you can download with both styles.

You must use this prompt style.

### Query: <query>
### Response: <response>

Loss Curve:

image/png

Open LLM Leaderboard Evaluation Results

Detailed results will be found Here

Metric Value
Avg.
ARC (25-shot)
HellaSwag (10-shot)
MMLU (5-shot)
TruthfulQA (0-shot)
Winogrande (5-shot)
GSM8K (5-shot)
Downloads last month
0
Safetensors
Model size
10.7B params
Tensor type
FP16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Q-bert/MOLAR-10.7B

Adapter
(1)
this model

Dataset used to train Q-bert/MOLAR-10.7B