TeeZee
/

Phi-3-mini-4k-instruct-LASER

Text Generation

Inference Endpoints

Model card Files Files and versions Community

Edit model card

Phi-3-mini-4k-instruct-LASER

model used: microsoft/Phi-3-mini-4k-instruct
LASER scripts used: rmt_laser.py,rmt_laser_snr.py,rmt_laser_snr_math.py from laserRMT

Results

perplexity is reduced comparing to base model, waiting for HF eval results - due to trust_remote_code=True it won't happen soon.

Downloads last month: 3

Safetensors

Model size

3.82B params

Tensor type

BF16

·

Collection including TeeZee/Phi-3-mini-4k-instruct-LASER

LASERS

Fun with LASERS (https://github.com/cognitivecomputations/laserRMT) • 2 items • Updated 23 days ago