Edit model card

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

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
10
Safetensors
Model size
3.82B params
Tensor type
BF16
·
Inference API
Input a message to start chatting with TeeZee/Phi-3-mini-4k-instruct-LASER.
This model can be loaded on Inference API (serverless).

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