microsoft
/

Phi-3-mini-128k-instruct

Text Generation

Inference Endpoints

Model card Files Files and versions Community

Resources

View closed (48)

Irrelvant response

#64 opened 2 days ago by

fix: update tokenizer config to support `add_generation_prompt=True` and clarify content

#63 opened 4 days ago by

Flash attention with 14k tokens gets obscure results

#62 opened 5 days ago by

Using item() makes torch.export not possible

#61 opened 5 days ago by

Is there a plan to release the pretrained base model for Phi-3?

#60 opened 6 days ago by

About Transformers version

#58 opened 8 days ago by

Get target_modules

#56 opened 13 days ago by

Phi-3 instruct model continuously repeating the answer

#55 opened 13 days ago by

Model can't stop from explaining itself

#53 opened 13 days ago by

model destroyed by deleting tokens?

#52 opened 13 days ago by

Cannot deploy Phi-3-mini-4k-instruct model on AWS Sagemaker

#51 opened 13 days ago by

Pipeline tokenizer does not get initialized when loading from string

#50 opened 13 days ago by

clarification on the usage of `short_factor` and `long_factor`?

#49 opened 15 days ago by

J22

Probably Memory Leak issue？

#46 opened 16 days ago by

sentiment analysis and friendly behavior

#35 opened 20 days ago by

gguf

#24 opened 21 days ago by