microsoft
/

Phi-3-mini-4k-instruct

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Resources

View closed (72)

Thanks for Phi 3 mini and your inclusion of MedQA benchmark in your testing!

#95 opened 3 months ago by

KV cahing problem during the inference loop

#94 opened 3 months ago by

Issue with Phi-3 Mini 4K Instruct Response Format

#93 opened 3 months ago by

Is it required to add a BOS token?

#92 opened 3 months ago by

Thanks for sharing this model, I use it in my open source app for synthetic data :)

#91 opened 3 months ago by

phi3 4K vs phi3 4K. dupplcated name on the leaderboard

#89 opened 4 months ago by

Please add more AutoModel Mapping

#88 opened 4 months ago by

phi3 4K vs 128K

#87 opened 4 months ago by

CUDA error when using the code example with pipeline provided on the model page

#86 opened 4 months ago by

Issues with llamacpp/LM studio and ollama

#85 opened 4 months ago by

Model doesn't seem to tokenize new lines in chat template?

#84 opened 4 months ago by

Underreported HumanEval Scores?

#83 opened 4 months ago by

Uploaded GGUF and exl2 as Phi 3.1

#80 opened 4 months ago by

Thanks for the updated version!

#78 opened 4 months ago by

The model stops after generating one new token

#76 opened 4 months ago by

rajiv-data-chef

Create the tokenizer.json properly (with TemplateProcessing included).

#75 opened 4 months ago by

Jetson nano

#74 opened 5 months ago by

fixed generation_args in Sample inference code

#73 opened 5 months ago by

Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.

#72 opened 5 months ago by

tflite convertion

#71 opened 5 months ago by

fine-tuning with structured data set

#68 opened 5 months ago by

fp16 normal weights

#62 opened 6 months ago by

Recent change on the rstrip property on special tokens

#59 opened 6 months ago by

Help with merging LoRA layers back onto Phi3

#55 opened 6 months ago by