Resources

View closed (12)

Determinism Challenges with Microsoft Phi-3.5-mini-instruct Across Different GPU Architectures

#28 opened 3 days ago by

HumzaAli

microsoft/Phi-3.5-mini-instruct not working with FA2 due to position_ids

#27 opened 11 days ago by

BramVanroy

Looking forward to the phi 4 model release.

#26 opened 26 days ago by

win10

Hallucinated reply if you prompt same prompt several times. Ollama and phi3.5

#25 opened about 1 month ago by

sepihala

curl run on colab

#23 opened 3 months ago by

sdyy

KeyError: 'phi3' when attempting to train in Oogabooga

#21 opened 3 months ago by

Bob4444

Please support phi-3.5-mini-instruct in llama.cpp

#20 opened 4 months ago by

ThiloteE

Can't install flash_attn package on WSL2

#19 opened 4 months ago by

aytugkaya

How to add new token or special token?

#16 opened 4 months ago by

hahaMiao

Evaluation of Phi-3.5 on long-context BABILong bench

#12 opened 4 months ago by

yurakuratov

Phi3ForCausalLM.forward() got an unexpected keyword argument 'decoder_input_ids'

#11 opened 4 months ago by

Tejarao

tokenizer.model_max_length=2048 in sample_finetune.py

#10 opened 4 months ago by

anakin87

Very safe model!

#6 opened 4 months ago by

SicariusSicariiStuff

Will there be int 4 ONNX DirectML versions in the future?

#5 opened 4 months ago by

PaulTheHuman

My quants and my "silly" version.

#4 opened 4 months ago by

ZeroWw

Why not include MedQA in your benchmarks?

#1 opened 4 months ago by

Hugman2345