Finetuning Vision part for phi 4 mm
#62 opened 3 days ago
by
ritikakap
fix loading processor after save_pretrained with transformers 4.49+
#60 opened 4 days ago
by
katuni4ka

Quantized Fine-Tunning
2
#59 opened 4 days ago
by
dierop
transformers==4.48.2
#58 opened 7 days ago
by
don412
vLLM Deployment Problems
#57 opened 7 days ago
by
surajd

HF format chat template
#56 opened 12 days ago
by
RaushanTurganbay
Convert to HF format
4
#55 opened 13 days ago
by
cyrilvallez

Suggested command fails to start with vLLM 0.8.1
3
#51 opened 13 days ago
by
dinerburger

Decoding strategy of the Phi4 Multimodal
1
#50 opened 17 days ago
by
Zhengyang
how to inference with vllm?
2
#48 opened 20 days ago
by
tomatoChenBM
Fine-tuning on a new language
1
#47 opened 21 days ago
by
amaraa
**[Bug] Fixed NoneType Slicing Error in `modeling_phi4mm.py`: “bad operand type for unary -”**
4
#46 opened 22 days ago
by
TheWW

Fix image embedding logic to be mps-compatible
1
#45 opened 23 days ago
by
DefOs9

Padding of labels bug?
2
#44 opened 24 days ago
by
haukurpj
Experience with Phi-4-Multimodal vs. Whisper-1 for Speech-to-Text
2
#39 opened 26 days ago
by
hdevio
Does the model support beam search for ASR?
6
#31 opened about 1 month ago
by
h9LtLSb
`tokenizer.model` is missing
7
#30 opened about 1 month ago
by
happyme531

Getting Bounding Boxes for Vision
1
#29 opened about 1 month ago
by
sujan2023
how to input a video?
9
#16 opened about 1 month ago
by
maltoseflower
Error during inference with image and text.
8
#12 opened about 1 month ago
by
aarbelle

llama.cpp support when?
10
#7 opened about 1 month ago
by
alanzhuly

How to use it with LM Studio?
6
#3 opened about 1 month ago
by
neokiller62
thanks , how to fine tune?
19
#1 opened about 1 month ago
by
NickyNicky
