Resources

View closed (43)

Fine tuning the LLM backbone

#76 opened 4 days ago by

antogrk

transformers-4.50 or higher

👍 1

#75 opened 15 days ago by

mqpham

temp_len: 5217, output_imgs[-1].shape[1]: 5233

#74 opened 25 days ago by

HERIUN

Error when loading audio processor saved with processor.save_pretrained(path_to_dir), and num_logits_to_keep wrong init value

#73 opened about 1 month ago by

YaelAiola

When yhou support an arabic audio?

#72 opened about 1 month ago by

oalhamawi2023

cannot import name 'SlidingWindowCache' from 'transformers.cache_utils'

#71 opened about 1 month ago by

alighabusaleh

Convert to HF format

#70 opened about 2 months ago by

cyrilvallez

Inference with an external LM?

#69 opened about 2 months ago by

agonzalezd

Phi4 output gibberish

#68 opened about 2 months ago by

surajd

Error when loading model quantized with BitsAndBytesConfig for inference

🚀 1

#67 opened about 2 months ago by

deathknight0

Speech to Vision?

#66 opened about 2 months ago by

ifire

DDP error when multi-gpu finetuning with speech encoder parameters unfrozen

#63 opened about 2 months ago by

rumourscape

Finetuning Vision part for phi 4 mm

#62 opened 2 months ago by

ritikakap

fix loading processor after save_pretrained with transformers 4.49+

#60 opened 2 months ago by

katuni4ka

Quantized Fine-Tunning

🚀 2

#59 opened 2 months ago by

dierop

transformers==4.48.2

#58 opened 2 months ago by

don412

vLLM Deployment Problems

➕ 7

#57 opened 2 months ago by

surajd

Suggested command fails to start with vLLM 0.8.1

#51 opened 2 months ago by

dinerburger

Decoding strategy of the Phi4 Multimodal

#50 opened 3 months ago by

Zhengyang

how to inference with vllm?

#48 opened 3 months ago by

tomatoChenBM

Fine-tuning on a new language

#47 opened 3 months ago by

amaraa

[Bug] Fixed NoneType Slicing Error in `modeling_phi4mm.py`: “bad operand type for unary -”

🔥 👍 11

#46 opened 3 months ago by

TheWW

Fix image embedding logic to be mps-compatible

#45 opened 3 months ago by

DefOs9

Padding of labels bug?

#44 opened 3 months ago by

haukurpj

Experience with Phi-4-Multimodal vs. Whisper-1 for Speech-to-Text

#39 opened 3 months ago by

hdevio

Does the model support beam search for ASR?

👍 1

#31 opened 3 months ago by

h9LtLSb

`tokenizer.model` is missing

#30 opened 3 months ago by

happyme531

Getting Bounding Boxes for Vision

#29 opened 3 months ago by

sujan2023

how to input a video?

#16 opened 3 months ago by

maltoseflower

Error during inference with image and text.

➕ 3

#12 opened 3 months ago by

aarbelle

llama.cpp support when?

❤️ 1

#7 opened 3 months ago by

alanzhuly

How to use it with LM Studio?

#3 opened 3 months ago by

neokiller62

thanks , how to fine tune?

#1 opened 3 months ago by

NickyNicky