Microsoft

microsoft's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Articles

Yif29 

in microsoft/LLM2CLIP-Llama3.1-8B-siglip2-so400m-patch14-224 about 11 hours ago

Any rough estimate on when the model might be open-sourced?

1

#1 opened about 14 hours ago by

RitaR229

nguyenbh 

in microsoft/Phi-4-multimodal-instruct about 14 hours ago

How to use it with LM Studio?

6

#3 opened 15 days ago by

neokiller62

Detected version 0.0.0. Error: FlashAttention2

3

#43 opened 1 day ago by

the1Domo

Error during inference with image and text.

5

#12 opened 14 days ago by

aarbelle

I am quite late, but...

1

#27 opened 8 days ago by

FalconNet

fepegar 

in microsoft/maira-2 1 day ago

Request: DOI

#15 opened 7 days ago by

yusrakpln

freewym 

in microsoft/Phi-4-multimodal-instruct 1 day ago

Does the model support beam search for ASR?

6

#31 opened 8 days ago by

h9LtLSb

gargamit 

in microsoft/Phi-4-multimodal-instruct 1 day ago

fixes the asserion error when num_beams > 1

#42 opened 1 day ago by

freewym

freewym 

in microsoft/Phi-4-multimodal-instruct 1 day ago

fixes the asserion error when num_beams > 1

#42 opened 1 day ago by

freewym

nguyenbh 

in microsoft/Phi-4-multimodal-instruct 2 days ago

Demo inference code running error

5

#23 opened 11 days ago by

DrNicefellow

Can I use DeepSpeed with the vision fine-tuning code?

1

#35 opened 6 days ago by

GoGiants1

phi

#41 opened 2 days ago by

smohdy

nguyenbh 

updated a model 2 days ago

microsoft/Phi-4-multimodal-instruct

Automatic Speech Recognition • Updated 1 day ago • 472k • 1.13k

nguyenbh 

in microsoft/Phi-4-multimodal-instruct 2 days ago

Add Appendix B: Fine-tuning Korean speech

#40 opened 3 days ago by

daekeun-ml

Yif29 

updated a collection 2 days ago

LLM2CLIP

Collection

LLM2CLIP makes SOTA pretrained CLIP modal more SOTA ever. • 11 items • Updated 2 days ago • 55

Yif29 

published a model 2 days ago

microsoft/LLM2CLIP-Llama3.1-8B-siglip2-so400m-patch14-224

Updated 2 days ago • 2

xutan 

authored 4 papers 2 days ago

CLaMP 2: Multimodal Music Information Retrieval Across 101 Languages Using Large Language Models

Paper • 2410.13267 • Published Oct 17, 2024 • 1

Memories are One-to-Many Mapping Alleviators in Talking Face Generation

Paper • 2212.05005 • Published Dec 9, 2022

DAE-Talker: High Fidelity Speech-Driven Talking Face Generation with Diffusion Autoencoder

Paper • 2303.17550 • Published Mar 30, 2023

Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis

Paper • 2502.04128 • Published Feb 6 • 25