lucasjin

lucasjin's activity

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

New activity in RedHatAI/Qwen2.5-VL-72B-Instruct-quantized.w4a16 about 1 month ago

qwen2.5 VL 7B can not be run

#1 opened about 1 month ago by

lucasjin

New activity in THUdyh/Ola-Data about 1 month ago

video data's amount mismatch with the ola paper mentioned

2

#3 opened 4 months ago by

Kyousan

New activity in lucasjin/XCodec2 5 months ago

Create README.md

#1 opened 5 months ago by

MonolithFoundation

New activity in greyzyl/vary_data_600k 5 months ago

如何解压

1

#1 opened 6 months ago by

lololololoki

commented a paper 6 months ago

HiFi-SR: A Unified Generative Transformer-Convolutional Adversarial Network for High-Fidelity Speech Super-Resolution

Paper • 2501.10045 • Published Jan 17 • 9 •

3

New activity in Respair/Tsukasa_Speech 6 months ago

Can u please opensource the right weights?

11

#1 opened 6 months ago by

lucasjin

New activity in hexgrad/Kokoro-82M 6 months ago

Guys, Rust inference of Kokoro!

🔥 3

2

#35 opened 6 months ago by

lucasjin

New activity in CohereLabs/aya-expanse-8b 9 months ago

ValueError: Tokenizer class CohereTokenizer does not exist or is not currently imported.

3

#9 opened 9 months ago by

lucasjin

New activity in OpenGVLab/InternOmni 10 months ago

Multimodal model opensource

👍 5

2

#1 opened 11 months ago by

YangJiassh

New activity in CausalLM/miniG 11 months ago

Does there any tutorial on how to use the multimodal?

3

#8 opened 11 months ago by

lucasjin

New activity in omlab/omchat-v2.0-13B-single-beta_hf 11 months ago

is there any opensource repo for this?

3

#1 opened 11 months ago by

lucasjin

New activity in microsoft/Phi-3.5-MoE-instruct 11 months ago

About training mem usage for moe

👍 1

3

#2 opened 11 months ago by

lucasjin

New activity in google/gemma-2-9b 12 months ago

Fine-tuning Hyperparameters

8

#27 opened about 1 year ago by

tanliboy

New activity in microsoft/Florence-2-large-ft 12 months ago

Chinese very bad

15

#12 opened about 1 year ago by

lucasjin

New activity in nyu-visionx/Cambrian-10M 12 months ago

data_engine image doesn't match question

5

#5 opened about 1 year ago by

NightStar

New activity in microsoft/Florence-2-large about 1 year ago

How to retrain the model with large max length?

➕ 🔥 3

7

#46 opened about 1 year ago by

lucasjin

What does the output coordinate format?

6

#9 opened about 1 year ago by

lucasjin

New activity in microsoft/Florence-2-large-ft about 1 year ago

What is the prompt format for VQA?

4

#13 opened about 1 year ago by

dnhkng

New activity in OpenGVLab/InternVL2-26B about 1 year ago

About the downsample ratio

2

#3 opened about 1 year ago by

lucasjin

New activity in microsoft/Florence-2-large-ft about 1 year ago

Swift now supports inference, training, and deployment of the Florence models.

3

#14 opened about 1 year ago by

hu5enpai