Shulin Yang

Prophet000's activity

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

updated 2 collections 8 days ago

TeleOCR

Collection

TeleOCR parses scans, PDFs and photos, supporting complex layouts, tables, formulas and charts. OmniDocBench V1.6 (96.87) and Wild-OmniDocBenc(88.53). • 1 item • Updated 8 days ago • 1

Xing4.0-29B-A4B

Collection

Native 256K context (expandable to 512K). 4-bit quant ~15GB VRAM, local run on RTX3090/4090. Scores 75.0 on SWE-bench Verified, 93.52 on SuperCLUE. • 3 items • Updated 8 days ago • 2

upvoted a collection 8 days ago

Xing4.0-29B-A4B

Collection

Native 256K context (expandable to 512K). 4-bit quant ~15GB VRAM, local run on RTX3090/4090. Scores 75.0 on SWE-bench Verified, 93.52 on SuperCLUE. • 3 items • Updated 8 days ago • 2

New activity in XingChen-AGI/Xing4.0-29B-A4B 13 days ago

training data knowledge cutoff

1

#10 opened 15 days ago by

khtsly

New activity in Venastine-Research/Xing4.0-29B-A4B-GGUF 14 days ago

Which tier are you actually running day to day?

1

#1 opened 14 days ago by

Prophet000

liked a model 14 days ago

vincespeed/Xing4.0-29B-A4B-APEX-GGUF

Text Generation • 31B • Updated 16 days ago • 2.95k • 5

New activity in vincespeed/Xing4.0-29B-A4B-APEX-GGUF 14 days ago

Question about the tier naming in Apex Quant

1

#1 opened 14 days ago by

Prophet000

New activity in kingjones777/quant-lab 14 days ago

Question on the AMD/ROCm path for Xing4.0

1

#1 opened 14 days ago by

Prophet000

liked a Space 14 days ago

Running

1

KingJones Quant Lab

🔧

1

ROCmFP4 & NVFP4 quants for Strix Halo — measured

New activity in XingChen-AGI/Xing4.0-29B-A4B 15 days ago

Minimum number of A100/H100 GPUs to serve Xing4.0-29B-A4B at full 256K context?

2

#9 opened 16 days ago by

rtudriny

wen Xing5.0?

🚀 2

1

#4 opened 16 days ago by

21g

Questions on safety alignment approach

1

#7 opened 16 days ago by

mavis8368

New activity in XingChen-AGI/Xing4.0-29B-A4B-GGUF 15 days ago

Chinese

👀 1

2

#3 opened 16 days ago by

apathy-exe

New activity in XingChen-AGI/Xing4.0-29B-A4B 15 days ago

On par with Qwen3.6 35B for thinking mode; slightly weaker without thinking. Advice?

1

#5 opened 16 days ago by

springbarley

Version of vLLM/SGLang

3

#3 opened 16 days ago by

hahajinbu

文本输出质量比同等规模的Qwen好

1

#1 opened 18 days ago by

chinanet-v1

liked 2 models 16 days ago

HITSZ-TMG/Xing4.0-29B-A4B-OR-SFT

Text Generation • 31B • Updated 16 days ago • 303 • 2

HITSZ-TMG/Xing4.0-29B-A4B-Finance-SFT

Text Generation • 31B • Updated 16 days ago • 405 • 3