Inferact Inc.

Inferact's activity

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

harryleafchen 

submitted a paper to Daily Papers 25 days ago

Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090

Paper • 2608.27370 • Published 30 days ago • 40

ZixiQi 

in Inferact/Kimi-K3-DSpark-Block5 28 days ago

vLLM cannot load this checkpoint: inherited DeepseekV2Config validator rejects num_attention_heads=96

👍 1

1

#1 opened 29 days ago by

Nafeij

Isotr0py 

published a model 28 days ago

Inferact/GLM-5.3-NVFP4

Text Generation • 391B • Updated 28 days ago • 72.3k • 4

harryleafchen 

authored a paper 28 days ago

Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090

Paper • 2608.27370 • Published 30 days ago • 40

Isotr0py 

updated a model 28 days ago

Inferact/GLM-5.3-NVFP4

Text Generation • 391B • Updated 28 days ago • 72.3k • 4

Isotr0py 

published a model about 1 month ago

Inferact/Qwen3.8-Flash-Next-NVFP4

Image-Text-to-Text • 118B • Updated about 1 month ago • 90.2k • 29

Isotr0py 

updated a model about 1 month ago

Inferact/Qwen3.8-Flash-Next-NVFP4

Image-Text-to-Text • 118B • Updated about 1 month ago • 90.2k • 29

ZixiQi 

in Inferact/Kimi-K3-DSpark about 1 month ago

Kimi-K3-DSpark acceptance collapses beyond approximately 128K context on H200

7

#2 opened about 2 months ago by

dhbloo

ZixiQi 

published a model about 1 month ago

Inferact/Kimi-K3-DSpark-Block5

Text Generation • 3B • Updated about 1 month ago • 382

ZixiQi 

updated a model about 1 month ago

Inferact/Kimi-K3-DSpark-Block5

Text Generation • 3B • Updated about 1 month ago • 382

TiezhenWANG 

published 2 models about 1 month ago

Inferact/Qwen3.8-27B-NVFP4

Image-Text-to-Text • 18B • Updated Aug 14 • 1.23M • 19

Inferact/Qwen3.8-27B-MXFP4

Image-Text-to-Text • 18B • Updated Aug 14 • 301 • 4

Isotr0py 

updated a model about 1 month ago

Inferact/Qwen3.8-27B-MXFP4

Image-Text-to-Text • 18B • Updated Aug 14 • 301 • 4

TiezhenWANG 

updated 2 models about 1 month ago

Inferact/Qwen3.8-27B-MXFP4

Image-Text-to-Text • 18B • Updated Aug 14 • 301 • 4

Inferact/Qwen3.8-27B-NVFP4

Image-Text-to-Text • 18B • Updated Aug 14 • 1.23M • 19

Isotr0py 

updated 2 models about 1 month ago

Inferact/Qwen3.8-27B-NVFP4

Image-Text-to-Text • 18B • Updated Aug 14 • 1.23M • 19

Inferact/Qwen3.8-2.4T-A95B-MXFP4

Text Generation • 1.2T • Updated Aug 13 • 525

harryleafchen 

authored 3 papers 10 months ago

CPM: A Large-scale Generative Chinese Pre-trained Language Model

Paper • 2012.00413 • Published Dec 1, 2020

CPM-2: Large-scale Cost-effective Pre-trained Language Models

Paper • 2106.10715 • Published Jun 20, 2021 • 1

PCMind-2.1-Kaiyuan-2B Technical Report

Paper • 2512.07612 • Published Dec 8, 2025 • 2