Jonathan Schemoul

jon1012's activity

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

updated a model 1 day ago

LibertAIDAI/MiMo-V2.6-Flash-MOPD-NVFP4

Image-Text-to-Text • 159B • Updated 1 day ago • 25

published a model 1 day ago

LibertAIDAI/MiMo-V2.6-Flash-MOPD-NVFP4

Image-Text-to-Text • 159B • Updated 1 day ago • 25

updated a model 2 days ago

LibertAIDAI/deem-0.6-v1

0.6B • Updated 2 days ago • 17

published a model 2 days ago

LibertAIDAI/deem-0.6-v1

0.6B • Updated 2 days ago • 17

updated a model 4 days ago

LibertAIDAI/deem-0.8-v1

0.8B • Updated 4 days ago • 55 • 1

published a model 5 days ago

LibertAIDAI/deem-0.8-v1

0.8B • Updated 4 days ago • 55 • 1

updated a model 5 days ago

LibertAIDAI/deem-9b-v1

9B • Updated 5 days ago • 45 • 3

published a model 5 days ago

LibertAIDAI/deem-9b-v1

9B • Updated 5 days ago • 45 • 3

updated a model 15 days ago

LibertAIDAI/DeepSeek-V4.1-Flash-REAP-256E

Image-Text-to-Text • Updated 15 days ago • 409 • 6

published a model 18 days ago

LibertAIDAI/DeepSeek-V4.1-Flash-REAP-256E

Image-Text-to-Text • Updated 15 days ago • 409 • 6

updated a model 18 days ago

LibertAIDAI/DeepSeek-V4.1-Flash-REAP-272E

Image-Text-to-Text • Updated 18 days ago • 133 • 1

published a model 18 days ago

LibertAIDAI/DeepSeek-V4.1-Flash-REAP-272E

Image-Text-to-Text • Updated 18 days ago • 133 • 1

New activity in nvidia/GLM-5.3-Flash-NVFP4 18 days ago

ignore / exclude_modules omits the MTP layer (45): checkpoint fails to load with speculative decoding

❤️ 4

1

#6 opened 18 days ago by

jon1012

New activity in LibertAIDAI/DeepSeek-V4.1-Flash-NVFP4 19 days ago

Thank you so much for your excellent job!!!!

1

#1 opened 19 days ago by

nakululusatuva

updated a model 19 days ago

LibertAIDAI/DeepSeek-V4.1-Flash-NVFP4

Image-Text-to-Text • 386B • Updated 19 days ago • 1.05k • 13

published a model 19 days ago

LibertAIDAI/DeepSeek-V4.1-Flash-NVFP4

Image-Text-to-Text • 386B • Updated 19 days ago • 1.05k • 13

updated a model 21 days ago

LibertAIDAI/GLM-5.3-Flash-Uncensored-Prefill-Topup

Updated 21 days ago

published a model 21 days ago

LibertAIDAI/GLM-5.3-Flash-Uncensored-Prefill-Topup

Updated 21 days ago

New activity in LibertAIDAI/GLM-5.3-Flash-NVFP4 29 days ago

B200 VLLM:glm53-flash

5

#2 opened about 1 month ago by

corgito

The model's single-inference speed measured on two DGX systems is only 16 tokens/s, which does not meet productivity requirements.

1

#9 opened 29 days ago by

SAJDOQPDPS