Gabriel Wu

lucifer1004's activity

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

New activity in nvidia/GLM-5.3-Flash-NVFP4 15 days ago

fix: declare NextN (MTP) layer 45 as BF16 in quantization ignore lists

1

#11 opened 15 days ago by

lucifer1004

fix: declare NextN (MTP) layer 45 as BF16 in quantization ignore lists

1

#10 opened 16 days ago by

lucifer1004

New activity in nvidia/GLM-5.3-Flash-NVFP4 16 days ago

NextN (MTP) layer stored in BF16 but missing from quantization_config.ignore — speculative decoding fails to load

1

#9 opened 16 days ago by

lucifer1004

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

❤️ 4

1

#6 opened 22 days ago by

jon1012

liked a model over 1 year ago

moonshotai/Kimi-Dev-72B

Text Generation • 73B • Updated Jun 17, 2025 • 6.5k • • 393

liked a Space over 1 year ago

Running

4.06k

The Ultra-Scale Playbook

🌌

4.06k

The ultimate guide to training LLM on large GPU Clusters

liked a dataset over 1 year ago

SakanaAI/AI-CUDA-Engineer-Archive

Viewer • Updated Feb 20, 2025 • 30.6k • 30.8k • 229

liked a dataset over 2 years ago

nyu-visionx/Cambrian-10M

Preview • Updated Jul 8, 2024 • 20.3k • 131

liked 3 models over 2 years ago

deepseek-ai/DeepSeek-Coder-V2-Instruct

Text Generation • 236B • Updated Aug 21, 2024 • 8.32k • 701

bosonai/Higgs-Llama-3-70B

Text Generation • 71B • Updated Aug 20, 2024 • 8.66k • • 229

aiXcoder/aixcoder-7b-base

Text Generation • 7B • Updated Apr 15, 2024 • 588 • 55

liked 2 models almost 3 years ago

microsoft/phi-2

Text Generation • 3B • Updated Dec 8, 2025 • 599k • • 3.52k

mistralai/Mixtral-8x7B-Instruct-v0.1

47B • Updated Jul 24, 2025 • 215k • 4.76k

liked a Space over 3 years ago

Running

Agents

Featured

507

Guanaco Playground Tgi

📊

507

Chat with an AI assistant powered by Guanaco 33B

liked a model over 3 years ago

BlinkDL/rwkv-4-raven

Text Generation • Updated Jun 30, 2023 • 30.1k • 497

updated a model over 3 years ago

lucifer1004/mstm-gnn

Updated Mar 8, 2023

liked a model over 3 years ago

microsoft/beit-large-patch16-224-pt22k

Image Classification • 0.3B • Updated May 8, 2023 • 275 • 3