Yudi Xue

yudixue's activity

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

New activity in JamAndTeaStudios/DeepSeek-R1-Distill-Qwen-32B-FP8-Dynamic 23 days ago

Fix chat_template crash when assistant message omits the `content` key

#2 opened about 2 months ago by

qgallouedec

updated a model 10 months ago

JamAndTeaStudios/DeepSeek-R1-0528-Qwen3-8B-FP8-Dynamic

Text Generation • 8B • Updated Aug 21, 2025 • 26

published a model about 1 year ago

JamAndTeaStudios/DeepSeek-R1-0528-Qwen3-8B-FP8-Dynamic

Text Generation • 8B • Updated Aug 21, 2025 • 26

updated 2 models about 1 year ago

JamAndTeaStudios/gemma-2-9b-it-FP8-Dynamic

Text Generation • 10B • Updated Apr 22, 2025 • 4

JamAndTeaStudios/gemma-3-12b-it-FP8-Dynamic

Image-Text-to-Text • 13B • Updated Apr 22, 2025 • 4

published a model about 1 year ago

JamAndTeaStudios/gemma-3-12b-it-FP8-Dynamic

Image-Text-to-Text • 13B • Updated Apr 22, 2025 • 4

updated 2 models about 1 year ago

JamAndTeaStudios/Qwen2.5-7B-Instruct-1M-FP8-Dynamic

Text Generation • 8B • Updated Apr 21, 2025 • 2

JamAndTeaStudios/Qwen2.5-14B-Instruct-1M-FP8-Dynamic

Text Generation • 15B • Updated Apr 21, 2025 • 7

updated a model over 1 year ago

yudixue/qwen2.5_3b_instruct_MLA

Text Generation • 3B • Updated Feb 14, 2025 • 6

published a model over 1 year ago

yudixue/qwen2.5_3b_instruct_MLA

Text Generation • 3B • Updated Feb 14, 2025 • 6

updated a collection over 1 year ago

FP8 Deepseek R1 Distilled LLMs for SGLang and vLLM

Collection

Accurate FP8 quantized deepseek R1 distilled models, ready for use with SGLang and vLLM! • 6 items • Updated Jan 29, 2025 • 1

updated 4 models over 1 year ago

JamAndTeaStudios/DeepSeek-R1-Distill-Qwen-32B-FP8-Dynamic

Text Generation • 33B • Updated 23 days ago • 1.35k • 2

JamAndTeaStudios/DeepSeek-R1-Distill-Qwen-14B-FP8-Dynamic

Text Generation • 15B • Updated Jan 29, 2025 • 22 • 1

JamAndTeaStudios/DeepSeek-R1-Distill-Llama-70B-FP8-Dynamic

Text Generation • 71B • Updated Jan 29, 2025 • 4

JamAndTeaStudios/DeepSeek-R1-Distill-Llama-8B-FP8-Dynamic

Text Generation • 8B • Updated Jan 29, 2025 • 10 • 1