Hebangwen

hebangwen's activity

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

New activity in zai-org/GLM-5.1 7 days ago

GLM5.1角色问题-重要

9

#17 opened 7 days ago by

liuyt6515

New activity in Qwen/Qwen3.5-35B-A3B about 1 month ago

RIP

🤝 10

2

#44 opened about 1 month ago by

kabachuha

New activity in Qwen/Qwen3.5-9B about 1 month ago

DGX SPARK VLLM RESULTS

👍 2

2

#4 opened about 2 months ago by

RGMC98

New activity in meituan-longcat/LongCat-Flash-Lite about 2 months ago

llama.cpp support please.

❤️ 17

3

#1 opened 3 months ago by

rosspanda0

New activity in LiquidAI/LFM2.5-1.2B-Instruct 3 months ago

Some question about Inference Benchmark

1

#8 opened 3 months ago by

hebangwen

New activity in microsoft/VibeVoice-Realtime-0.5B 4 months ago

How can we access the acoustic encoder and semantics encoder?

1

#20 opened 4 months ago by

hebangwen

New activity in deepseek-ai/DeepSeek-V3.2 5 months ago

Humble request for a stable vLLM/SGLang deployment setup for DeepSeek-V3.2

👀❤️ 13

11

#15 opened 5 months ago by

burrowswang

New activity in deepseek-ai/DeepSeek-OCR 5 months ago

make deepseekocr compatible with mps and latest transformers

#96 opened 5 months ago by

hebangwen

RuntimeError: The expanded size of the tensor (753) must match the existing size (752) at non-singleton dimension 0. Target sizes: [753, 1280]. Tensor sizes: [752, 1]

1

#95 opened 5 months ago by

deathknight0

New activity in bosonai/higgs-audio-v2-generation-3B-base 9 months ago

Wrong link to the `ARCHITECTURE_BLOG`

1

#16 opened 9 months ago by

hebangwen

New activity in HuggingFaceTB/SmolLM3-3B 9 months ago

Question about the figure showing GQA.

➕ 2

1

#8 opened 9 months ago by

hebangwen

New activity in Qwen/Qwen2.5-VL-32B-Instruct-AWQ 10 months ago

AssertionError: Both operands must be same dtype. Got fp16 and bf16

20

#8 opened about 1 year ago by

treehugg3

New activity in deepseek-ai/DeepSeek-R1-0528 11 months ago

Will R2 be released before the National Day or Mid-Autumn Festival?

4

#28 opened 11 months ago by

dashi6174

New activity in Qwen/Qwen2.5-Omni-7B about 1 year ago

just a question about params

6

#17 opened about 1 year ago by

xubin-bruce

New activity in openbmb/MiniCPM-o-2_6-gguf about 1 year ago

How to get speech synthesized and speech recognized?

4

#3 opened about 1 year ago by

supercharge19

New activity in xai-org/grok-1 about 2 years ago

Thank you, Elon Musk! You are truly leading by example! Respect to you sir!

😔❤️ 22

7

#15 opened about 2 years ago by

jobenb