9 6

muziyongshixin

AI & ML interests

None yet

Recent Activity

new activity about 1 month ago

meituan/DeepSeek-R1-Channel-INT8:how to achieve 2500 tps throughput？

new activity about 2 months ago

cognitivecomputations/DeepSeek-R1-AWQ:Any one can run this model with SGlang framework？

new activity about 2 months ago

cognitivecomputations/DeepSeek-R1-AWQ:MLA is not supported with moe_wna16 quantization. Disabling MLA.

View all activity

Organizations

None yet

muziyongshixin's activity

New activity in meituan/DeepSeek-R1-Channel-INT8 about 1 month ago

how to achieve 2500 tps throughput？

#8 opened about 1 month ago by

muziyongshixin

New activity in cognitivecomputations/DeepSeek-R1-AWQ about 2 months ago

Any one can run this model with SGlang framework？

#13 opened about 2 months ago by

muziyongshixin

MLA is not supported with moe_wna16 quantization. Disabling MLA.

#7 opened 2 months ago by

AMOSE

New activity in cognitivecomputations/DeepSeek-R1-AWQ 2 months ago

Deployment framework

#2 opened 3 months ago by

xro7

New activity in mattshumer/Reflection-Llama-3.1-70B 7 months ago

When experiencing models on the Hugging Face space, Chinese input often results in garbled output.

#14 opened 7 months ago by

muziyongshixin

New activity in 01-ai/Yi-1.5-34B-32K 11 months ago

what is the difference between this model and 01-ai/Yi-1.5-34B?

#2 opened 11 months ago by

muziyongshixin

New activity in databricks/dbrx-instruct about 1 year ago

why does the im_start and im_end token id exceed the tokenizer.voc_size?

#36 opened about 1 year ago by

muziyongshixin

New activity in mlabonne/Beyonder-4x7B-v2 about 1 year ago

How does MergeKit's Moe Integration work?

#8 opened about 1 year ago by

arhanovich

New activity in bigscience/bloomz-7b1-p3 about 2 years ago

what is the difference between this model and bigscience / bloomz-7b1-mt?

#2 opened about 2 years ago by

muziyongshixin