Hugging Face's logo
ghostplant's picture
7 1

ghostplant

ghostplant

AI & ML interests

None yet

Recent Activity

updated a dataset 6 days ago
ghostplant/data-collections
new activity 13 days ago
deepseek-ai/DeepSeek-R1:Deploying production ready service with Unsloth GGUF quants on your AWS account. (4 x L40S)
new activity 13 days ago
deepseek-ai/DeepSeek-R1:Does R1 support long context (> 4K)?
View all activity

Organizations

None yet

ghostplant's activity

New activity in deepseek-ai/DeepSeek-R1 13 days ago

Deploying production ready service with Unsloth GGUF quants on your AWS account. (4 x L40S)

8
#171 opened 13 days ago by
samagra-tensorfuse

Does R1 support long context (> 4K)?
#172 opened 13 days ago by
ghostplant
New activity in deepseek-ai/DeepSeek-R1 15 days ago

90+ tokens per second for MI300x8 using batch_size = 1

1
#166 opened 16 days ago by
ghostplant
New activity in unsloth/DeepSeek-R1-GGUF 16 days ago

Q2_K_XL 好还是 Q4好呢

3
#34 opened 18 days ago by
jializou
New activity in deepseek-ai/DeepSeek-R1 17 days ago

所以部署一个671B的模型 显存需要多少 有什么基准的硬件配置？

27
#118 opened about 1 month ago by
cena163
New activity in deepseek-ai/DeepSeek-R1-Distill-Llama-70B about 1 month ago

How much vram do you need?

8
#12 opened about 1 month ago by
hyun10
New activity in unsloth/DeepSeek-R1-GGUF about 1 month ago

Is there a model removing non-shared MoE experts?

4
#17 opened about 1 month ago by
ghostplant
New activity in deepseek-ai/DeepSeek-R1-Distill-Qwen-32B about 1 month ago

Please convert these models to GGUF format...

5
#12 opened about 2 months ago by
Moodym