Hugging Face's logo
Steve Li's picture
67 16

Steve Li

CHNtentes
ltim's profile picture 21world's profile picture
·

AI & ML interests

None yet

Recent Activity

new activity 3 days ago
google/gemma-3-27b-it:SigLIP or SigLIP2 encoder?
new activity 5 days ago
deepseek-ai/DeepSeek-V3-0324:Downloading weights without duplicates
new activity 10 days ago
deepseek-ai/DeepSeek-V3-0324:听我说谢谢你因为有你温暖了四季
View all activity

Organizations

None yet

CHNtentes's activity

New activity in google/gemma-3-27b-it 3 days ago

SigLIP or SigLIP2 encoder?

3
#48 opened 4 days ago by
orrzohar
New activity in deepseek-ai/DeepSeek-V3-0324 5 days ago

Downloading weights without duplicates

2
#52 opened 5 days ago by
vadimkantorov
New activity in deepseek-ai/DeepSeek-V3-0324 10 days ago

听我说谢谢你因为有你温暖了四季

4
#37 opened 11 days ago by
iwangdy
New activity in Qwen/Qwen2.5-Omni-7B 11 days ago

Qwen2.5-Omni-7B-AWQ?

1
#7 opened 11 days ago by
CHNtentes

Can this be quantized with bitsAndBytes?

8
#6 opened 11 days ago by
Permahuman
liked a model 12 days ago
New activity in Qwen/Qwen1.5-MoE-A2.7B-Chat-GPTQ-Int4 13 days ago

Int4为什么比没量化的float32和float16还慢

1
#3 opened 29 days ago by
hujianmin
New activity in THUDM/CogView4-6B 15 days ago

Maybe rename it 15B

2
#5 opened about 1 month ago by
CHNtentes
New activity in mistralai/Mistral-Small-3.1-24B-Instruct-2503 15 days ago

Quantized models with vision included?

12
#27 opened 18 days ago by
geoad
New activity in bartowski/nvidia_Llama-3_3-Nemotron-Super-49B-v1-GGUF 18 days ago

Does it support thinking on/off?

5
#2 opened 18 days ago by
CHNtentes
liked a model about 1 month ago
New activity in unsloth/QwQ-32B about 1 month ago

I could be wrong, but I think the <think> tag needs to be removed from the last bit of the jinja template in the tokenizer_config.json

3
#1 opened about 1 month ago by
jth01
liked a Space about 1 month ago
New activity in Qwen/QwQ-32B about 1 month ago

When will you fix the model replies missing</think>\n start tags

17
#19 opened about 1 month ago by
xldistance
liked a Space about 1 month ago
New activity in moonshotai/Moonlight-16B-A3B-Instruct about 1 month ago

When running example got ValueError: Attention mask should be of size (1, 1, 1, 30), but is torch.Size([1, 1, 1, 29])

6
#9 opened about 1 month ago by
Phando
New activity in nvidia/DeepSeek-R1-FP4 about 1 month ago

Benchmark results compared to orig fp8 / int4 quants etc?

5
#1 opened about 1 month ago by
CHNtentes
New activity in Congliu/Chinese-DeepSeek-R1-Distill-data-110k about 1 month ago

有的题目不完整

3
#6 opened about 1 month ago by
CHNtentes
liked a model about 2 months ago
New activity in deepseek-ai/DeepSeek-R1-Distill-Qwen-14B 2 months ago

Why change the configuration of the tokenizer?

2
#4 opened 2 months ago by
Lingrui