Steve Li's picture

65 16

Steve Li

CHNtentes

·

CHNtentes

AI & ML interests

None yet

Recent Activity

new activity 1 day ago

deepseek-ai/DeepSeek-V3-0324:听我说谢谢你因为有你温暖了四季

new activity 2 days ago

Qwen/Qwen2.5-Omni-7B:Qwen2.5-Omni-7B-AWQ?

new activity 2 days ago

Qwen/Qwen2.5-Omni-7B:Can this be quantized with bitsAndBytes?

View all activity

Organizations

None yet

CHNtentes's activity

New activity in deepseek-ai/DeepSeek-V3-0324 1 day ago

听我说谢谢你因为有你温暖了四季

#37 opened 3 days ago by

New activity in Qwen/Qwen2.5-Omni-7B 2 days ago

Qwen2.5-Omni-7B-AWQ?

#7 opened 2 days ago by

Can this be quantized with bitsAndBytes?

#6 opened 3 days ago by

New activity in Qwen/Qwen1.5-MoE-A2.7B-Chat-GPTQ-Int4 5 days ago

Int4为什么比没量化的float32和float16还慢

#3 opened 21 days ago by

New activity in THUDM/CogView4-6B 7 days ago

Maybe rename it 15B

#5 opened 24 days ago by

New activity in mistralai/Mistral-Small-3.1-24B-Instruct-2503 7 days ago

Quantized models with vision included?

#27 opened 10 days ago by

New activity in bartowski/nvidia_Llama-3_3-Nemotron-Super-49B-v1-GGUF 9 days ago

Does it support thinking on/off?

#2 opened 9 days ago by

New activity in unsloth/QwQ-32B 22 days 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

#1 opened 23 days ago by

New activity in Qwen/QwQ-32B 23 days ago

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

#19 opened 23 days ago by

New activity in moonshotai/Moonlight-16B-A3B-Instruct 26 days ago

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

#9 opened 29 days ago by

New activity in nvidia/DeepSeek-R1-FP4 about 1 month ago

Benchmark results compared to orig fp8 / int4 quants etc?

#1 opened about 1 month ago by

New activity in Congliu/Chinese-DeepSeek-R1-Distill-data-110k about 1 month ago

有的题目不完整

#6 opened about 1 month ago by

New activity in deepseek-ai/DeepSeek-R1-Distill-Qwen-14B 2 months ago

Why change the configuration of the tokenizer?

#4 opened 2 months ago by

New activity in unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF 2 months ago

Quality vs 4bnb version

#2 opened 2 months ago by

New activity in deepseek-ai/DeepSeek-R1-Distill-Qwen-14B 2 months ago

System Prompt

#2 opened 2 months ago by

New activity in Qwen/Qwen2.5-Coder-32B-Instruct 2 months ago

Thieves!

#36 opened 3 months ago by

New activity in unsloth/DeepSeek-V3-GGUF 3 months ago

why use q5 for key cache?

#7 opened 3 months ago by

New activity in bullerwins/DeepSeek-V3-GGUF 3 months ago

这我也跑不动啊你们都是在拿什么玩意玩啊。我勒个公鸡母鸡战斗鸡啊

#8 opened 3 months ago by

New activity in city96/HunyuanVideo-gguf 3 months ago

Can we use "temporal tiling support" with these gguf models?

#10 opened 3 months ago by

New activity in deepseek-ai/DeepSeek-V3 3 months ago

minimum vram?

#9 opened 3 months ago by