Steve Li's picture

Steve Li

CHNtentes

·

CHNtentes

AI & ML interests

None yet

Recent Activity

new activity about 1 hour ago

unsloth/GLM-4-32B-0414-GGUF:Is UD-Q5_K_XL better than Q5_K_M one?

upvoted a collection about 2 hours ago

Unsloth Dynamic 2.0 Quants

new activity about 2 hours ago

unsloth/gemma-3-12b-it-qat-GGUF:Are these better than regular (non-qat) ones?

View all activity

Organizations

None yet

CHNtentes's activity

New activity in unsloth/GLM-4-32B-0414-GGUF about 1 hour ago

Is UD-Q5_K_XL better than Q5_K_M one?

#3 opened about 2 hours ago by

New activity in unsloth/gemma-3-12b-it-qat-GGUF about 2 hours ago

Are these better than regular (non-qat) ones?

#1 opened about 2 hours ago by

New activity in bartowski/THUDM_GLM-4-32B-0414-GGUF 1 day ago

llama.cpp fixes have just been merged

#5 opened 5 days ago by

New activity in bartowski/THUDM_GLM-4-32B-0414-GGUF 6 days ago

Broken results

#2 opened 14 days ago by

New activity in moonshotai/Kimi-VL-A3B-Thinking 12 days ago

gguf?

#1 opened 18 days ago by

AlgorithmicKing

New activity in city96/HiDream-I1-Full-gguf 12 days ago

Can we use existed llama 3.1 gguf

#1 opened 12 days ago by

New activity in meta-llama/Llama-4-Scout-17B-16E-Instruct 21 days ago

Unethical comparisons with Deepseek replacing chinese languages by thai/vietnamese only

#32 opened 22 days ago by

New activity in google/gemma-3-27b-it 25 days ago

SigLIP or SigLIP2 encoder?

#48 opened 26 days ago by

New activity in deepseek-ai/DeepSeek-V3-0324 27 days ago

Downloading weights without duplicates

#52 opened 27 days ago by

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

听我说谢谢你因为有你温暖了四季

#37 opened about 1 month ago by

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

Can this be quantized with bitsAndBytes?

#6 opened about 1 month ago by

New activity in Qwen/Qwen1.5-MoE-A2.7B-Chat-GPTQ-Int4 about 1 month ago

Int4为什么比没量化的float32和float16还慢

#3 opened about 2 months ago by

New activity in THUDM/CogView4-6B about 1 month ago

Maybe rename it 15B

#5 opened about 2 months ago by

New activity in mistralai/Mistral-Small-3.1-24B-Instruct-2503 about 1 month ago

Quantized models with vision included?

#27 opened about 1 month ago by

New activity in unsloth/QwQ-32B about 2 months 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 about 2 months ago by

New activity in Qwen/QwQ-32B about 2 months ago

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

#19 opened about 2 months ago by

New activity in moonshotai/Moonlight-16B-A3B-Instruct about 2 months 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 about 2 months ago by

New activity in Congliu/Chinese-DeepSeek-R1-Distill-data-110k 2 months ago

有的题目不完整

#6 opened 2 months ago by

New activity in deepseek-ai/DeepSeek-R1-Distill-Qwen-14B 3 months ago

Why change the configuration of the tokenizer?

#4 opened 3 months ago by

New activity in unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF 3 months ago

Quality vs 4bnb version

#2 opened 3 months ago by