Darx Kies's picture

Darx Kies

darxkies

·

darxkies

AI & ML interests

None yet

Recent Activity

new activity about 1 month ago

lmstudio-community/gpt-oss-20b-GGUF:Broken chat template

liked a model about 1 month ago

ggml-org/gpt-oss-20b-GGUF

liked a model about 1 month ago

tencent/Hunyuan-4B-Instruct

View all activity

Organizations

None yet

New activity in lmstudio-community/gpt-oss-20b-GGUF about 1 month ago

Broken chat template

#2 opened about 1 month ago by

New activity in Disya/Mistral-qwq-12b-merge 3 months ago

Feedback

#1 opened 3 months ago by

New activity in microsoft/Phi-4-reasoning-plus 4 months ago

"ChatML" & <|im_sep|>

#10 opened 4 months ago by

New activity in NikolayKozloff/Llama-3.1-Minitron-4B-Width-Base-Q8_0-GGUF about 1 year ago

Can't run

#1 opened about 1 year ago by

New activity in Undi95/Llama-3-Unholy-8B-GGUF over 1 year ago

It's an excellent version, but...

#1 opened over 1 year ago by

New activity in saishf/Fimbulvetr-Kuro-Lotus-10.7B-GGUF over 1 year ago

q8 quants

#1 opened over 1 year ago by

New activity in Herman555/Kunoichi-AshhLimaRP-Mistral-7B-GGUF over 1 year ago

q8 quant

#1 opened over 1 year ago by

New activity in TheBloke/OpenHermes-2.5-neural-chat-7B-v3-2-7B-GGUF almost 2 years ago

This model uses <0x0A> instead of a carriage return

#1 opened almost 2 years ago by

New activity in tastypear/NSFW_13B_sft-GGUF almost 2 years ago

q8 quantization

#1 opened almost 2 years ago by

New activity in Herman555/MythoMist-AshhLimaRP-Mistral-7B-GGUF almost 2 years ago

Favorite Model?

#2 opened almost 2 years ago by

New activity in Herman555/dolphin-2.2.1-AshhLimaRP-Mistral-7B-GGUF almost 2 years ago

q8 file

#1 opened almost 2 years ago by

New activity in Undi95/Toppy-M-7B-GGUF almost 2 years ago

Good!

#1 opened almost 2 years ago by

New activity in coyude/Nous-Hermes-13b-Chinese-GGML about 2 years ago

q8

#1 opened about 2 years ago by

New activity in dbian/gpt4-x-vicuna-13B-chinese over 2 years ago

大神能讲讲你是什么转换过来的么

#2 opened over 2 years ago by

New activity in ShadowPower/ggml-alpaca-chatgpt-new over 2 years ago

q8_0

#1 opened over 2 years ago by

New activity in rustformers/mpt-7b-ggml over 2 years ago

llama.cpp

#1 opened over 2 years ago by

New activity in execveat/wizardLM-13b-ggml-4bit over 2 years ago

q8

#1 opened over 2 years ago by

New activity in TheBloke/wizardLM-7B-GGML over 2 years ago

Which is better? GGML of GPTQ version or of the merged deltas

#3 opened over 2 years ago by