Henky!!
Henk717
AI & ML interests
GPT based language generation, chatbots and AI based gaming
Recent Activity
new activity 9 days ago
Esobold/EsoTest_GGUFs:why no comments? updated a model 19 days ago
koboldcpp/kcppt updated a model 23 days ago
koboldcpp/kcpptOrganizations
why no comments?
1
#1 opened 9 days ago
by
lawless92
Apply for community grant: Opensource community project (gpu)
5
#1 opened almost 3 years ago
by
Henk717
Doesn't work with KoboldCPP?
6
#4 opened 5 months ago
by
MttCode
Not actually fully uncensored
3
#1 opened 5 months ago
by
Henk717
Qwen3.6-27B?
🚀❤️ 32
19
#2 opened 5 months ago
by
lingyezhixing
Model has trouble understanding who it's supposed to talk as.
3
#1 opened over 1 year ago
by
BigBeavis
K quants in non K quants
#13 opened 11 months ago
by
Henk717
K quants in the non K quants
#43 opened 11 months ago
by
Henk717
Not uncensored
3
#3 opened about 1 year ago
by
Henk717
Final GLM-4-32B-0414-GGUF fixes!
🚀 1
7
#8 opened about 1 year ago
by
shimmyshimmer
Running with VLLM is not printing '<think>' tokens.
➕ 7
8
#8 opened over 1 year ago
by
TalonOne
When GGUF?
🤗👍 12
25
#6 opened over 1 year ago
by
ChuckMcSneed
How do I combine the file parts?
3
#1 opened almost 2 years ago
by
Frank2478
Any planes for the future?
1
#3 opened about 2 years ago
by
SicariusSicariiStuff
Default context setting seems borked
1
#3 opened about 2 years ago
by
headmold
"llama.cpp error: 'error loading model vocabulary: unknown pre-tokenizer type: 'dolphin12b''"
👍 1
23
#1 opened about 2 years ago
by
jrell
Rope fix?
👍 2
2
#2 opened about 2 years ago
by
DataPhreak
exception in koboldcpp
3
#2 opened about 2 years ago
by
Szarka
nvidia/Mistral-NeMo-12B-Base
9
#156 opened about 2 years ago
by
DazzlingXeno