Neo HuggingF
NeoHuggingF
AI & ML interests
Local SLM
Organizations
None yet
This model stops driving tools below ~2.7 bpw — and no fidelity metric shows it
10
#1 opened 2 months ago
by
KikoCis
Any ideas why 1.5 is bigger than 1.0? MTP?
❤️ 1
10
#1 opened 3 months ago
by
NeoHuggingF
ProCreation vs Kai-OS
4
#1 opened 4 months ago
by
QBANIN
Quick feedback (IQ4_XS GGUF)
#1 opened 3 months ago
by
NeoHuggingF
Possible enhancemet to avoid problems with tool calling
❤️ 1
1
#1 opened 3 months ago
by
NeoHuggingF
Some results from non-deterministic tests
4
#2 opened 3 months ago
by
NeoHuggingF
Info on the synthetic prompt pipeline
1
#5 opened 3 months ago
by
nraxl1
Good results and possible request
🧠 1
5
#3 opened 4 months ago
by
NeoHuggingF
Error loading the GGUF using instructions from README
3
#1 opened 4 months ago
by
NeoHuggingF
KAT-Coder-V2.5-Dev vs Qwen 3.6-35B-A3B
👍 3
3
#4 opened 4 months ago
by
Kirin1997
IQ3_M or IQ3_XS?
❤️ 1
14
#1 opened 4 months ago
by
NeoHuggingF
Infinite thiking
7
#5 opened 5 months ago
by
KralHarlaus
GGUFs ship without tokenizer.chat_template → repetition-loop degeneration in Ollama/llama.cpp
🚀 2
1
#2 opened 5 months ago
by
KikoCis
Typo in Modelfile and some comments
1
#2 opened 5 months ago
by
NeoHuggingF
imatrix?
1
#1 opened 5 months ago
by
NeoHuggingF
Strange loop
4
#4 opened 5 months ago
by
StoykovK
Got an error while starting this model with mtp
👍 1
1
#6 opened 5 months ago
by
Norfein
q8 why is this size inappropriately small?!
2
#5 opened 5 months ago
by
skskskkss