Nico Hezel
Neiko2002
AI & ML interests
None yet
Recent Activity
liked a model about 8 hours ago
internlm/Intern-S2-Mobius liked a model 1 day ago
badtheorylabs/BTL-4 new activity 4 days ago
JasonW2025/Laguna-S-2.1-ModelOpt-NVFP4-W4A4-vllm:Amazing QuantOrganizations
Amazing Quant
😎 1
1
#1 opened 4 days ago
by
Neiko2002
Benchmark results?
1
#1 opened 5 days ago
by
Neiko2002
Thinking Loops, and Chat Template possible fix!
❤️ 4
20
#23 opened 14 days ago
by
danielcherubini
Much better with the original chat template
2
#3 opened about 1 month ago
by
Neiko2002
Are there plans to release something around 9-12B in weight?
4
#3 opened about 1 month ago
by
XuehangCang
Gets even better with the right template
🔥 1
#1 opened about 1 month ago
by
Neiko2002
FP8 seems to be broken
➕ 1
3
#1 opened about 1 month ago
by
Neiko2002
Original ninja.template provides better results
3
#1 opened 2 months ago
by
Neiko2002
comparison
17
#2 opened 4 months ago
by
kalle07
Broken config.json for vllm v0.21.0
#3 opened 3 months ago
by
Neiko2002
Improved quality by changing the chat_template.jinja
4
#1 opened 3 months ago
by
Neiko2002
tool calling?
1
#1 opened 3 months ago
by
Neiko2002
tool calling?
1
#4 opened 3 months ago
by
Neiko2002
tool calling?
1
#2 opened 3 months ago
by
Neiko2002
Worse tool-calling accuracy due to chat_template.jinja
1
#2 opened 3 months ago
by
Neiko2002
Crashes with newest vllm version (v0.20.1)
15
#1 opened 3 months ago
by
Neiko2002
Does not work on 3090 GPUs
3
#2 opened 3 months ago
by
Neiko2002
Amazing model
🔥 1
1
#3 opened 3 months ago
by
Neiko2002
New activity in cyburn/Qwopus3.6-35B-A3B-v1-PrismaSCOUT-Blackwell-NVFP4-BF16-vllm-4.75bits 3 months ago
Works on 3090
#1 opened 3 months ago
by
Neiko2002
tool calls?
6
#4 opened 3 months ago
by
CryptoAIM