Nico Hezel
Neiko2002
AI & ML interests
None yet
Recent Activity
new activity 3 days ago
kai-os/Carnice-9b:comparison new activity 5 days ago
GestaltLabs/Qwen3.6-35B-A3B-NSC-ACE-SABER:FP8 or NVFP4 versions for vLLM new activity 5 days ago
kai-os/Carnice-9b:Broken config.json for vllm v0.21.0Organizations
comparison
12
#2 opened about 1 month ago
by
kalle07
FP8 or NVFP4 versions for vLLM
3
#1 opened 6 days ago
by
Qnibbles
Broken config.json for vllm v0.21.0
#3 opened 5 days ago
by
Neiko2002
Improved quality by changing the chat_template.jinja
4
#1 opened 6 days ago
by
Neiko2002
tool calling?
1
#1 opened 14 days ago
by
Neiko2002
tool calling?
1
#4 opened 14 days ago
by
Neiko2002
tool calling?
1
#2 opened 14 days ago
by
Neiko2002
Worse tool-calling accuracy due to chat_template.jinja
1
#2 opened 6 days ago
by
Neiko2002
Crashes with newest vllm version (v0.20.1)
15
#1 opened 17 days ago
by
Neiko2002
Can't load image processor
2
#1 opened 9 days ago
by
Neiko2002
Does not work on 3090 GPUs
3
#2 opened 13 days ago
by
Neiko2002
Amazing model
🔥 1
1
#3 opened 13 days ago
by
Neiko2002
New activity in cyburn/Qwopus3.6-35B-A3B-v1-PrismaSCOUT-Blackwell-NVFP4-BF16-vllm-4.75bits 13 days ago
Works on 3090
#1 opened 13 days ago
by
Neiko2002
tool calls?
6
#4 opened 26 days ago
by
CryptoAIM
Removing speculative-config with care
#2 opened 17 days ago
by
Neiko2002
RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (CUDABFloat16Type) should be the same
2
#4 opened over 1 year ago
by
Neiko2002
Flash Attention 2
2
#1 opened almost 2 years ago
by
Modularity