Nico Hezel

Neiko2002's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in TeichAI/Qwen3.5-9B-Fable-5-v1 about 21 hours ago

Much better with the original chat template

2

#3 opened 2 days ago by

Neiko2002

New activity in tencent/Hy3 3 days ago

Are there plans to release something around 9-12B in weight?

4

#3 opened 3 days ago by

XuehangCang

New activity in Tivaphraen/Geryon-9B-v1 9 days ago

Gets even better with the right template

🔥 1

#1 opened 9 days ago by

Neiko2002

New activity in deepreinforce-ai/Ornith-1.0-35B-FP8 11 days ago

FP8 seems to be broken

➕ 1

3

#1 opened 13 days ago by

Neiko2002

New activity in ytgui/Qwen3.5-Sonnet-9B about 1 month ago

Original ninja.template provides better results

3

#1 opened about 1 month ago by

Neiko2002

New activity in kai-os/Carnice-9b about 2 months ago

comparison

17

#2 opened 3 months ago by

kalle07

Broken config.json for vllm v0.21.0

#3 opened about 2 months ago by

Neiko2002

New activity in Xingyu-Zheng/Qwopus3.6-27B-v1-preview-INT4-FOEM about 2 months ago

Improved quality by changing the chat_template.jinja

4

#1 opened about 2 months ago by

Neiko2002

New activity in Jackrong/Qwopus3.5-9B-v3.5 about 2 months ago

tool calling?

1

#1 opened 2 months ago by

Neiko2002

New activity in Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash about 2 months ago

tool calling?

1

#4 opened 2 months ago by

Neiko2002

New activity in Jackrong/Qwen3.5-9B-GLM5.1-Distill-v1 about 2 months ago

tool calling?

1

#2 opened 2 months ago by

Neiko2002

New activity in webhie/Qwen3.6-27B-int4-AutoRound-Code about 2 months ago

Worse tool-calling accuracy due to chat_template.jinja

1

#2 opened about 2 months ago by

Neiko2002

New activity in Minachist/Qwen3.6-35B-A3B-INT8-AutoRound about 2 months ago

Crashes with newest vllm version (v0.20.1)

15

#1 opened 2 months ago by

Neiko2002

New activity in rdtand/Qwen3.6-27B-PrismaSCOUT-Blackwell-NVFP4-BF16-vllm 2 months ago

Does not work on 3090 GPUs

3

#2 opened 2 months ago by

Neiko2002

New activity in hampsonw/Qwen3.6-27B-AWQ-BF16-INT4-mtp-bf16 2 months ago

Amazing model

🔥 1

1

#3 opened 2 months ago by

Neiko2002

New activity in cyburn/Qwopus3.6-35B-A3B-v1-PrismaSCOUT-Blackwell-NVFP4-BF16-vllm-4.75bits 2 months ago

Works on 3090

#1 opened 2 months ago by

Neiko2002

New activity in Jackrong/Qwopus3.6-27B-v1-preview 2 months ago

tool calls?

6

#4 opened 2 months ago by

CryptoAIM

New activity in Minachist/Qwen3.6-35B-A3B-INT8-AutoRound 2 months ago

Removing speculative-config with care

#2 opened 2 months ago by

Neiko2002

New activity in HuggingFaceTB/SmolVLM2-2.2B-Instruct over 1 year ago

RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (CUDABFloat16Type) should be the same

2

#4 opened over 1 year ago by

Neiko2002

New activity in OpenGVLab/InternVL2-4B almost 2 years ago

Flash Attention 2

2

#1 opened about 2 years ago by

Modularity