Superb Emphasis
SuperbEmphasis
AI & ML interests
None yet
Recent Activity
liked
a model
6 days ago
coder3101/Cydonia-24B-v4.3-heretic
liked
a model
11 days ago
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
new activity
19 days ago
mistralai/Ministral-3-14B-Reasoning-2512:Reasoning not parsing correctly within VLLM
Organizations
None yet
Reasoning not parsing correctly within VLLM
11
#4 opened 24 days ago
by
SuperbEmphasis
Gguf
1
#4 opened about 1 month ago
by
DarkGenius01
Working on Hopper?
#2 opened about 1 month ago
by
SuperbEmphasis
Llama-3_3-Nemotron-Super-49B-v1_5-NVFP4/llama_nemotron_toolcall_parser_no_streaming.py missing
1
#1 opened about 1 month ago
by
SuperbEmphasis
Granite Docling not working using vllm
👍
2
4
#20 opened 3 months ago
by
SadiaSid
Could you shar the gradio demo code?
4
#18 opened 3 months ago
by
SuperbEmphasis
Possible to disable thinking via a karg?
1
#7 opened 4 months ago
by
SuperbEmphasis
Is there a benefit of this version vs the original MXFP4?
#5 opened 3 months ago
by
SuperbEmphasis
Any tricks to make this model code better?
3
#1 opened 4 months ago
by
SuperbEmphasis
--enable-reasoning is deprecated
2
#4 opened 5 months ago
by
SuperbEmphasis
Can't stop it from speweing garbage after about 1000 tokens...
#2 opened 5 months ago
by
SuperbEmphasis
Cool way to fine tune that I wanted to share.
👀
1
#9 opened 6 months ago
by
SuperbEmphasis
what instruct format does it use? or does it not use any?
1
#1 opened 6 months ago
by
Krolon
Context and Instruct Templates?
4
#2 opened 6 months ago
by
Leonxwerty
A more correct prompt from a spelling standpoint
2
#1 opened 6 months ago
by
FrescoHF
SuperbEmphasis/Viloet-Eclipse-2x12B-v0.2-MINI
3
#1052 opened 7 months ago
by
SuperbEmphasis
[bot] Conversion to Parquet
#1 opened 7 months ago
by
parquet-converter
SuperbEmphasis/Velvet-Eclipse-4x12B-v0.2
2
#1046 opened 7 months ago
by
SuperbEmphasis
Multiple back to back assistant messages
2
#1 opened 7 months ago
by
SuperbEmphasis
Update README.md
1
#1 opened 7 months ago
by
SuperbEmphasis