Sujit Vasanth PRO
sujitvasanth
·
AI & ML interests
inference optimisation, gait reinforcement learning for mobile robots (quadrupeds, bipeds), song (music and vocal) generation, local computer use models and agents
Recent Activity
updated a model 33 minutes ago
sujitvasanth/piper-voice-data-mnn published a model 33 minutes ago
sujitvasanth/piper-voice-data-mnn updated a model about 12 hours ago
sujitvasanth/suayptalha-DeepSeek-R1-Distill-Llama-3BOrganizations
None yet
models performance sats is for the 31b
4
#1 opened 6 months ago
by sujitvasanth
respectfully: expanded CI suite breaks all repo github builds
#3 opened 5 months ago
by sujitvasanth
imatrix gguf's
2
#1 opened 6 months ago
by sujitvasanth
google/gemma-4-26B-A4B-it-assistant
👍 2
3
#1 opened 6 months ago
by sujitvasanth
Hcompany/Holo2-4B
1
#10 opened 11 months ago
by sujitvasanth
Qwen3VL-8B with WORKING coordinates please!
1
#9 opened 11 months ago
by sujitvasanth
Great model!
#1 opened 12 months ago
by sujitvasanth
Nice voice!
#1 opened 12 months ago
by sujitvasanth
Great voice!
#1 opened 12 months ago
by sujitvasanth
Wow so fast!
3
#1 opened about 1 year ago
by sujitvasanth
I have produced quantized exllamav2 version 6Gb and much faster inference
5
#3 opened about 1 year ago
by sujitvasanth
Model uses server not your huggingface model
#1 opened about 1 year ago
by sujitvasanth
Grounding task always (incorrectly) produce click action
#2 opened about 1 year ago
by sujitvasanth
Practicalities of fast inference (NOT OSWorld!)
1
#2 opened about 1 year ago
by sujitvasanth
add pipeline
9
#6 opened over 2 years ago
by 
not-lain
Example of tinyllava model implementation Tk transformers
2
#2 opened over 2 years ago
by sujitvasanth
The model supports multi-image and multi-prompt generation.?
2
#1 opened over 2 years ago
by sujitvasanth
Quants
7
#1 opened over 2 years ago
by 
CyberTimon