Jawad Mansoor
supercharge19
AI & ML interests
NLP for text and voice (even videos)
RL with multimodaliy models (agent is able to learn human speech as well as can see and make decisions based on what it "sees")
Recent Activity
liked
a model
3 days ago
bytedance-research/UI-TARS-7B-DPO
new activity
6 days ago
Qwen/Qwen2.5-Coder-32B-Instruct:Thieves!
new activity
9 days ago
unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF:Quality vs 4bnb version
Organizations
supercharge19's activity
Thieves!
9
#36 opened 18 days ago
by
supercharge19
Quality vs 4bnb version
5
#2 opened 10 days ago
by
supercharge19
Not distilled!
4
#5 opened 11 days ago
by
supercharge19
Wen R2D2?
1
#8 opened 12 days ago
by
TiFoil
Working with only these models?
1
#2 opened 28 days ago
by
supercharge19
How much RAM and VRAM does the model require?
2
#5 opened 29 days ago
by
supercharge19
Trained on ternary bits?
1
#3 opened 30 days ago
by
LLMToaster
Input token limit
1
#1 opened 4 months ago
by
HappyLemon
This is cooked
3
#2 opened about 1 month ago
by
supercharge19
It is quant of your own finetuned or original model?
6
#1 opened about 2 months ago
by
supercharge19
Best dataset for highest DocVQA
#6 opened 2 months ago
by
supercharge19
tools inventory
5
#2 opened 3 months ago
by
lucyknada
How to use a GGUF model for tool calling.
#1 opened 3 months ago
by
supercharge19
What does 3X mean and how does it compare with 3B model?
#1 opened 3 months ago
by
supercharge19
Why name pythagora?
1
#2 opened 4 months ago
by
supercharge19
Error: Matmul multiplication error
#29 opened 4 months ago
by
supercharge19
Any quantization possible?
3
#18 opened about 1 year ago
by
supercharge19
Congratulations on 100 score
#1 opened 9 months ago
by
supercharge19
compare with original gemma 2b?
#6 opened 9 months ago
by
supercharge19
GGUF versoin please
7
#1 opened 9 months ago
by
HR1777