BuiDoan
BuiDoan
AI & ML interests
None yet
Recent Activity
liked a model about 8 hours ago
tattrongvu/Jeffan-9B-1211-FP8 liked a model about 8 hours ago
microsoft/Aion-1.0-Instruct-2.3B liked a model about 8 hours ago
RadixArk/DaisyRose-27B-FP8Organizations
vLLM / SGLang Support for Nemotron 3.5 120B CQ (CUDA + MTP)
#2 opened 2 days ago
by
BuiDoan
Is d3-ultra-FP8 too heavy for production concurrency?
2
#1 opened 17 days ago
by
BuiDoan
Improving Multilingual Support and NER Accuracy
1
#3 opened 21 days ago
by
BuiDoan
vllm version for deploy?
6
#4 opened 22 days ago
by
adasjh
vLLM-Compatible Quantized Models (FP8 / AWQ / GPTQ)
➕ 1
#3 opened 23 days ago
by
BuiDoan
Korean document-QA results vs the base gemma4 E4B, and thinking in Ollama
2
#1 opened 24 days ago
by
shoo99
Which SGLang 0.5.22 Version Was Used for Benchmarking?
1
#8 opened about 1 month ago
by
BuiDoan
Quantized version for vLLM support
👀 1
9
#2 opened about 1 month ago
by
BuiDoan
Hands down the best OCR model for regional languages!
❤️ 7
#1 opened about 1 month ago
by
BuiDoan
Are the PolyOCR model files missing?
1
#1 opened about 1 month ago
by
BuiDoan
Multilingual support details?
1
#3 opened about 2 months ago
by
BuiDoan
Performance Discrepancy Compared to the Official Web Model
#17 opened about 2 months ago
by
BuiDoan
Shall I reduce the num of spec tokens?
2
#9 opened 3 months ago
by
Nunodonato
How exactly is this model used?
2
#1 opened 5 months ago
by
Aloooom
THANK YOU
2
#1 opened 3 months ago
by
BuiDoan
Poor results
#1 opened 3 months ago
by
BuiDoan
Absolute legend!
🔥❤️ 20
#30 opened 3 months ago
by
BuiDoan
K-Quant-17GB
1
#14 opened 3 months ago
by
BuiDoan
Going completely mad
🚀🔥 45
11
#1 opened 4 months ago
by
xiezirock
Looping
18
#1 opened 4 months ago
by
jbourny