Celso F
celsowm
AI & ML interests
None yet
Recent Activity
published a dataset 8 days ago
celsowm/srp-gpt2-ptbr-corpus updated a dataset 8 days ago
celsowm/srp-gpt2-ptbr-corpus new activity 8 days ago
deepseek-ai/DeepSeek-V4-Flash:Is 158B or 284b params ?Organizations
None yet
Is 158B or 284b params ?
6
#17 opened 8 days ago
by
celsowm
vllm error
👍 3
2
#1 opened 28 days ago
by
celsowm
Recipe for full tuning using trl?
#11 opened about 2 months ago
by
celsowm
Benchmark numbers comparison
#6 opened about 2 months ago
by
celsowm
Benchmark numbers of this quant version
👀 6
#1 opened about 2 months ago
by
celsowm
please includes portuguese in the next training
🤗➕ 2
3
#2 opened 4 months ago
by
celsowm
how much memory to run with 8k ctx?
1
#1 opened 4 months ago
by
celsowm
The start of <think> is not been used on assistant response using vllm 0.13
1
#5 opened 4 months ago
by
celsowm
nex-agi/DeepSeek-V3.1-Nex-N1
1
#6289 opened 5 months ago
by
celsowm
URL to test this model online?
1
#12 opened 7 months ago
by
celsowm
Any place to test it online?
2
#4 opened 8 months ago
by
celsowm
Please add portuguese in the next version
#1 opened 8 months ago
by
celsowm
Please release fp8 version
1
#9 opened 9 months ago
by
celsowm
nvidia/NVIDIA-Nemotron-Nano-9B-v2
❤️🚀 26
1
#4233 opened 9 months ago
by
celsowm
nvidia/NVIDIA-Nemotron-Nano-12B-v2-Base
❤️ 7
#4232 opened 9 months ago
by
celsowm
Fp8 version
2
#41 opened 9 months ago
by
celsowm
tencent/Hunyuan-7B-Instruct
👍 2
#3855 opened 9 months ago
by
celsowm
arcee-ai/AFM-4.5B-GGUF
#3753 opened 9 months ago
by
celsowm
ai21labs/AI21-Jamba-Mini-1.7
👍 2
#3555 opened 9 months ago
by
celsowm
nvidia/OpenReasoning-Nemotron-32B
🚀 3
#3511 opened 10 months ago
by
celsowm