Sebastien
sebastienbo
AI & ML interests
None yet
Recent Activity
new activity 1 day ago
Qwen/Qwen-Image-2512:Qwen-Image-2 new activity 18 days ago
qualcomm/Llama-v2-7B-Chat:LLAMA.cpp for SnapDragon on Windows ARM64 new activity 21 days ago
agentscope-ai/QwenPaw-Flash-9B:[Agent Evaluation] Testing CoPaw-Flash-9B as a local coding agentOrganizations
None yet
Qwen-Image-2
👀❤️ 11
5
#24 opened about 2 months ago
by
ionanghelina
LLAMA.cpp for SnapDragon on Windows ARM64
5
#8 opened over 1 year ago
by
Berowne
[Agent Evaluation] Testing CoPaw-Flash-9B as a local coding agent
7
#1 opened 23 days ago
by
FutureMa
What data is used?
#1 opened about 1 month ago
by
sebastienbo
Data it was trained on?
2
#1 opened about 1 month ago
by
sebastienbo
only 12b active? Weren't you guys saying 20b?
3
#1 opened about 2 months ago
by
szilard995
Abliterate on models with low KLD
👍 2
#8 opened about 2 months ago
by
sebastienbo
Schematron security against prompt injections?
#2 opened 2 months ago
by
sebastienbo
Kimi K2.5 slow?
2
#72 opened 2 months ago
by
sebastienbo
Benchmarks
🔥 3
7
#1 opened 4 months ago
by
itsme-nishanth
What is the purpose of this new 57B variant?
1
#1 opened 3 months ago
by
sebastienbo
Muliltipage documents
👍 2
2
#8 opened 3 months ago
by
jondecker76
Long context reasoning scores bad?
2
#49 opened 3 months ago
by
sebastienbo
Parquet file is toxic?
1
#3 opened 3 months ago
by
sebastienbo
Unsloth Magic Quants - Q4
👍 1
#1 opened 3 months ago
by
sebastienbo
MagicQuant for Apriel 1.6?
7
#1 opened 3 months ago
by
sebastienbo
ClosedAI: MXFP4 is not Open Source
👍 7
1
#168 opened 4 months ago
by
Max-and-Omnis
Do you plan to create GGUF versions of different model sizes for the NSFW AIO based on Qwen 2511?
2
#28 opened 4 months ago
by
daijava
GGUF when? 8 bit quant when?
➕❤️ 13
14
#1 opened 8 months ago
by
ouchiewouchie
When new version?
👍 1
1
#37 opened 9 months ago
by
MajinAnix