🔄 In a Training Loop
Md Ismail Sojal
0xSojalSec
AI & ML interests
Ai-ML-RL-LLM-MoE-SLMs-MLMs-LAMs-VLMs
Re-searcher/ post-training / reasoning models / RAG /
Recent Activity
liked a model 5 days ago
XiaomiMiMo/MiMo-V2.6-Flash-RL liked a Space 14 days ago
Pepe104/MiniMax-H3-Turbo-Lora-UNCENSORED upvoted an article 20 days ago
Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO StepsOrganizations
big open model
vision model for military or sports use
cyber-model
coding
iPhone
vuln-Scanners
top model
Phone ai
OCR
3D World
filtered dataset.
single consumer GPU
smaller model
-
Motif-Technologies/Motif-2.6B
Text Generation • 3B • Updated • 485 • 88 -
InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
Paper • 2508.18265 • Published • 221 -
OpenGVLab/InternVL3_5-241B-A28B
Image-Text-to-Text • 241B • Updated • 922 • 141 -
openbmb/MiniCPM-V-4_5
Image-Text-to-Text • 9B • Updated • 146k • 1.1k
voiceover
-
allenai/wildjailbreak-r1-v2-format-filtered
Viewer • Updated • 41.4k • 120 • 4 - Running on ZeroAgentsFeatured864
Sesame CSM
🌱864Conversational speech generation
-
mistralai/Voxtral-4B-TTS-2603
Text-to-Speech • Updated • 1.58k • 918 -
Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice
Text-to-Speech • 2B • Updated • 2.44M • 2k
lama
18+ anime video model
distilled model
claude-trace
WebGPu
Robot
uncensor
- Running on ZeroAgents585
OBLITERATUS
💥585One-click model liberation + chat playground
-
huihui-ai/Huihui-Qwen3.5-9B-abliterated
Image-Text-to-Text • 10B • Updated • 7.9k • • 140 -
dealignai/Gemma-4-31B-JANG_4M-CRACK
Image-Text-to-Text • 20B • Updated • 16.4k • 1.72k -
Jiunsong/supergemma4-26b-uncensored-mlx-4bit-v2
Text Generation • 25B • Updated • 7.13k • 299
medical datasets
dataset
Reasoning
Vision-to-Diagram
locally
Reasoner
image-to-image editing
tools
Chains model
creative
18+ anime video model
big open model
distilled model
vision model for military or sports use
claude-trace
cyber-model
WebGPu
coding
Robot
iPhone
uncensor
- Running on ZeroAgents585
OBLITERATUS
💥585One-click model liberation + chat playground
-
huihui-ai/Huihui-Qwen3.5-9B-abliterated
Image-Text-to-Text • 10B • Updated • 7.9k • • 140 -
dealignai/Gemma-4-31B-JANG_4M-CRACK
Image-Text-to-Text • 20B • Updated • 16.4k • 1.72k -
Jiunsong/supergemma4-26b-uncensored-mlx-4bit-v2
Text Generation • 25B • Updated • 7.13k • 299
vuln-Scanners
medical datasets
top model
dataset
Phone ai
Reasoning
OCR
Vision-to-Diagram
3D World
locally
filtered dataset.
Reasoner
single consumer GPU
image-to-image editing
smaller model
-
Motif-Technologies/Motif-2.6B
Text Generation • 3B • Updated • 485 • 88 -
InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
Paper • 2508.18265 • Published • 221 -
OpenGVLab/InternVL3_5-241B-A28B
Image-Text-to-Text • 241B • Updated • 922 • 141 -
openbmb/MiniCPM-V-4_5
Image-Text-to-Text • 9B • Updated • 146k • 1.1k
tools
voiceover
-
allenai/wildjailbreak-r1-v2-format-filtered
Viewer • Updated • 41.4k • 120 • 4 - Running on ZeroAgentsFeatured864
Sesame CSM
🌱864Conversational speech generation
-
mistralai/Voxtral-4B-TTS-2603
Text-to-Speech • Updated • 1.58k • 918 -
Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice
Text-to-Speech • 2B • Updated • 2.44M • 2k
Chains model
lama