devilman

devilmanz

devilmanz

AI & ML interests

None yet

Recent Activity

liked a model about 1 month ago

magiccodingman/Qwen3-4B-Thinking-2507-Unsloth-MagicQuant-Hybrid-GGUF

liked a model 3 months ago

Qwen/Qwen3-VL-4B-Thinking

reacted to codelion's post with 🔥 5 months ago

I recently added a recipe in ellora to improve reasoning capabilities to Gemma-3-1B using self-supervised learning. Model now shows step-by-step thinking in <think> tags before answering. Logic puzzle accuracy: 61% → 84%. 3 hours training on single GPU. 🧠 Used GRPO where model generates multiple responses and learns to prefer better reasoning. Works surprisingly well for making smaller models more transparent. 🔗 Colab: https://colab.research.google.com/github/codelion/ellora/blob/main/Ellora_Recipe_2_Reasoning_LoRA_with_Self-Rewarding_GRPO.ipynb 🤗 Model: https://huggingface.co/codelion/gemma-3-1b-it-reasoning-grpo-lora 💻 Code: https://github.com/codelion/ellora

View all activity

Organizations

None yet

liked a model about 1 month ago

magiccodingman/Qwen3-4B-Thinking-2507-Unsloth-MagicQuant-Hybrid-GGUF

Text Generation • 4B • Updated Dec 5, 2025 • 724 • 1

liked a model 3 months ago

Qwen/Qwen3-VL-4B-Thinking

Image-Text-to-Text • 4B • Updated Oct 15, 2025 • 99k • 97

liked 2 models 5 months ago

microsoft/VibeVoice-1.5B

Text-to-Speech • 3B • Updated Sep 1, 2025 • 296k • 2.17k

nvidia/NVIDIA-Nemotron-Nano-9B-v2

Text Generation • 9B • Updated 12 days ago • 101k • 462

liked a Space 5 months ago

Open ASR Leaderboard

🏆

1.2k

View and request speech models benchmark data

liked a model 5 months ago

hexgrad/Kokoro-82M

Text-to-Speech • Updated Apr 10, 2025 • 1.91M • • 5.59k

liked 5 models 6 months ago

liked 2 models 9 months ago

Qwen/Qwen3-30B-A3B

Text Generation • 31B • Updated Jul 26, 2025 • 467k • • 840

microsoft/Phi-4-mini-reasoning

Text Generation • 4B • Updated Dec 10, 2025 • 12.1k • 213

liked a Space 9 months ago

GGUF My Repo

🦙

1.81k

Create quantized models from Hugging Face repos

liked 4 models 10 months ago

Qwen/QwQ-32B-GGUF

Text Generation • 33B • Updated Mar 13, 2025 • 1.64k • 207

Qwen/QwQ-32B

Text Generation • 33B • Updated Mar 11, 2025 • 86.3k • • 2.88k

unsloth/gemma-3-4b-it-GGUF

Image-to-Text • 4B • Updated Aug 14, 2025 • 48k • 164

google/gemma-3-4b-it

Image-Text-to-Text • 4B • Updated Mar 21, 2025 • 816k • 1.11k

liked 2 models over 1 year ago

openai/whisper-large-v3-turbo

Automatic Speech Recognition • 0.8B • Updated Oct 4, 2024 • 2.73M • • 2.77k

meta-llama/Llama-3.1-405B

Text Generation • 406B • Updated Sep 25, 2024 • 266k • 953