Article
Liberate your OpenClaw
- +6
•
30
Anthony Loyola PRO
LOYOLABIZ
AI & ML interests
None yet
Recent Activity
upvoted an article about 5 hours ago
Liberate your OpenClaw upvoted an article about 5 hours ago
Welcome Gemma 4: Frontier multimodal intelligence on device liked a model about 6 hours ago
DavidAU/gemma-4-31B-it-Mystery-Fine-Tune-HERETIC-UNCENSORED-Thinking-Instruct-GGUFOrganizations
upvoted 2
articles about 5 hours ago
Article
Welcome Gemma 4: Frontier multimodal intelligence on device
- +5
•
464
liked a
model about 6 hours ago
liked a
model about 18 hours ago
reactedto PhysiQuanty's post with 🚀🔥 about 22 hours ago
Post
1947
🇫🇷 French PATENT DataSet
🚀 800k patent (1981-2026)
INPI-France/FR-Patent-2020-2026-Raw
INPI-France/FR-Patent-2020-Claims
INPI-France/FR-Patent-2024-Chunked
INPI-France/Brevets-Francais-1981-2026-Raw
🔓 API/FTP INPI ACCESS
🔑 Access to the API/FTP INPI : https://data.inpi.fr/content/editorial/apis_pi
🚀 800k patent (1981-2026)
INPI-France/FR-Patent-2020-2026-Raw
INPI-France/FR-Patent-2020-Claims
INPI-France/FR-Patent-2024-Chunked
INPI-France/Brevets-Francais-1981-2026-Raw
🔓 API/FTP INPI ACCESS
🔑 Access to the API/FTP INPI : https://data.inpi.fr/content/editorial/apis_pi
reactedto shriarul5273's post with 🚀 1 day ago
Post
2208
🔁 One API. 12 model families. 28 variants. Why depth_estimation makes depth research easier
Switching between depth models usually means rewriting preprocessing, adapting outputs, and dealing with different codebases.
depth_estimation removes that friction.
With the same interface, you can work with:
🌊 Depth Anything
🍎 DepthPro
🧭 MiDaS
📏 ZoeDepth
🧩 MoGe
🛰️ VGGT / OmniVGGT
and more
Change one model string, keep the rest of your workflow the same.
That makes it much easier to:
⚖️ compare models fairly
🧪 prototype quickly
📈 benchmark consistently
🛠️ build reusable depth pipelines
GitHub: https://github.com/shriarul5273/depth_estimation
#depthestimation #research #computervision #python #machinelearning #opensource #pytorch
Switching between depth models usually means rewriting preprocessing, adapting outputs, and dealing with different codebases.
depth_estimation removes that friction.
With the same interface, you can work with:
🌊 Depth Anything
🍎 DepthPro
🧭 MiDaS
📏 ZoeDepth
🧩 MoGe
🛰️ VGGT / OmniVGGT
and more
Change one model string, keep the rest of your workflow the same.
That makes it much easier to:
⚖️ compare models fairly
🧪 prototype quickly
📈 benchmark consistently
🛠️ build reusable depth pipelines
GitHub: https://github.com/shriarul5273/depth_estimation
#depthestimation #research #computervision #python #machinelearning #opensource #pytorch
reactedto ArtelTaleb's post with 🚀❤️ 1 day ago
Post
2622
Hello 3D lover !
You have a 3D model sitting somewhere and just want to see it
no software to install, no account to create.
Canva3D is a free browser viewer built for that exact moment.
Drop any format — GLB, OBJ, FBX, STL, USDZ — it just loads.
Swap the background with HDRI lighting to set the mood of your scene.
Record a video ready to share — orbit, animate, export.
That's it. No settings to configure. No GPU required.
______________________________________________________
Bonjour les amoureux de la 3D
T'as un modèle 3D quelque part et tu veux juste le voir sans logiciel à
installer, sans compte à créer.
Canva3D est un viewer gratuit dans le navigateur, fait exactement pour ça.
Glisse n'importe quel format — GLB, OBJ, FBX, STL, USDZ —
il charge direct.
Change le fond avec un éclairage HDRI pour poser l'ambiance de ta scène.
Enregistre une vidéo prête à partager — orbite, anime, exporte.
C'est tout. Rien à configurer. Pas besoin de GPU.
👉 ArtelTaleb/canva3d
You have a 3D model sitting somewhere and just want to see it
no software to install, no account to create.
Canva3D is a free browser viewer built for that exact moment.
Drop any format — GLB, OBJ, FBX, STL, USDZ — it just loads.
Swap the background with HDRI lighting to set the mood of your scene.
Record a video ready to share — orbit, animate, export.
That's it. No settings to configure. No GPU required.
______________________________________________________
Bonjour les amoureux de la 3D
T'as un modèle 3D quelque part et tu veux juste le voir sans logiciel à
installer, sans compte à créer.
Canva3D est un viewer gratuit dans le navigateur, fait exactement pour ça.
Glisse n'importe quel format — GLB, OBJ, FBX, STL, USDZ —
il charge direct.
Change le fond avec un éclairage HDRI pour poser l'ambiance de ta scène.
Enregistre une vidéo prête à partager — orbite, anime, exporte.
C'est tout. Rien à configurer. Pas besoin de GPU.
👉 ArtelTaleb/canva3d
reactedto ArtelTaleb's post with 🔥 1 day ago
Post
2756
Hey Music Lovers !
You have a track and you want the stems.
Retro 6stems splits any audio file into 6 clean, separated tracks
Drop an MP3, WAV, FLAC or M4A — Demucs gets to work immediately with a minimal retro design .
Instrumental mix included automatically
Vocals
Drums
Bass
Guitar
Piano
Other (strings, synths...)
Preview each stem directly in the browser, download individually or grab the full ZIP.
No install. No GPU needed on your end. Just upload and wait.
👉 ArtelTaleb/retro-6stems
You have a track and you want the stems.
Retro 6stems splits any audio file into 6 clean, separated tracks
Drop an MP3, WAV, FLAC or M4A — Demucs gets to work immediately with a minimal retro design .
Instrumental mix included automatically
Vocals
Drums
Bass
Guitar
Piano
Other (strings, synths...)
Preview each stem directly in the browser, download individually or grab the full ZIP.
No install. No GPU needed on your end. Just upload and wait.
👉 ArtelTaleb/retro-6stems
liked 2
models 2 days ago
liked 4
models 3 days ago
mradermacher/Llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-i1-GGUF
8B • Updated • 74.5k • 36
mradermacher/OpenAI-gpt-oss-20B-Claude-4.5-Opus-Heretic-Uncensored-i1-GGUF
21B • Updated • 52.3k • 42
askalgore/Phi-3.5-mini-instruct-heretic
Text Generation • 4B • Updated • 12 • 1
mradermacher/Llama-3.1-KoEn-8b-Coder-DARE-i1-GGUF
8B • Updated • 110 • 3
reactedto SeaWolf-AI's post with 🚀 3 days ago
Post
2106
🧬 Darwin-35B-A3B-Opus — The Child That Surpassed Both Parents
What if a merged model could beat both its parents? We proved it can.
Darwin-35B-A3B-Opus is a 35B MoE model (3B active) built with our Darwin V5 engine — the first evolution system that CT-scans parent models before merging them.
🤗 Model: FINAL-Bench/Darwin-35B-A3B-Opus
The result speaks for itself: GPQA Diamond 90.0%, versus Father (Qwen3.5-35B-A3B) at 84.2% and Mother (Claude 4.6 Opus Distilled) at 85.0%. That's +6.9% over Father and +5.9% over Mother. Not a tradeoff — a genuine leap. Meanwhile, MMMLU sits at 85.0% (Father: 85.2%), multimodal is fully intact, and all 201 languages are preserved.
How? Model MRI changed everything. Traditional merging is guesswork. Darwin V4 added evolution. Darwin V5 added X-ray vision. Model MRI scans each parent layer by layer and discovers: Mother's L34–L38 is the reasoning engine (peak cosine distance), 50–65% of Mother's experts are dead (killed by text-only distillation), and Father is a healthy generalist with every expert alive. The prescription: transplant Mother's reasoning brain at L38 (90% weight), replace her dead experts with Father's living ones, and let Father's router handle the output layer. Reasoning went up. Versatility stayed intact. No tradeoff — just evolution.
35B total, 3B active (MoE) · GPQA Diamond 90.0% · MMMLU 85.0% (201 languages) · Multimodal Image & Video · 262K native context · 147.8 tok/s on H100 · Runs on a single RTX 4090 (Q4) · Apache 2.0
Darwin V5's full algorithm and technical details will be released alongside an upcoming paper.
🚀 Live Demo: FINAL-Bench/Darwin-35B-A3B-Opus
🏆 FINAL Bench Leaderboard: FINAL-Bench/Leaderboard
📊 ALL Bench Leaderboard: FINAL-Bench/all-bench-leaderboard
Built by VIDRAFT · Supported by the Korean Government GPU Support Program
What if a merged model could beat both its parents? We proved it can.
Darwin-35B-A3B-Opus is a 35B MoE model (3B active) built with our Darwin V5 engine — the first evolution system that CT-scans parent models before merging them.
🤗 Model: FINAL-Bench/Darwin-35B-A3B-Opus
The result speaks for itself: GPQA Diamond 90.0%, versus Father (Qwen3.5-35B-A3B) at 84.2% and Mother (Claude 4.6 Opus Distilled) at 85.0%. That's +6.9% over Father and +5.9% over Mother. Not a tradeoff — a genuine leap. Meanwhile, MMMLU sits at 85.0% (Father: 85.2%), multimodal is fully intact, and all 201 languages are preserved.
How? Model MRI changed everything. Traditional merging is guesswork. Darwin V4 added evolution. Darwin V5 added X-ray vision. Model MRI scans each parent layer by layer and discovers: Mother's L34–L38 is the reasoning engine (peak cosine distance), 50–65% of Mother's experts are dead (killed by text-only distillation), and Father is a healthy generalist with every expert alive. The prescription: transplant Mother's reasoning brain at L38 (90% weight), replace her dead experts with Father's living ones, and let Father's router handle the output layer. Reasoning went up. Versatility stayed intact. No tradeoff — just evolution.
35B total, 3B active (MoE) · GPQA Diamond 90.0% · MMMLU 85.0% (201 languages) · Multimodal Image & Video · 262K native context · 147.8 tok/s on H100 · Runs on a single RTX 4090 (Q4) · Apache 2.0
Darwin V5's full algorithm and technical details will be released alongside an upcoming paper.
🚀 Live Demo: FINAL-Bench/Darwin-35B-A3B-Opus
🏆 FINAL Bench Leaderboard: FINAL-Bench/Leaderboard
📊 ALL Bench Leaderboard: FINAL-Bench/all-bench-leaderboard
Built by VIDRAFT · Supported by the Korean Government GPU Support Program
- 8 replies
liked a
model 3 days ago
reactedto alibidaran's post with 🔥 3 days ago
Post
1986
🧠 Introducing Qwen3.5 — Cognitive Reasoning Mode
I fine-tuned Qwen2.5 with GRPO to actually think before it answers — not just pattern-match.
Most LLMs mimic reasoning. This one builds a real cognitive path:
📌 Plan → understand the task
🔍 Monitor → reason step by step
✅ Evaluate → verify before answering
Every response follows a strict structured protocol:
<think> <planning> ... <monitoring> ... <evaluation> ... </think>
Then a clean, reasoning-free <output>.
The model self-checks its own structure. If a section is missing or malformed → the response is invalid.
This isn't chain-of-thought slapped on top. The reasoning protocol is baked in via RL.
🔗 Full README + inference code below 👇
alibidaran/Qwen_COG_Thinker_Merged
#AI #LLM #Qwen #ReasoningModels #GRPO #OpenSource
I fine-tuned Qwen2.5 with GRPO to actually think before it answers — not just pattern-match.
Most LLMs mimic reasoning. This one builds a real cognitive path:
📌 Plan → understand the task
🔍 Monitor → reason step by step
✅ Evaluate → verify before answering
Every response follows a strict structured protocol:
<think> <planning> ... <monitoring> ... <evaluation> ... </think>
Then a clean, reasoning-free <output>.
The model self-checks its own structure. If a section is missing or malformed → the response is invalid.
This isn't chain-of-thought slapped on top. The reasoning protocol is baked in via RL.
🔗 Full README + inference code below 👇
alibidaran/Qwen_COG_Thinker_Merged
#AI #LLM #Qwen #ReasoningModels #GRPO #OpenSource
- 2 replies
repliedto sergiopaniego's post 3 days ago
WooHo