MachinaCheck: Building a Multi-Agent CNC Manufacturability System on AMD MI300X
• 1
AI & ML interests
None defined yet.
Recent Activity
View all activity
Articles
Shrijanagain
posted an update about 17 hours ago
Post
50
🚀 Big News for the AI Community! 🔥
We’re excited to release NRS_QWEN_MYTHOS_1M — a powerful reasoning model built on Qwen 3.5 9B!
At SKT AI LABS, we’ve supercharged this 9B model with our proprietary Neural Reasoning System (NRS) to deliver next-level performance.
🔥 Why This Model is a Game-Changer:
✅ 100x Reasoning Capacity — Exceptional deep logical thinking and complex problem-solving
✅ 1 Million Token Context — Perfect for massive codebases, long documents, and multi-turn agentic workflows
✅ Advanced Thinking Mode — Native <think> tags for true step-by-step Chain-of-Thought reasoning
✅ Tool-Use Ready — Optimized for Python execution, Web Search, and self-correction
✅ Blazing Fast — Runs smoothly on consumer GPUs like RTX 3090/4090
Technical Highlights:
Base: Qwen 3.5 9B
Tuning: NRS-specific high-quality reasoning data
Context: 1M Tokens (YaRN Scaling)
License: NRS DOCS
Whether you’re a developer building coding agents, a researcher working with long-context data, or someone who loves powerful reasoning — this model is built for you.
👉 Try it now on Hugging Face:
SKT-NRS/NRS_QWEN_MYTHOS_1M
Drop a comment: What will you build with it first? 👇
#AI #OpenSource #LLM #Qwen #ReasoningModel #HuggingFace #NewModel #AICommunity
We’re excited to release NRS_QWEN_MYTHOS_1M — a powerful reasoning model built on Qwen 3.5 9B!
At SKT AI LABS, we’ve supercharged this 9B model with our proprietary Neural Reasoning System (NRS) to deliver next-level performance.
🔥 Why This Model is a Game-Changer:
✅ 100x Reasoning Capacity — Exceptional deep logical thinking and complex problem-solving
✅ 1 Million Token Context — Perfect for massive codebases, long documents, and multi-turn agentic workflows
✅ Advanced Thinking Mode — Native <think> tags for true step-by-step Chain-of-Thought reasoning
✅ Tool-Use Ready — Optimized for Python execution, Web Search, and self-correction
✅ Blazing Fast — Runs smoothly on consumer GPUs like RTX 3090/4090
Technical Highlights:
Base: Qwen 3.5 9B
Tuning: NRS-specific high-quality reasoning data
Context: 1M Tokens (YaRN Scaling)
License: NRS DOCS
Whether you’re a developer building coding agents, a researcher working with long-context data, or someone who loves powerful reasoning — this model is built for you.
👉 Try it now on Hugging Face:
SKT-NRS/NRS_QWEN_MYTHOS_1M
Drop a comment: What will you build with it first? 👇
#AI #OpenSource #LLM #Qwen #ReasoningModel #HuggingFace #NewModel #AICommunity
Update README.md
#1 opened 12 days ago
by 
Achoyyy
Shrijanagain
posted an update about 1 month ago
Post
2611
We are pleased to announce that the W-IMG Vision Dataset infrastructure is officially live.
The complete asset infrastructure is now accessible on Hugging Face for internal validation and architecture scaling targets.
Dataset Endpoint - sKT-Ai-Labs/W-IMG
#SovereignAI #ComputerVision #MachineLearning #OpenSource
The complete asset infrastructure is now accessible on Hugging Face for internal validation and architecture scaling targets.
Dataset Endpoint - sKT-Ai-Labs/W-IMG
#SovereignAI #ComputerVision #MachineLearning #OpenSource
Add model card: architecture, training, usage, limitations
#1 opened about 1 month ago
by 
Yatsuiii
fix: conditional Ollama timeout — 5s when vLLM primary, 240s otherwise
#3 opened about 1 month ago
by 
msradam
fix: cold-start, keepalives, vLLM readiness probe, fast Ollama fallback timeout
#2 opened about 1 month ago
by msradam
fix: cold-start timeouts, keepalives, vLLM probe, fast-Ollama-fallback
#1 opened about 1 month ago
by msradam
Post
148
Shipped StudioMI300 for the AMD x lablab hackathon. One English sentence becomes a 30-second cinematic reel, end-to-end on a single AMD Instinct MI300X.
Every model in the pipeline is Apache 2.0 or MIT.
🎬 Director Agent — Qwen3.5-35B-A3B via vLLM with AITER MoE acceleration. Plans 6 shots, character bibles, music brief, per-shot voice-over.
🎨 Character keyframes — FLUX.2 klein 4B reference editing. No LoRA training step. Identity stays consistent across shots by construction.
🎞️ Animation — Wan2.2-I2V-A14B with ParaAttention FBCache (lossless 2x) and selective torch.compile on transformer_2 (another 1.2x). End-to-end Wan2.2 inference went from 25.9 min to 10.4 min per 720p clip.
🔍 Vision Critic — same Qwen3.5 checkpoint reloaded with a 10-label failure taxonomy (character drift, extras invade frame, camera ignored, walking backwards, hand artifact, wardrobe drift, neon glow leak, stylized AI look, random intimacy, object morphing). Bad clips auto-retry with targeted strategies. Up to 3 attempts.
🎵 Music — ACE-Step v1 generates 30s instrumental from Director's brief.
🗣️ Narration — Kokoro-82M, 9 languages. Director picks language to match setting. Tokyo to Japanese, Paris to French, Mumbai to Hindi.
The 192 GB HBM3 on MI300X is what lets four very different model architectures share one card sequentially. On a 24 GB consumer GPU this stack needs 4-5 separate machines wired together.
Space (live infra restoring after hackathon close, pls like this space):
lablab-ai-amd-developer-hackathon/studiomi300
Code (Apache 2.0):
https://github.com/bladedevoff/studiomi300
Special thanks to the FLUX, Wan2.2, ACE-Step and Kokoro teams for keeping serious generative AI open. The pipeline composes their work into something none of them alone can produce — a complete cinematic artifact from a single prompt.
#AMDHackathon #ROCm #MI300X #OpenSource
Every model in the pipeline is Apache 2.0 or MIT.
🎬 Director Agent — Qwen3.5-35B-A3B via vLLM with AITER MoE acceleration. Plans 6 shots, character bibles, music brief, per-shot voice-over.
🎨 Character keyframes — FLUX.2 klein 4B reference editing. No LoRA training step. Identity stays consistent across shots by construction.
🎞️ Animation — Wan2.2-I2V-A14B with ParaAttention FBCache (lossless 2x) and selective torch.compile on transformer_2 (another 1.2x). End-to-end Wan2.2 inference went from 25.9 min to 10.4 min per 720p clip.
🔍 Vision Critic — same Qwen3.5 checkpoint reloaded with a 10-label failure taxonomy (character drift, extras invade frame, camera ignored, walking backwards, hand artifact, wardrobe drift, neon glow leak, stylized AI look, random intimacy, object morphing). Bad clips auto-retry with targeted strategies. Up to 3 attempts.
🎵 Music — ACE-Step v1 generates 30s instrumental from Director's brief.
🗣️ Narration — Kokoro-82M, 9 languages. Director picks language to match setting. Tokyo to Japanese, Paris to French, Mumbai to Hindi.
The 192 GB HBM3 on MI300X is what lets four very different model architectures share one card sequentially. On a 24 GB consumer GPU this stack needs 4-5 separate machines wired together.
Space (live infra restoring after hackathon close, pls like this space):
lablab-ai-amd-developer-hackathon/studiomi300
Code (Apache 2.0):
https://github.com/bladedevoff/studiomi300
Special thanks to the FLUX, Wan2.2, ACE-Step and Kokoro teams for keeping serious generative AI open. The pipeline composes their work into something none of them alone can produce — a complete cinematic artifact from a single prompt.
#AMDHackathon #ROCm #MI300X #OpenSource
space: interactive replay demo — fast-forward 22s through real generation stages, with 6 real SF walk keyframes
#3 opened about 1 month ago
by 
pollix
space: interactive replay demo
#1 opened about 2 months ago
by pollix
space: add 6 real keyframes (SF walk) for replay demo
#2 opened about 2 months ago
by pollix
athena129
updated a
collection about 2 months ago
Sourabh-Kumar04
updated a
Space about 2 months ago
pollix
updated a
Space about 2 months ago
pollix
updated a
collection about 2 months ago
pollix
published a
Space about 2 months ago
Sourabh-Kumar04
published a
Space about 2 months ago
pollix
updated a
collection about 2 months ago
emmanuelakbi
updated a
Space about 2 months ago
Shrijanagain
updated a
collection about 2 months ago