GLM-5: from Vibe Coding to Agentic Engineering
Paper
• 2602.15763 • Published
• 82
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
OmniMoE: An Efficient MoE by Orchestrating Atomic Experts at Scale
EgoActor: Grounding Task Planning into Spatial-aware Egocentric Actions for Humanoid Robots via Visual-Language Models
zxdu20
authored a paper 6 days ago
JingzeShi
submitted a paper to Daily Papers 15 days ago
xxuan01
updated a dataset 16 days ago
tellarin
authored 2 papers 19 days ago
tellarin
submitted a paper to Daily Papers 19 days ago
Sri-Vigneshwar-DJ
posted an
update 19 days ago
Post
1381
Just released a new dataset designed for training reasoning models on Meta (Facebook/Instagram) advertising fatigue detection!
What is it? A GRPO (Group Relative Policy Optimization) training dataset with 200+ carefully crafted scenarios covering:
🔍 Fatigue Signal Detection: CTR drops, CPM spikes, frequency analysis
🩺 Performance Diagnosis: Root cause analysis frameworks
📋 Strategy: Creative refresh cadence, testing frameworks
📊 Analysis: ROI calculations, metric interpretation
Why GRPO? GRPO training helps models learn structured reasoning. Each response follows the <thinking> and <answer> format.
Check it out here: Sri-Vigneshwar-DJ/meta-fatigue-grpo-dataset
What is it? A GRPO (Group Relative Policy Optimization) training dataset with 200+ carefully crafted scenarios covering:
🔍 Fatigue Signal Detection: CTR drops, CPM spikes, frequency analysis
🩺 Performance Diagnosis: Root cause analysis frameworks
📋 Strategy: Creative refresh cadence, testing frameworks
📊 Analysis: ROI calculations, metric interpretation
Why GRPO? GRPO training helps models learn structured reasoning. Each response follows the <thinking> and <answer> format.
Check it out here: Sri-Vigneshwar-DJ/meta-fatigue-grpo-dataset
xxuan01
updated 2 datasets 20 days ago
xxuan01
published 2 datasets 22 days ago
xxuan01
updated a collection 22 days ago
xxuan01
published a dataset 22 days ago
ZacLiu
authored a paper 26 days ago
ZmoreZoe
updated a Space 28 days ago
Sri-Vigneshwar-DJ
posted an
update 29 days ago
Post
211
🏙️ Hugging Face Community Post
Title: 🧬 Experimenting with "Dynamic Chaos" in Tamil SLMs
Hi everyone! I just published a new experimental study on Small Language Model (SLM) resilience.
I took the Qwen2.5-0.5B model and put it through a "Chaos Phase" to see how much weight data a tiny model can lose before its understanding of classical Tamil grammar breaks.
Key highlights of the study:
Target Data: Fine-tuned on the Thirukkural (1,330 couplets + modern explanations).
The Chaos Step: Applied 20% random weight pruning but implemented "Layer Protection" for the Token Embeddings and LM Head to keep the characters readable.
Compression: 4-bit (Q4_K_M) quantization for extreme efficiency.
Result: A surrealist classical Tamil model that is ultra-light (~300MB) and ultra-fast!
Check out the model and the experiment logic here: Sri-Vigneshwar-DJ/qwen-tamil-chaos-v1
Title: 🧬 Experimenting with "Dynamic Chaos" in Tamil SLMs
Hi everyone! I just published a new experimental study on Small Language Model (SLM) resilience.
I took the Qwen2.5-0.5B model and put it through a "Chaos Phase" to see how much weight data a tiny model can lose before its understanding of classical Tamil grammar breaks.
Key highlights of the study:
Target Data: Fine-tuned on the Thirukkural (1,330 couplets + modern explanations).
The Chaos Step: Applied 20% random weight pruning but implemented "Layer Protection" for the Token Embeddings and LM Head to keep the characters readable.
Compression: 4-bit (Q4_K_M) quantization for extreme efficiency.
Result: A surrealist classical Tamil model that is ultra-light (~300MB) and ultra-fast!
Check out the model and the experiment logic here: Sri-Vigneshwar-DJ/qwen-tamil-chaos-v1
tanhuajie2001
authored a paper 29 days ago
tanhuajie2001
updated a model 29 days ago