Article
Free dataset Optimizer/cleaner + Finetuning + continual learning that actually doesn't forget.
•
2
Kiran N PRO
Fourwheels2512
AI & ML interests
None yet
Recent Activity
posted an update 4 days ago
We trained Mistral 7B, Qwen 8B, Gemma 9B models on 5 domains sequentially to test catastrophic forgetting.
We achieved zero forgetting with medical knowledge retained at 100% after adding enterprise, finance, military, and real estate domains on top.
Most fine-tuned models catastrophically forget everything they learned when you train them on something new. We built a continual learning engine that prevents this. First of its kind.
We're shipping it as a SaaS platform at modelbrew.ai - dataset optimization + fine-tuning + continual learning in one pipeline.
I'm looking for ML fine-tuning engineers and researchers who want to test this. DM me or comment below. new activity 12 days ago
blog-explorers/README:The Next Evolution of AI: From Passive Models to Autonomous SystemsOrganizations
upvoted an article 4 days ago
posted an update 4 days ago
Post
862
We trained Mistral 7B, Qwen 8B, Gemma 9B models on 5 domains sequentially to test catastrophic forgetting.
We achieved zero forgetting with medical knowledge retained at 100% after adding enterprise, finance, military, and real estate domains on top.
Most fine-tuned models catastrophically forget everything they learned when you train them on something new. We built a continual learning engine that prevents this. First of its kind.
We're shipping it as a SaaS platform at modelbrew.ai - dataset optimization + fine-tuning + continual learning in one pipeline.
I'm looking for ML fine-tuning engineers and researchers who want to test this. DM me or comment below.
We achieved zero forgetting with medical knowledge retained at 100% after adding enterprise, finance, military, and real estate domains on top.
Most fine-tuned models catastrophically forget everything they learned when you train them on something new. We built a continual learning engine that prevents this. First of its kind.
We're shipping it as a SaaS platform at modelbrew.ai - dataset optimization + fine-tuning + continual learning in one pipeline.
I'm looking for ML fine-tuning engineers and researchers who want to test this. DM me or comment below.
The Next Evolution of AI: From Passive Models to Autonomous Systems
🚀🔥 2
43
#15 opened 12 days ago
by 
oncody
posted an update 12 days ago
Post
955
Dataset Optimizer (free) + fine tuning + continual learning platform with zero forgetting.
try it at modelbrew.ai
try it at modelbrew.ai
published an article 12 days ago
Article
Free dataset Optimizer/cleaner + Finetuning + continual learning that actually doesn't forget.
•
2
published an article 27 days ago
Article
RAG (vs) Fine-Tuning + continual learning
posted an update about 1 month ago
Post
147
Zero Forgetting in LLM Fine-Tuning — 4 Benchmarks, All Domains Retained
We tested sequential fine-tuning on Mistral-7B across 4 independent benchmarks (5, 4, 5, and 8 domains).
Standard LoRA forgets 38–49% of prior knowledge per domain. Our continual learning adapter: -0.17% drift.
The Salesforce 5-domain test showed positive backward transfer — the model got better at old domains as it learned new ones (retention BERTScore: 0.889 → 0.907).
No replay buffers. No EWC. No knowledge distillation. Spectral norm locked at 1.0. Naive LoRA crashed at gradient norm 263. Ours: under 6.
Interactive benchmark dashboard: Fourwheels2512/zero-forgetting-benchmarks
Live product (free tier): https://mhc-finetune-saas-zrtokzlkbnue9zsk7jfgad.streamlit.app
Patent pending. 7 technical reports. 196 automated tests. Solo founder, 6 months of R&D.
We tested sequential fine-tuning on Mistral-7B across 4 independent benchmarks (5, 4, 5, and 8 domains).
Standard LoRA forgets 38–49% of prior knowledge per domain. Our continual learning adapter: -0.17% drift.
The Salesforce 5-domain test showed positive backward transfer — the model got better at old domains as it learned new ones (retention BERTScore: 0.889 → 0.907).
No replay buffers. No EWC. No knowledge distillation. Spectral norm locked at 1.0. Naive LoRA crashed at gradient norm 263. Ours: under 6.
Interactive benchmark dashboard: Fourwheels2512/zero-forgetting-benchmarks
Live product (free tier): https://mhc-finetune-saas-zrtokzlkbnue9zsk7jfgad.streamlit.app
Patent pending. 7 technical reports. 196 automated tests. Solo founder, 6 months of R&D.
updated a
Space about 1 month ago
published a
Space about 1 month ago
CRMA: Stable Fine-Tuning + Continual Learning for Small LLMs
#2 opened about 2 months ago
by Fourwheels2512
CRMA Fine-Tuner: QLoRA + gradient stability adapter (CRMA + ZClip + PiSSA) for TinyLlama, Gemma, Mistral — ablation results
#1153 opened about 2 months ago
by Fourwheels2512
Built a stability adapter on top of TRL's SFTTrainer (CRMA + ZClip) — sharing ablation results
#1 opened about 2 months ago
by Fourwheels2512
Welcome to CRMA Fine-Tuner — what it does and how to use it
#1 opened about 2 months ago
by Fourwheels2512
CRMA Fine-Tuner: QLoRA + stability adapter (CRMA + ZClip) for TinyLlama, Gemma, Mistral — ablation results inside
#9 opened about 2 months ago
by Fourwheels2512
updated a
Space about 2 months ago
published a
Space about 2 months ago