DedeProGames/Terminal-Reasoning-SFT
Updated
• 1
DedeProGames
DedeProGames
·
AI & ML interests
Thinking and Agentic Finetuning
Recent Activity
liked
a dataset about 1 hour ago
DedeProGames/Terminal-Reasoning-SFT updated
a dataset about 2 hours ago
DedeProGames/Terminal-Reasoning-SFT published
a dataset about 2 hours ago
DedeProGames/Terminal-Reasoning-SFT Organizations
None yet
liked a dataset about 1 hour ago
updated a dataset about 2 hours ago
published a dataset about 2 hours ago
liked 2 models about 2 hours ago
Qwen/Qwen3.5-2B
🚀 🔥 2
1
#8367 opened 3 days ago
by
mikaelnias
liked 2 datasets 1 day ago
Qwen/Qwen3.5-0.8B
🚀 6
3
#8368 opened 3 days ago
by
Atlas-0
reacted to OzTianlu's post with 🤗 3 days ago
Post
4739
🔥 UPGRADE in Kai: 30B Scaling! 🔥
NoesisLab/Kai-30B-Instruct
NoesisLab/Kai-30B-Instruct
We are incredibly excited to announce that the Kai-30B-Instruct model and its official Space are now LIVE! 🚀
If you've been following the journey from Kai-0.35B to Kai-3B, you know we're rethinking how models reason. Tired of verbose, slow Chain-of-Thought (CoT) outputs that flood your screen with self-talk? So are we.
Kai-30B-Instruct scales up our Adaptive Dual-Search Distillation (ADS) framework. By bridging classical A* heuristic search with continuous gradient descent , we use an information-theoretic log-barrier to physically prune high-entropy reasoning paths during training.
The result? Pure implicit reasoning. The model executes structured logic, arithmetic carries, and branch selections as a reflex in a single forward pass—no external scaffolding required.
At 3B, we observed a phase transition where the model achieved "logical crystallization". Now, at 30B, we are giving the ADS regularizer the massive representational capacity it needs to tackle higher-order symbolic abstractions and complex reasoning tasks.
🧪 Test Kai yourself in our new Space:
NoesisLab/Kai-30B-Instruct
📦 Model Weights:
NoesisLab/Kai-30B-Instruct
Bring your hardest math, logic, and coding benchmarks. We invite the community to stress-test the limits of the penalty wall! 🧱💥
NoesisLab/Kai-30B-Instruct
NoesisLab/Kai-30B-Instruct
We are incredibly excited to announce that the Kai-30B-Instruct model and its official Space are now LIVE! 🚀
If you've been following the journey from Kai-0.35B to Kai-3B, you know we're rethinking how models reason. Tired of verbose, slow Chain-of-Thought (CoT) outputs that flood your screen with self-talk? So are we.
Kai-30B-Instruct scales up our Adaptive Dual-Search Distillation (ADS) framework. By bridging classical A* heuristic search with continuous gradient descent , we use an information-theoretic log-barrier to physically prune high-entropy reasoning paths during training.
The result? Pure implicit reasoning. The model executes structured logic, arithmetic carries, and branch selections as a reflex in a single forward pass—no external scaffolding required.
At 3B, we observed a phase transition where the model achieved "logical crystallization". Now, at 30B, we are giving the ADS regularizer the massive representational capacity it needs to tackle higher-order symbolic abstractions and complex reasoning tasks.
🧪 Test Kai yourself in our new Space:
NoesisLab/Kai-30B-Instruct
📦 Model Weights:
NoesisLab/Kai-30B-Instruct
Bring your hardest math, logic, and coding benchmarks. We invite the community to stress-test the limits of the penalty wall! 🧱💥
- 1 reply
liked a dataset 4 days ago
updated a model 6 days ago
published a model 6 days ago
published a dataset 6 days ago
updated 2 datasets 6 days ago
published a dataset 6 days ago
updated a collection 7 days ago