Update README.md
Browse files
README.md
CHANGED
|
@@ -38,6 +38,8 @@ model-index:
|
|
| 38 |
|
| 39 |
# ATLAS-8B-Thinking
|
| 40 |
|
|
|
|
|
|
|
| 41 |
**ATLAS-8B-Thinking** is a specialized teacher model developed by Arc Intelligence, designed to solve the core reliability problem in reinforcement learning for LLMs. Standard RL fine-tuning is often brittle, leading to performance degradation where new skills are learned at the expense of old ones.
|
| 42 |
|
| 43 |
This model reframes the training process as one of **effective pedagogy**. Instead of just optimizing a student model, `ATLAS-8B-Thinking` first uses a lightweight **diagnostic probe** to assess the student's reasoning. Based on this diagnosis, it provides **adaptive guidance**—comprehensive help for struggling models and minimal intervention for capable ones. This "do no harm" approach ensures consistent capability improvement without the usual side effects of RL.
|
|
|
|
| 38 |
|
| 39 |
# ATLAS-8B-Thinking
|
| 40 |
|
| 41 |
+
|
| 42 |
+
|
| 43 |
**ATLAS-8B-Thinking** is a specialized teacher model developed by Arc Intelligence, designed to solve the core reliability problem in reinforcement learning for LLMs. Standard RL fine-tuning is often brittle, leading to performance degradation where new skills are learned at the expense of old ones.
|
| 44 |
|
| 45 |
This model reframes the training process as one of **effective pedagogy**. Instead of just optimizing a student model, `ATLAS-8B-Thinking` first uses a lightweight **diagnostic probe** to assess the student's reasoning. Based on this diagnosis, it provides **adaptive guidance**—comprehensive help for struggling models and minimal intervention for capable ones. This "do no harm" approach ensures consistent capability improvement without the usual side effects of RL.
|