Update README.md
Browse files
README.md
CHANGED
|
@@ -17,6 +17,8 @@ tags:
|
|
| 17 |
- code
|
| 18 |
---
|
| 19 |
|
|
|
|
|
|
|
| 20 |
# Magpie-Qwen-CortexDual-0.6B
|
| 21 |
|
| 22 |
> **Magpie-Qwen-CortexDual-0.6B** is a specialized, general-purpose model designed for **math**, **code**, and **structured reasoning**. Built with **CortexDual thinking mode**, it dynamically adapts to the complexity of a problem, automatically shifting into a stepwise reasoning mode for intricate logic or math tasks. This 0.6B parameter model leverages **80% of the Magpie Pro 330k dataset** and a modular blend of datasets for general-purpose proficiency and domain versatility.
|
|
@@ -94,6 +96,21 @@ print(response)
|
|
| 94 |
|
| 95 |
---
|
| 96 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 97 |
## Intended Use
|
| 98 |
|
| 99 |
* General-purpose problem solving in math, logic, and code
|
|
|
|
| 17 |
- code
|
| 18 |
---
|
| 19 |
|
| 20 |
+

|
| 21 |
+
|
| 22 |
# Magpie-Qwen-CortexDual-0.6B
|
| 23 |
|
| 24 |
> **Magpie-Qwen-CortexDual-0.6B** is a specialized, general-purpose model designed for **math**, **code**, and **structured reasoning**. Built with **CortexDual thinking mode**, it dynamically adapts to the complexity of a problem, automatically shifting into a stepwise reasoning mode for intricate logic or math tasks. This 0.6B parameter model leverages **80% of the Magpie Pro 330k dataset** and a modular blend of datasets for general-purpose proficiency and domain versatility.
|
|
|
|
| 96 |
|
| 97 |
---
|
| 98 |
|
| 99 |
+
## Demo Inference
|
| 100 |
+
|
| 101 |
+
> [!warning]
|
| 102 |
+
non-thinking (direct, reactive, retrieval-based responses)
|
| 103 |
+
|
| 104 |
+

|
| 105 |
+
|
| 106 |
+
> [!warning]
|
| 107 |
+
thinking (reasoning, planning, deeper analysis)
|
| 108 |
+
|
| 109 |
+

|
| 110 |
+

|
| 111 |
+
|
| 112 |
+
---
|
| 113 |
+
|
| 114 |
## Intended Use
|
| 115 |
|
| 116 |
* General-purpose problem solving in math, logic, and code
|