Update README.md
Browse files
README.md
CHANGED
|
@@ -25,6 +25,10 @@ tags:
|
|
| 25 |
|
| 26 |
> **Canum-Qwen3\_R1-4B-iCoT** is a precision-tuned variant of the Qwen3-4B architecture, explicitly aligned with **internal chain-of-thought (iCoT)** methodologies. Trained on the **TAUR-dev/STEPS\_\_r1\_4d\_eval\_\_mini\_all** dataset, this model excels in **long-form mathematical reasoning**, **progressive symbolic logic**, and **multi-stage problem decomposition**, all within a compact 4B parameter footprint.
|
| 27 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
## Key Features
|
| 29 |
|
| 30 |
1. **Internal Chain-of-Thought Reasoning (iCoT)**
|
|
|
|
| 25 |
|
| 26 |
> **Canum-Qwen3\_R1-4B-iCoT** is a precision-tuned variant of the Qwen3-4B architecture, explicitly aligned with **internal chain-of-thought (iCoT)** methodologies. Trained on the **TAUR-dev/STEPS\_\_r1\_4d\_eval\_\_mini\_all** dataset, this model excels in **long-form mathematical reasoning**, **progressive symbolic logic**, and **multi-stage problem decomposition**, all within a compact 4B parameter footprint.
|
| 27 |
|
| 28 |
+
> [!note]
|
| 29 |
+
GGUF : https://huggingface.co/prithivMLmods/Canum-Qwen3_R1-4B-iCoT-Q4_K_M-GGUF
|
| 30 |
+
|
| 31 |
+
|
| 32 |
## Key Features
|
| 33 |
|
| 34 |
1. **Internal Chain-of-Thought Reasoning (iCoT)**
|