Update README.md
Browse files
README.md
CHANGED
|
@@ -21,7 +21,7 @@ This SAI-DeepCoder-14B-Preview-v1.0 model is fine-tuned with policy-grounded dat
|
|
| 21 |
## Model Card
|
| 22 |
|
| 23 |
|
| 24 |
-
##
|
| 25 |
DeepCoder-14B-Preview is a code reasoning LLM fine-tuned from DeepSeek-R1-Distilled-Qwen-14B using distributed reinforcement learning (RL) to scale up to long context lengths. The model achieves 60.6% Pass@1 accuracy on LiveCodeBench v5 (8/1/24-2/1/25), representing a 8% improvement over the base model (53%) and achieving similar performance to OpenAI's o3-mini with just 14B parameters.
|
| 26 |
|
| 27 |
<div style="margin: 0 auto;">
|
|
|
|
| 21 |
## Model Card
|
| 22 |
|
| 23 |
|
| 24 |
+
## SAI-DeepCoder-14B-Preview-v1.0 Overview
|
| 25 |
DeepCoder-14B-Preview is a code reasoning LLM fine-tuned from DeepSeek-R1-Distilled-Qwen-14B using distributed reinforcement learning (RL) to scale up to long context lengths. The model achieves 60.6% Pass@1 accuracy on LiveCodeBench v5 (8/1/24-2/1/25), representing a 8% improvement over the base model (53%) and achieving similar performance to OpenAI's o3-mini with just 14B parameters.
|
| 26 |
|
| 27 |
<div style="margin: 0 auto;">
|