nvidia
/

Llama-3.1-Nemotron-Nano-4B-v1.1

@@ -38,7 +38,7 @@ GOVERNING TERMS: Your use of this model is governed by the [NVIDIA Open Model Li
 **Model Developer:** NVIDIA
-**Model Dates:** Trained between August 2024 and April 2025
 **Data Freshness:** The pretraining data has a cutoff of 2023 per Meta Llama 3.1 8B
@@ -48,11 +48,11 @@ GOVERNING TERMS: Your use of this model is governed by the [NVIDIA Open Model Li
 Developers designing AI Agent systems, chatbots, RAG systems, and other AI-powered applications. Also suitable for typical instruction-following tasks. Balance of model accuracy and compute efficiency (the model fits on a single RTX GPU and can be used locally).
 ## Release Date: <br>
-x/xx/2025 <br>
 ## References
-- [\[2502.00203\] Reward-aware Preference Optimization: A Unified Mathematical Framework for Model Alignment](https://arxiv.org/abs/2502.00203)
 ## Model Architecture
@@ -223,16 +223,16 @@ These results contain both “Reasoning On”, and “Reasoning Off”. We recom
 | Reasoning Mode | Score |
 |--------------|------------|
-| Reasoning Off | 7.6 |
-| Reasoning On | 8.1 |
 ### MATH500
 | Reasoning Mode | pass@1 |
 |--------------|------------|
-| Reasoning Off | 72.0% |
-| Reasoning On | 95.1%  |
 User Prompt Template:
@@ -246,7 +246,7 @@ User Prompt Template:
 | Reasoning Mode | pass@1 |
 |--------------|------------|
 | Reasoning Off | 13.3% |
-| Reasoning On | 46.7% |
 User Prompt Template:
@@ -259,8 +259,8 @@ User Prompt Template:
 | Reasoning Mode | pass@1 |
 |--------------|------------|
-| Reasoning Off | 31.8% |
-| Reasoning On | 55.8% |
 User Prompt Template:
@@ -274,15 +274,15 @@ User Prompt Template:
 | Reasoning Mode | Strict:Prompt | Strict:Instruction |
 |--------------|------------|------------|
-| Reasoning Off | 73.6% | 80.8% |
-| Reasoning On | 75.4% | 82.6% |
 ### BFCL v2 Live
 | Reasoning Mode | Score |
 |--------------|------------|
-| Reasoning Off | 57.1% |
-| Reasoning On | 64.2% |
 User Prompt Template:
@@ -298,8 +298,8 @@ User Prompt Template:
 | Reasoning Mode | pass@1 |
 |--------------|------------|
-| Reasoning Off | 66.4% |
-| Reasoning On | 86.0% |
 User Prompt Template:

 **Model Developer:** NVIDIA
+**Model Dates:** Trained between August 2024 and May 2025
 **Data Freshness:** The pretraining data has a cutoff of 2023 per Meta Llama 3.1 8B
 Developers designing AI Agent systems, chatbots, RAG systems, and other AI-powered applications. Also suitable for typical instruction-following tasks. Balance of model accuracy and compute efficiency (the model fits on a single RTX GPU and can be used locally).
 ## Release Date: <br>
+5/19/2025 <br>
 ## References
+- [\[2505.00949\] Llama-Nemotron: Efficient Reasoning Models](https://arxiv.org/abs/2505.00949)
 ## Model Architecture
 | Reasoning Mode | Score |
 |--------------|------------|
+| Reasoning Off | 7.4 |
+| Reasoning On | 8.0 |
 ### MATH500
 | Reasoning Mode | pass@1 |
 |--------------|------------|
+| Reasoning Off | 71.8% |
+| Reasoning On | 96.2%  |
 User Prompt Template:
 | Reasoning Mode | pass@1 |
 |--------------|------------|
 | Reasoning Off | 13.3% |
+| Reasoning On | 46.3% |
 User Prompt Template:
 | Reasoning Mode | pass@1 |
 |--------------|------------|
+| Reasoning Off | 33.8% |
+| Reasoning On | 55.1% |
 User Prompt Template:
 | Reasoning Mode | Strict:Prompt | Strict:Instruction |
 |--------------|------------|------------|
+| Reasoning Off | 70.1% | 78.5% |
+| Reasoning On | 75.5% | 82.6% |
 ### BFCL v2 Live
 | Reasoning Mode | Score |
 |--------------|------------|
+| Reasoning Off | 63.6% |
+| Reasoning On | 67.9% |
 User Prompt Template:
 | Reasoning Mode | pass@1 |
 |--------------|------------|
+| Reasoning Off | 61.9% |
+| Reasoning On | 85.8% |
 User Prompt Template: