Update README.md

README.md

@@ -23,8 +23,8 @@ language:
 
 1. [Model Summary](#model-summary)
 2. [Evaluation](#evaluation)
-3. [Limitations](#limitations)
-4. [Training](#training)
+3. [Training](#training)
+4. [Limitations](#limitations)
 5. [License](#license)
 
 ## Model Summary
@@ -161,13 +161,8 @@ Evaluation results in reasoning mode for SmolLM3 and Qwen3 models:
 | Graduate-level reasoning | GPQA Diamond | **41.7** | 39.9 | **55.3** |
 | Instruction following | IFEval | 71.2 | **74.2** | **85.4** |
 | Alignment | MixEval Hard | 30.8 | **33.9** | **38.0** |
-| Alignment | AlpacaEval | **53.7** | 43.4 | **61.6** |
 | Multilingual Q&A | Global MMLU | **64.1** | 62.3 | **73.3** |
 
-## Limitations
-
-SmolLM3 can produce text on a variety of topics, but the generated content may not always be factually accurate, logically consistent, or free from biases present in the training data. These models should be used as assistive tools rather than definitive sources of information. Users should always verify important information and critically evaluate any generated content.
-
 ## Training
 
 ### Model
@@ -183,12 +178,16 @@ SmolLM3 can produce text on a variety of topics, but the generated content may n
 - **Data processing framework:** [datatrove](https://github.com/huggingface/datatrove)
 - **Evaluation framework:** [lighteval](https://github.com/huggingface/lighteval)
 - **Postraining Framework:** [TRL](https://github.com/huggingface/trl)
-  
+
 ### Open resources
 Here is an infographic with all the training details [TODO]. 
 - The datasets used for pretraining can be found in this [collection](https://huggingface.co/collections/HuggingFaceTB/smollm3-pretraining-datasets-685a7353fdc01aecde51b1d9) and those used in mid-training and pos-training can be found here [TODO]
 - The training and evaluation configs and code can be found in the [huggingface/smollm](https://github.com/huggingface/smollm) repository.
 
+## Limitations
+
+SmolLM3 can produce text on a variety of topics, but the generated content may not always be factually accurate, logically consistent, or free from biases present in the training data. These models should be used as assistive tools rather than definitive sources of information. Users should always verify important information and critically evaluate any generated content.
+
 
 ## License
 [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)