Update README.md

README.md

@@ -4,15 +4,21 @@ language:
 - en
 pipeline_tag: text-generation
 base_model:
-- allenai/OLMo-2-1124-7B-DPO
+- allenai/OLMo-2-1124-13B-DPO
 library_name: transformers
 datasets:
-- allenai/RLVR-GSM
+- allenai/RLVR-GSM-MATH-IF-Mixed-Constraints
 ---
 
 <img alt="OLMo Logo" src="https://huggingface.co/datasets/allenai/blog-images/resolve/main/olmo2/olmo.png" width="242px">
 
-# OLMo-2-1124-7B-Instruct
+# OLMo-2-1124-13B-Instruct
+
+## NOTE: 12/18/2024 UPDATE:
+
+Upon the initial release of OLMo-2 models, we realized the post-trained models did not share the pre-tokenization logic that the base models use. As a result, we have trained new post-trained models. The new models are available under the same names as the original models, but we have made the old models available with a postfix "-legacy". See [OLMo 2 Legacy Post-trained Models](https://huggingface.co/collections/allenai/olmo-2-legacy-post-trained-models-6762f662c660962e52de7c96) for the colleciton of the legacy models.
+
+## Release Documentation
 
 OLMo 2 7B Instruct November 2024 is post-trained variant of the [OLMo-2 7B November 2024](https://huggingface.co/allenai/OLMo2-7B-1124) model, which has undergone supervised finetuning on an OLMo-specific variant of the [Tülu 3 dataset](allenai/tulu-3-sft-olmo-2-mixture) and further DPO training on [this dataset](https://huggingface.co/datasets/allenai/olmo-2-1124-7b-preference-mix), and finally RLVR training using [this data](https://huggingface.co/datasets/allenai/RLVR-GSM).
 Tülu 3 is designed for state-of-the-art performance on a diversity of tasks in addition to chat, such as MATH, GSM8K, and IFEval.
@@ -29,7 +35,7 @@ The core models released in this batch include the following:
 | **SFT**              | [allenai/OLMo-2-1124-7B-SFT](https://huggingface.co/allenai/OLMo-2-1124-7B-SFT)                | [allenai/OLMo-2-1124-13B-SFT](https://huggingface.co/allenai/OLMo-2-1124-13B-SFT)              |
 | **DPO**              | [allenai/OLMo-2-1124-7B-DPO](https://huggingface.co/allenai/OLMo-2-1124-7B-DPO)                | [allenai/OLMo-2-1124-13B-DPO](https://huggingface.co/allenai/OLMo-2-1124-13B-DPO)              |
 | **Final Models (RLVR)** | [allenai/OLMo-2-1124-7B-Instruct](https://huggingface.co/allenai/OLMo-2-1124-7B-Instruct)                        | [allenai/OLMo-2-1124-13B-Instruct](https://huggingface.co/allenai/OLMo-2-1124-13B-Instruct)                      |
-| **Reward Model (RM)**| [allenai/OLMo-2-1124-7B-RM](https://huggingface.co/allenai/OLMo-2-1124-7B-RM)                                                     | (Same as 7B)                                                     |
+| **Reward Model (RM)**| [allenai/OLMo-2-1124-7B-RM](https://huggingface.co/allenai/OLMo-2-1124-7B-RM)                                                     | [allenai/OLMo-2-1124-13B-RM](https://huggingface.co/allenai/OLMo-2-1124-13B-RM)                                                     |
 
 
 
@@ -121,6 +127,7 @@ See the Falcon 180B model card for an example of this.
 | **OLMo-2-7B-1124–Instruct** | 54.8 | 29.1 | 46.6 | 60.5 | 85.1 | 72.3 | 32.5 | 61.3 | 80.6 | 23.2 | 56.5 |
 | **OLMo-2-13B-1124-Instruct** | 62.0 | 39.5 | 58.8 | 71.5 | 87.4 | 82.6 | 39.2 | 68.5 | 79.1 | 28.8 | 64.3 |
 
+
 ## License and use
 
 OLMo 2 is licensed under the Apache 2.0 license.