allenai
/

OLMo-2-0325-32B

Text Generation

Transformers

Safetensors

English

olmo2

Model card Files Files and versions Community

amanrangapur commited on 16 days ago

Commit

39ac4d3

verified ·

1 Parent(s): 8d2d36b

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -5

README.md CHANGED Viewed

@@ -26,11 +26,11 @@ The core models released in this batch include the following:
 | **Stage**           | **OLMo 2 32B**                                                                                          | **OLMo 2 13B**                                                                                         | **OLMo 2 7B**
 |----------------------|----------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------|
-| **Base Model**       | [allenai/OLMo-2-0325-32B](https://huggingface.co/allenai/OLMo-2-1124-7B)                                | [allenai/OLMo-2-1124-13B](https://huggingface.co/allenai/OLMo-2-1124-13B)                             | [allenai/OLMo-2-1124-7B](https://huggingface.co/allenai/OLMo-2-1124-7B)                                |
-| **SFT**              | [allenai/OLMo-2-0325-32B-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)              | [allenai/OLMo-2-1124-7B-SFT](https://huggingface.co/allenai/OLMo-2-1124-7B-SFT)                |
-| **DPO**              | [allenai/OLMo-2-0325-32B-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)              | [allenai/OLMo-2-1124-7B-DPO](https://huggingface.co/allenai/OLMo-2-1124-7B-DPO)                |
-| **Final Models (RLVR)** | [allenai/OLMo-2-0325-32B-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)                      | [allenai/OLMo-2-1124-7B-Instruct](https://huggingface.co/allenai/OLMo-2-1124-7B-Instruct)                        |
-| **Reward Model (RM)**| [allenai/OLMo-2-0325-32B-RM](https://huggingface.co/allenai/OLMo-2-1124-7B-RM)                                                     | (Same as 7B)                                                     | [allenai/OLMo-2-1124-7B-RM](https://huggingface.co/allenai/OLMo-2-1124-7B-RM)                                                     |
 ## Installation
@@ -81,6 +81,7 @@ from huggingface_hub import list_repo_refs
 out = list_repo_refs("allenai/OLMo-2-0325-32B")
 branches = [b.name for b in out.branches]
 ```
 ### Fine-tuning
 Model fine-tuning can be done from the final checkpoint (the `main` revision of this model) or many intermediate checkpoints. Two recipes for tuning are available.

 | **Stage**           | **OLMo 2 32B**                                                                                          | **OLMo 2 13B**                                                                                         | **OLMo 2 7B**
 |----------------------|----------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------|
+| **Base Model**       | [allenai/OLMo-2-0325-32B](https://huggingface.co/allenai/OLMo-2-0325-32B)                                | [allenai/OLMo-2-1124-13B](https://huggingface.co/allenai/OLMo-2-1124-13B)                             | [allenai/OLMo-2-1124-7B](https://huggingface.co/allenai/OLMo-2-1124-7B)                                |
+| **SFT**              | [allenai/OLMo-2-0325-32B-SFT](https://huggingface.co/allenai/OLMo-2-0325-32B-SFT)                | [allenai/OLMo-2-1124-13B-SFT](https://huggingface.co/allenai/OLMo-2-1124-13B-SFT)              | [allenai/OLMo-2-1124-7B-SFT](https://huggingface.co/allenai/OLMo-2-1124-7B-SFT)                |
+| **DPO**              | [allenai/OLMo-2-0325-32B-DPO](https://huggingface.co/allenai/OLMo-2-0325-32B-DPO)                | [allenai/OLMo-2-1124-13B-DPO](https://huggingface.co/allenai/OLMo-2-1124-13B-DPO)              | [allenai/OLMo-2-1124-7B-DPO](https://huggingface.co/allenai/OLMo-2-1124-7B-DPO)                |
+| **Final Models (RLVR)** | [allenai/OLMo-2-0325-32B-Instruct](https://huggingface.co/allenai/OLMo-2-0325-32B-Instruct)                        | [allenai/OLMo-2-1124-13B-Instruct](https://huggingface.co/allenai/OLMo-2-1124-13B-Instruct)                      | [allenai/OLMo-2-1124-7B-Instruct](https://huggingface.co/allenai/OLMo-2-1124-7B-Instruct)                        |
+| **Reward Model (RM)**|                                                     | (Same as 7B)                                                     | [allenai/OLMo-2-1124-7B-RM](https://huggingface.co/allenai/OLMo-2-1124-7B-RM)                                                     |
 ## Installation
 out = list_repo_refs("allenai/OLMo-2-0325-32B")
 branches = [b.name for b in out.branches]
 ```
+Note: vLLM for OLMo2 32B does not correctly handle attention when the number of heads differs from the number of KV heads (i.e., when using Grouped-Query Attention (GQA) or Multi-Query Attention (MQA) instead of Multi-Head Attention (MHA)). Specifically, it incorrectly splits QKV into equal chunks rather than based on the actual sizes of Q, K, and V. vLLM hasn't released a version with the fix yet ([Issue](https://github.com/vllm-project/vllm/pull/13687)).
 ### Fine-tuning
 Model fine-tuning can be done from the final checkpoint (the `main` revision of this model) or many intermediate checkpoints. Two recipes for tuning are available.