Update README.md

README.md

@@ -24,20 +24,19 @@ python convert.py \
     -b 8.0 \
     -hb 8
 ```
+# Model Card for OlympicCoder-32B
 
-# Model Card for OlympicCoder-7B
-
-OlympicCoder-7B is a code model that achieves strong performance on competitive coding benchmarks such as LiveCodeBench and the 2024 International Olympiad in Informatics. 
+OlympicCoder-32B is a code mode that achieves very strong performance on competitive coding benchmarks such as LiveCodeBench andthe 2024 International Olympiad in Informatics.
 
 * Repository: https://github.com/huggingface/open-r1
 * Blog post: https://huggingface.co/blog/open-r1/update-3
 
 ## Model description
 
-- **Model type:** A 7B parameter model fine-tuned on a decontaminated version of the codeforces dataset.
+- **Model type:** A 32B parameter model fine-tuned on a decontaminated version of the codeforces dataset.
 - **Language(s) (NLP):** Primarily English
 - **License:** apache-2.0
-- **Finetuned from model:** [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct)
+- **Finetuned from model:** [Qwen/Qwen2.5-Coder-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct)
 
 ## Evaluation
 
@@ -45,18 +44,16 @@ OlympicCoder-7B is a code model that achieves strong performance on competitive
 
 
 
+
 ## Usage
 Here's how you can run the model using the `pipeline()` function from 🤗 Transformers:
 
 ```python
 # pip install transformers
 # pip install accelerate
-
 import torch
 from transformers import pipeline
-
-pipe = pipeline("text-generation", model="open-r1/OlympicCoder-7B", torch_dtype=torch.bfloat16, device_map="auto")
-
+pipe = pipeline("text-generation", model="open-r1/OlympicCoder-32B", torch_dtype=torch.bfloat16, device_map="auto")
 # We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
 messages = [
     {"role": "user", "content": "Write a python program to calculate the 10th Fibonacci number"},
@@ -70,22 +67,23 @@ print(outputs[0]["generated_text"])
 #<think>Okay, I need to write a Python program that calculates the 10th Fibonacci number. Hmm, the Fibonacci sequence starts with 0 and 1. Each subsequent number is the sum of the two preceding ones. So the sequence goes: 0, 1, 1, 2, 3, 5, 8, 13, 21, 34, and so on. ...
 ```
 
-> [!WARNING]
-> To ensure that the model consistently outputs a long chain-of-thought, we have edited the chat template to prefill the first assistant turn with a `<think>` token. As a result, the outputs from this model will not show the opening `<think>` token if you use the model's `generate()` method.  To apply reinforcement learning with a format reward, either prepend the `<think>` token to the model's completions or amend the chat template to remove the prefill. 
+> [!IMPORTANT]
+> To ensure that the model consistently outputs a long chain-of-thought, we have edited the chat template to prefill the first assistant turn with a `<think>` token. As a result, the outputs from this model will not show the opening `<think>` token if you use the model's `generate()` method.  To apply reinforcement learning with a format reward, either prepend the `<think>` token to the model's completions or amend the chat template to remove the prefill. Check out our [blog post](https://huggingface.co/blog/open-r1/update-3#lesson-4-prefill-with-think-to-consistently-enable-long-cot) for more details.
+
 
 ## Training procedure
 ### Training hyper-parameters
 
-The following hyperparameters were used during training:
+The following hyperparameters were used during training on 16 H100 nodes:
 
-- dataset: open-r1/codeforces-cots
+- dataset: open-r1/codeforces-cots_decontaminated
 - learning_rate: 4.0e-5
-- train_batch_size: 2
+- train_batch_size: 1
 - seed: 42
 - packing: false
-- distributed_type: deepspeed-zero-3
-- num_devices: 8
-- gradient_accumulation_steps: 8
+- distributed_type: fsdp
+- num_devices: 128
+- gradient_accumulation_steps: 1
 - total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine_with_min_lr