Instructions to use LLMJapan/OlympicCoder-7B_exl2_5.0bpw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LLMJapan/OlympicCoder-7B_exl2_5.0bpw with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="LLMJapan/OlympicCoder-7B_exl2_5.0bpw")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LLMJapan/OlympicCoder-7B_exl2_5.0bpw")
model = AutoModelForCausalLM.from_pretrained("LLMJapan/OlympicCoder-7B_exl2_5.0bpw")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use LLMJapan/OlympicCoder-7B_exl2_5.0bpw with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LLMJapan/OlympicCoder-7B_exl2_5.0bpw"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LLMJapan/OlympicCoder-7B_exl2_5.0bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LLMJapan/OlympicCoder-7B_exl2_5.0bpw

SGLang

How to use LLMJapan/OlympicCoder-7B_exl2_5.0bpw with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "LLMJapan/OlympicCoder-7B_exl2_5.0bpw" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LLMJapan/OlympicCoder-7B_exl2_5.0bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "LLMJapan/OlympicCoder-7B_exl2_5.0bpw" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LLMJapan/OlympicCoder-7B_exl2_5.0bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LLMJapan/OlympicCoder-7B_exl2_5.0bpw with Docker Model Runner:
```
docker model run hf.co/LLMJapan/OlympicCoder-7B_exl2_5.0bpw
```

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.

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.
Language(s) (NLP): Primarily English
License: apache-2.0
Finetuned from model: Qwen/Qwen2.5-Coder-7B-Instruct

Evaluation

Usage

Here's how you can run the model using the pipeline() function from 🤗 Transformers:

# 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")

# 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"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=8000, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
#<|im_start|>user
#Write a python program to calculate the 10th fibonacci number<|im_end|>
#<|im_start|>assistant
#<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. ...

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.

Training procedure

Training hyper-parameters

The following hyperparameters were used during training:

dataset: open-r1/codeforces-cots
learning_rate: 4.0e-5
train_batch_size: 2
seed: 42
packing: false
distributed_type: deepspeed-zero-3
num_devices: 8
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine_with_min_lr
min_lr_rate: 0.1
lr_scheduler_warmup_ratio: 0.03
num_epochs: 10.0

Downloads last month: -

Model tree for LLMJapan/OlympicCoder-7B_exl2_5.0bpw

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-Coder-7B

Finetuned

Qwen/Qwen2.5-Coder-7B-Instruct

Quantized

(191)

this model

LLMJapan
/

OlympicCoder-7B_exl2_5.0bpw