Instructions to use cfei621/OlympicCoder-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cfei621/OlympicCoder-32B with Transformers:

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

pipe = pipeline("text-generation", model="cfei621/OlympicCoder-32B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cfei621/OlympicCoder-32B")
model = AutoModelForCausalLM.from_pretrained("cfei621/OlympicCoder-32B")
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 cfei621/OlympicCoder-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cfei621/OlympicCoder-32B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cfei621/OlympicCoder-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cfei621/OlympicCoder-32B

SGLang

How to use cfei621/OlympicCoder-32B 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 "cfei621/OlympicCoder-32B" \
    --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": "cfei621/OlympicCoder-32B",
		"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 "cfei621/OlympicCoder-32B" \
        --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": "cfei621/OlympicCoder-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cfei621/OlympicCoder-32B with Docker Model Runner:
```
docker model run hf.co/cfei621/OlympicCoder-32B
```

cfei621 commited on Apr 17, 2025

Commit

09a0f0c

verified ·

1 Parent(s): 4c87b7a

Model save

Browse files

Files changed (5) hide show

README.md +1 -1
all_results.json +5 -5
generation_config.json +6 -8
train_results.json +5 -5
trainer_state.json +0 -0

README.md CHANGED Viewed

@@ -26,7 +26,7 @@ print(output["generated_text"])
 ## Training procedure
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/cfei-kaust/huggingface/runs/dsm35vrk)
 This model was trained with SFT.

 ## Training procedure
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/cfei-kaust/huggingface/runs/63lc4ds4)
 This model was trained with SFT.

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
-    "total_flos": 18857631034368.0,
-    "train_loss": 0.18426384230746942,
-    "train_runtime": 35740.9083,
     "train_samples": 5455,
-    "train_samples_per_second": 1.526,
-    "train_steps_per_second": 0.048
 }

 {
+    "total_flos": 15136392560640.0,
+    "train_loss": 0.18609273691826006,
+    "train_runtime": 35924.8672,
     "train_samples": 5455,
+    "train_samples_per_second": 1.518,
+    "train_steps_per_second": 0.047
 }

generation_config.json CHANGED Viewed

@@ -1,14 +1,12 @@
 {
-  "bos_token_id": 151643,
   "do_sample": true,
   "eos_token_id": [
-    151645,
-    151643
   ],
-  "pad_token_id": 151643,
-  "repetition_penalty": 1.05,
-  "temperature": 0.7,
-  "top_k": 20,
-  "top_p": 0.8,
   "transformers_version": "4.49.0"
 }

 {
+  "bos_token_id": 128000,
   "do_sample": true,
   "eos_token_id": [
+    128001,
+    128008,
+    128009
   ],
+  "temperature": 0.6,
+  "top_p": 0.9,
   "transformers_version": "4.49.0"
 }

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
-    "total_flos": 18857631034368.0,
-    "train_loss": 0.18426384230746942,
-    "train_runtime": 35740.9083,
     "train_samples": 5455,
-    "train_samples_per_second": 1.526,
-    "train_steps_per_second": 0.048
 }

 {
+    "total_flos": 15136392560640.0,
+    "train_loss": 0.18609273691826006,
+    "train_runtime": 35924.8672,
     "train_samples": 5455,
+    "train_samples_per_second": 1.518,
+    "train_steps_per_second": 0.047
 }

trainer_state.json CHANGED Viewed

The diff for this file is too large to render. See raw diff