Instructions to use howardzhou/Qwen2.5-7B-Open-R1-Distill with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use howardzhou/Qwen2.5-7B-Open-R1-Distill with Transformers:

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

pipe = pipeline("text-generation", model="howardzhou/Qwen2.5-7B-Open-R1-Distill")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("howardzhou/Qwen2.5-7B-Open-R1-Distill")
model = AutoModelForCausalLM.from_pretrained("howardzhou/Qwen2.5-7B-Open-R1-Distill", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use howardzhou/Qwen2.5-7B-Open-R1-Distill with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "howardzhou/Qwen2.5-7B-Open-R1-Distill"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "howardzhou/Qwen2.5-7B-Open-R1-Distill",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/howardzhou/Qwen2.5-7B-Open-R1-Distill

SGLang

How to use howardzhou/Qwen2.5-7B-Open-R1-Distill 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 "howardzhou/Qwen2.5-7B-Open-R1-Distill" \
    --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": "howardzhou/Qwen2.5-7B-Open-R1-Distill",
		"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 "howardzhou/Qwen2.5-7B-Open-R1-Distill" \
        --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": "howardzhou/Qwen2.5-7B-Open-R1-Distill",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use howardzhou/Qwen2.5-7B-Open-R1-Distill with Docker Model Runner:
```
docker model run hf.co/howardzhou/Qwen2.5-7B-Open-R1-Distill
```

howardzhou commited on Feb 11, 2025

Commit

c355cfd

verified ·

1 Parent(s): 18a44ee

Model save

Browse files

Files changed (4) hide show

README.md +1 -1
all_results.json +7 -7
train_results.json +7 -7
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/howardzhou92-nw/huggingface/runs/5fbhajij)
 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/howardzhou92-nw/huggingface/runs/cuu0yr0w)
 This model was trained with SFT.

all_results.json CHANGED Viewed

@@ -1,9 +1,9 @@
 {
-    "epoch": 1.0,
-    "total_flos": 4705642371612672.0,
-    "train_loss": 0.4742418575281553,
-    "train_runtime": 118145.0815,
-    "train_samples": 594015,
-    "train_samples_per_second": 4.862,
-    "train_steps_per_second": 0.038
 }

 {
+    "epoch": 0.9995169859925938,
+    "total_flos": 1627220267237376.0,
+    "train_loss": 0.5271049797074082,
+    "train_runtime": 41787.5323,
+    "train_samples": 112817,
+    "train_samples_per_second": 4.756,
+    "train_steps_per_second": 0.037
 }

train_results.json CHANGED Viewed

@@ -1,9 +1,9 @@
 {
-    "epoch": 1.0,
-    "total_flos": 4705642371612672.0,
-    "train_loss": 0.4742418575281553,
-    "train_runtime": 118145.0815,
-    "train_samples": 594015,
-    "train_samples_per_second": 4.862,
-    "train_steps_per_second": 0.038
 }

 {
+    "epoch": 0.9995169859925938,
+    "total_flos": 1627220267237376.0,
+    "train_loss": 0.5271049797074082,
+    "train_runtime": 41787.5323,
+    "train_samples": 112817,
+    "train_samples_per_second": 4.756,
+    "train_steps_per_second": 0.037
 }

trainer_state.json CHANGED Viewed

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