Instructions to use jvonrad/Qwen-2.5-7B-TED-grpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jvonrad/Qwen-2.5-7B-TED-grpo with Transformers:

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

pipe = pipeline("text-generation", model="jvonrad/Qwen-2.5-7B-TED-grpo")
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("jvonrad/Qwen-2.5-7B-TED-grpo")
model = AutoModelForCausalLM.from_pretrained("jvonrad/Qwen-2.5-7B-TED-grpo", 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 jvonrad/Qwen-2.5-7B-TED-grpo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jvonrad/Qwen-2.5-7B-TED-grpo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jvonrad/Qwen-2.5-7B-TED-grpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jvonrad/Qwen-2.5-7B-TED-grpo

SGLang

How to use jvonrad/Qwen-2.5-7B-TED-grpo 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 "jvonrad/Qwen-2.5-7B-TED-grpo" \
    --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": "jvonrad/Qwen-2.5-7B-TED-grpo",
		"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 "jvonrad/Qwen-2.5-7B-TED-grpo" \
        --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": "jvonrad/Qwen-2.5-7B-TED-grpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jvonrad/Qwen-2.5-7B-TED-grpo with Docker Model Runner:
```
docker model run hf.co/jvonrad/Qwen-2.5-7B-TED-grpo
```

jvonrad commited on May 25

Commit

9e296e8

verified ·

1 Parent(s): 272d467

Upload Qwen-2.5-7B TED GRPO checkpoint-1200 merged

Browse files

Files changed (3) hide show

model-00001-of-00004.safetensors +1 -1
model-00002-of-00004.safetensors +1 -1
model-00003-of-00004.safetensors +1 -1

model-00001-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13f8b5b896d3ac6fd4b712aef3035d60ef135348a658dd13c892f94dd062194d
 size 4877660776

 version https://git-lfs.github.com/spec/v1
+oid sha256:74bfd55443b15f9394cfe34ff99e5dae3c6d21b7cb3ef53840139e54f50b8b54
 size 4877660776

model-00002-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:624adcb85defe460afbe88d0f03bb6c46aa02c4a3cbbcc67cd31b24c64cb52c8
 size 4932751008

 version https://git-lfs.github.com/spec/v1
+oid sha256:8ef2b99c5cab53cf24a5ff3c4314641e39efa5d32ea47f12a80dd3621e01b5c5
 size 4932751008

model-00003-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9a62e8120d1373988353984f83175cdb68220b1e239eae60309fb49e7fed480
 size 4330865200

 version https://git-lfs.github.com/spec/v1
+oid sha256:19832dc460eb78999e80c1d97d0ca43a308d908e0a860cee216eb67d3c42cb58
 size 4330865200