Instructions to use JayHyeon/Qwen_0.5-cDPO_5e-7_1.0vpo_constant_ls0.1_seed42 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JayHyeon/Qwen_0.5-cDPO_5e-7_1.0vpo_constant_ls0.1_seed42 with Transformers:

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

pipe = pipeline("text-generation", model="JayHyeon/Qwen_0.5-cDPO_5e-7_1.0vpo_constant_ls0.1_seed42")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("JayHyeon/Qwen_0.5-cDPO_5e-7_1.0vpo_constant_ls0.1_seed42")
model = AutoModelForCausalLM.from_pretrained("JayHyeon/Qwen_0.5-cDPO_5e-7_1.0vpo_constant_ls0.1_seed42", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use JayHyeon/Qwen_0.5-cDPO_5e-7_1.0vpo_constant_ls0.1_seed42 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JayHyeon/Qwen_0.5-cDPO_5e-7_1.0vpo_constant_ls0.1_seed42"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JayHyeon/Qwen_0.5-cDPO_5e-7_1.0vpo_constant_ls0.1_seed42",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/JayHyeon/Qwen_0.5-cDPO_5e-7_1.0vpo_constant_ls0.1_seed42

SGLang

How to use JayHyeon/Qwen_0.5-cDPO_5e-7_1.0vpo_constant_ls0.1_seed42 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 "JayHyeon/Qwen_0.5-cDPO_5e-7_1.0vpo_constant_ls0.1_seed42" \
    --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": "JayHyeon/Qwen_0.5-cDPO_5e-7_1.0vpo_constant_ls0.1_seed42",
		"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 "JayHyeon/Qwen_0.5-cDPO_5e-7_1.0vpo_constant_ls0.1_seed42" \
        --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": "JayHyeon/Qwen_0.5-cDPO_5e-7_1.0vpo_constant_ls0.1_seed42",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use JayHyeon/Qwen_0.5-cDPO_5e-7_1.0vpo_constant_ls0.1_seed42 with Docker Model Runner:
```
docker model run hf.co/JayHyeon/Qwen_0.5-cDPO_5e-7_1.0vpo_constant_ls0.1_seed42
```

JayHyeon commited on Aug 13, 2025

Commit

c23d986

verified ·

1 Parent(s): ca2ff92

Model save

Browse files

Files changed (3) hide show

all_results.json +15 -0
eval_results.json +15 -0
generation_config.json +14 -0

all_results.json ADDED Viewed

	@@ -0,0 +1,15 @@

+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -1.0900075435638428,
+    "eval_logits/rejected": -1.0925240516662598,
+    "eval_logps/chosen": -451.7510986328125,
+    "eval_logps/rejected": -312.4322204589844,
+    "eval_loss": 0.6137669682502747,
+    "eval_rewards/accuracies": 0.6851891875267029,
+    "eval_rewards/chosen": -0.08272896707057953,
+    "eval_rewards/margins": 0.49261024594306946,
+    "eval_rewards/rejected": -0.57533198595047,
+    "eval_runtime": 202.7533,
+    "eval_samples_per_second": 90.795,
+    "eval_steps_per_second": 5.677
+}

eval_results.json ADDED Viewed

	@@ -0,0 +1,15 @@

+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -1.0900075435638428,
+    "eval_logits/rejected": -1.0925240516662598,
+    "eval_logps/chosen": -451.7510986328125,
+    "eval_logps/rejected": -312.4322204589844,
+    "eval_loss": 0.6137669682502747,
+    "eval_rewards/accuracies": 0.6851891875267029,
+    "eval_rewards/chosen": -0.08272896707057953,
+    "eval_rewards/margins": 0.49261024594306946,
+    "eval_rewards/rejected": -0.57533198595047,
+    "eval_runtime": 202.7533,
+    "eval_samples_per_second": 90.795,
+    "eval_steps_per_second": 5.677
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,14 @@

+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.55.0"
+}