Instructions to use yuaay/vanguard with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yuaay/vanguard with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yuaay/vanguard")
model = AutoModelForCausalLM.from_pretrained("yuaay/vanguard", 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 yuaay/vanguard with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/yuaay/vanguard

SGLang

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

Docker Model Runner
How to use yuaay/vanguard with Docker Model Runner:
```
docker model run hf.co/yuaay/vanguard
```

yuaay commited on 3 days ago

Commit

6f029b3

verified ·

1 Parent(s): f5a59a6

Delete SOURCE.md

Browse files

Files changed (1) hide show

SOURCE.md +0 -13

SOURCE.md DELETED Viewed

@@ -1,13 +0,0 @@
-# Model source
-Exported by: merge_agentguard_step100.sh
-Exported at: 2026-05-20T20:10:36+08:00
-- Base model: /mnt/shared-storage-user/ai4good2-share/models/Qwen/Qwen3-8B
-- Experiment: easy_r1_agentguard / agentguard_bleu_no_lambda_p_warmup_v5.13
-- Checkpoint step: global_step_300
-- Source actor dir: /mnt/shared-storage-user/ai4good2-share/xiongyuan/EasyR1_AgentGuard/checkpoints/easy_r1_agentguard/agentguard_bleu_no_lambda_p_warmup_v5.13/global_step_300/actor
-- Training config: /mnt/shared-storage-user/ai4good2-share/xiongyuan/EasyR1_AgentGuard/checkpoints/easy_r1_agentguard/agentguard_bleu_no_lambda_p_warmup_v5.13/experiment_config.json
-- Checkpoint tracker: /mnt/shared-storage-user/ai4good2-share/xiongyuan/EasyR1_AgentGuard/checkpoints/easy_r1_agentguard/agentguard_bleu_no_lambda_p_warmup_v5.13/checkpoint_tracker.json
-- Merger: /mnt/shared-storage-user/ai4good2-share/xiongyuan/EasyR1_AgentGuard/scripts/model_merger.py
-- Conda env used: vllm-fla (/mnt/shared-storage-user/xiongyuan/miniconda3)