Instructions to use xiaohaoWillX/policy_ragen_train_p0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xiaohaoWillX/policy_ragen_train_p0 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("/root/autodl-tmp/models/Qwen2.5-7B")
model = PeftModel.from_pretrained(base_model, "xiaohaoWillX/policy_ragen_train_p0")

Transformers

How to use xiaohaoWillX/policy_ragen_train_p0 with Transformers:

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

pipe = pipeline("text-generation", model="xiaohaoWillX/policy_ragen_train_p0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("xiaohaoWillX/policy_ragen_train_p0", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use xiaohaoWillX/policy_ragen_train_p0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xiaohaoWillX/policy_ragen_train_p0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xiaohaoWillX/policy_ragen_train_p0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xiaohaoWillX/policy_ragen_train_p0

SGLang

How to use xiaohaoWillX/policy_ragen_train_p0 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 "xiaohaoWillX/policy_ragen_train_p0" \
    --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": "xiaohaoWillX/policy_ragen_train_p0",
		"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 "xiaohaoWillX/policy_ragen_train_p0" \
        --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": "xiaohaoWillX/policy_ragen_train_p0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use xiaohaoWillX/policy_ragen_train_p0 with Docker Model Runner:
```
docker model run hf.co/xiaohaoWillX/policy_ragen_train_p0
```

policy_ragen_train_p0

This model is a fine-tuned version of /root/autodl-tmp/models/Qwen2.5-7B on the policy_ragen_train_p0 dataset. It achieves the following results on the evaluation set:

Loss: 1.1161

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 2
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 3
gradient_accumulation_steps: 16
total_train_batch_size: 96
total_eval_batch_size: 6
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5.0

Training results

Training Loss	Epoch	Step	Validation Loss
1.0057	3.3463	50	1.1555

Framework versions

PEFT 0.17.1
Transformers 4.56.2
Pytorch 2.5.1+cu124
Datasets 4.0.0
Tokenizers 0.22.1

Downloads last month: -