Instructions to use ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_51 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_51 with Transformers:

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

pipe = pipeline("text-generation", model="ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_51")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_51")
model = AutoModelForCausalLM.from_pretrained("ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_51", 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 ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_51 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_51"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_51",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_51

SGLang

How to use ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_51 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 "ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_51" \
    --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": "ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_51",
		"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 "ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_51" \
        --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": "ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_51",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_51 with Docker Model Runner:
```
docker model run hf.co/ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_51
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_51 runing the SFT with PPO for 51 steps. runing the SFT with PPO for 51 steps. runing the SFT with PPO for 51 steps. runing the SFT with PPO for 51 steps. runing the SFT with PPO for 51 steps.

Downloads last month: 53

Safetensors

Model size

7B params

Tensor type

F32

Model tree for ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_51

Quantizations

1 model