Instructions to use Katayoon/VPO-Zephyr-7B-iter-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Katayoon/VPO-Zephyr-7B-iter-2 with Transformers:

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

pipe = pipeline("text-generation", model="Katayoon/VPO-Zephyr-7B-iter-2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Katayoon/VPO-Zephyr-7B-iter-2")
model = AutoModelForMultimodalLM.from_pretrained("Katayoon/VPO-Zephyr-7B-iter-2")
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 Katayoon/VPO-Zephyr-7B-iter-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Katayoon/VPO-Zephyr-7B-iter-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Katayoon/VPO-Zephyr-7B-iter-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Katayoon/VPO-Zephyr-7B-iter-2

SGLang

How to use Katayoon/VPO-Zephyr-7B-iter-2 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 "Katayoon/VPO-Zephyr-7B-iter-2" \
    --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": "Katayoon/VPO-Zephyr-7B-iter-2",
		"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 "Katayoon/VPO-Zephyr-7B-iter-2" \
        --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": "Katayoon/VPO-Zephyr-7B-iter-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Katayoon/VPO-Zephyr-7B-iter-2 with Docker Model Runner:
```
docker model run hf.co/Katayoon/VPO-Zephyr-7B-iter-2
```

Katayoon commited on Jul 19, 2024

Commit

a0d2cda

verified ·

1 Parent(s): a1922f1

End of training

Browse files

Files changed (2) hide show

README.md +8 -1
config.json +1 -1

README.md CHANGED Viewed

@@ -2,9 +2,16 @@
 license: mit
 base_model: Katayoon/VPO-Zephyr-7B-iter-1
 tags:
 - trl
 - dpo
 - generated_from_trainer
 model-index:
 - name: VPO-Zephyr-7B-iter-2
   results: []
@@ -15,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 # VPO-Zephyr-7B-iter-2
-This model is a fine-tuned version of [Katayoon/VPO-Zephyr-7B-iter-1](https://huggingface.co/Katayoon/VPO-Zephyr-7B-iter-1) on the None dataset.
 ## Model description

 license: mit
 base_model: Katayoon/VPO-Zephyr-7B-iter-1
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- updated
+- original
 model-index:
 - name: VPO-Zephyr-7B-iter-2
   results: []
 # VPO-Zephyr-7B-iter-2
+This model is a fine-tuned version of [Katayoon/VPO-Zephyr-7B-iter-1](https://huggingface.co/Katayoon/VPO-Zephyr-7B-iter-1) on the updated and the original datasets.
 ## Model description

config.json CHANGED Viewed

@@ -21,6 +21,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.2",
-  "use_cache": false,
   "vocab_size": 32000
 }

   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.2",
+  "use_cache": true,
   "vocab_size": 32000
 }