Instructions to use sail/Zephyr-7B-DICE-Iter2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sail/Zephyr-7B-DICE-Iter2 with Transformers:

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

pipe = pipeline("text-generation", model="sail/Zephyr-7B-DICE-Iter2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sail/Zephyr-7B-DICE-Iter2")
model = AutoModelForCausalLM.from_pretrained("sail/Zephyr-7B-DICE-Iter2")
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 sail/Zephyr-7B-DICE-Iter2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sail/Zephyr-7B-DICE-Iter2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sail/Zephyr-7B-DICE-Iter2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sail/Zephyr-7B-DICE-Iter2

SGLang

How to use sail/Zephyr-7B-DICE-Iter2 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 "sail/Zephyr-7B-DICE-Iter2" \
    --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": "sail/Zephyr-7B-DICE-Iter2",
		"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 "sail/Zephyr-7B-DICE-Iter2" \
        --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": "sail/Zephyr-7B-DICE-Iter2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sail/Zephyr-7B-DICE-Iter2 with Docker Model Runner:
```
docker model run hf.co/sail/Zephyr-7B-DICE-Iter2
```

Add pipeline tag and link to Github repository

by nielsr HF Staff - opened Mar 10, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-2

Files changed (1) hide show

README.md +7 -2

README.md CHANGED Viewed

@@ -1,11 +1,13 @@
 ---
-library_name: transformers
-license: mit
 datasets:
 - HuggingFaceH4/ultrafeedback_binarized
 language:
 - en
 ---
 # Zephyr-7B-DICE-Iter2
 This model was developed using [Bootstrapping Language Models with DPO Implicit Rewards](https://arxiv.org/abs/2406.09760) (DICE) at iteration 2, based on the [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) as the starting point.
@@ -29,6 +31,9 @@ This model was developed using [Bootstrapping Language Models with DPO Implicit
 |[Zephyr-7B-DICE-Iter1](https://huggingface.co/sail/Zephyr-7B-DICE-Iter1) |19.03 |17.67
 |[Zephyr-7B-DICE-Iter2](https://huggingface.co/sail/Zephyr-7B-DICE-Iter2) |**20.71** |**20.16**
 ## Citation
 ```bibtex

 ---
 datasets:
 - HuggingFaceH4/ultrafeedback_binarized
 language:
 - en
+library_name: transformers
+license: mit
+pipeline_tag: text-generation
 ---
 # Zephyr-7B-DICE-Iter2
 This model was developed using [Bootstrapping Language Models with DPO Implicit Rewards](https://arxiv.org/abs/2406.09760) (DICE) at iteration 2, based on the [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) as the starting point.
 |[Zephyr-7B-DICE-Iter1](https://huggingface.co/sail/Zephyr-7B-DICE-Iter1) |19.03 |17.67
 |[Zephyr-7B-DICE-Iter2](https://huggingface.co/sail/Zephyr-7B-DICE-Iter2) |**20.71** |**20.16**
+## Code
+https://github.com/sail-sg/dice
 ## Citation
 ```bibtex