Instructions to use HuggingFaceH4/zephyr-7b-beta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceH4/zephyr-7b-beta with Transformers:

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

pipe = pipeline("text-generation", model="HuggingFaceH4/zephyr-7b-beta")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceH4/zephyr-7b-beta")
model = AutoModelForCausalLM.from_pretrained("HuggingFaceH4/zephyr-7b-beta", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HuggingFaceH4/zephyr-7b-beta with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceH4/zephyr-7b-beta"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceH4/zephyr-7b-beta",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HuggingFaceH4/zephyr-7b-beta

SGLang

How to use HuggingFaceH4/zephyr-7b-beta 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 "HuggingFaceH4/zephyr-7b-beta" \
    --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": "HuggingFaceH4/zephyr-7b-beta",
		"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 "HuggingFaceH4/zephyr-7b-beta" \
        --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": "HuggingFaceH4/zephyr-7b-beta",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HuggingFaceH4/zephyr-7b-beta with Docker Model Runner:
```
docker model run hf.co/HuggingFaceH4/zephyr-7b-beta
```

zephyr-7b-beta

Commit History

Nov 30, 2023

13:35
Update README.md

Wauplin HF Staff

3373c17
13:21
Update README.md

Wauplin HF Staff

a044a6c
13:19
Update README.md

Wauplin HF Staff

5ae4839

Nov 29, 2023

15:13
Update README.md

Wauplin HF Staff

72ac185
15:12
Update README.md

Wauplin HF Staff

a14ed68
15:10
[WIP] Add evaluation results to model card metadata⁠

Wauplin HF Staff

6581330

Nov 22, 2023

14:45
Add widget example (#34)⁠

lewtun HF Staff

8d44a71

Nov 21, 2023

17:27
Update README.md

lewtun HF Staff

36db76e

Nov 20, 2023

17:26
Adding Evaluation Results (#31)⁠

lewtun +1: leaderboard-pr-bot HF Staff

c2339b6
15:55
Update README.md (#28)⁠

lewtun +1: natolambert HF Staff

abe3655

Nov 4, 2023

19:51
Upload MistralForCausalLM (#20)⁠

lewtun HF Staff

8af01af

Oct 27, 2023

08:56
Update README.md (#1)⁠

lewtun +1: lvwerra HF Staff

3bac358
08:50
Update README.md

lewtun HF Staff

af28f1d
07:04
Update README.md

lewtun HF Staff

99dc9c4

Oct 26, 2023

13:38
Update README.md

lewtun HF Staff

8d4f1f7
12:47
Update README.md

lewtun HF Staff

0f4b871
12:33
Update README.md

lewtun HF Staff

e981ffb
12:31
Update config.json

lewtun HF Staff

e323593
12:31
Delete dialogue_template.json

lewtun HF Staff

fff0b6c
12:08
Update README.md

edbeeching HF Staff

63bc8ee
11:27
Update README.md

edbeeching HF Staff

8bf7bff
11:25
Duplicate from HuggingFaceH4-colab/zephyr-7b-beta-sharded

edbeeching HF Staff

97ecdb4

Commit History

Nov 30, 2023

Update README.md

Update README.md

Update README.md

Nov 29, 2023

Update README.md

Update README.md

[WIP] Add evaluation results to model card metadata⁠

Nov 22, 2023

Add widget example (#34)⁠

Nov 21, 2023

Update README.md

Nov 20, 2023

Adding Evaluation Results (#31)⁠

Update README.md (#28)⁠

Nov 4, 2023

Upload MistralForCausalLM (#20)⁠

Oct 27, 2023

Update README.md (#1)⁠

Update README.md

Update README.md

Oct 26, 2023

Update README.md

Update README.md

Update README.md

Update config.json

Delete dialogue_template.json

Update README.md

Update README.md

Duplicate from HuggingFaceH4-colab/zephyr-7b-beta-sharded