Instructions to use Zyphra/Zamba2-2.7B-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Zyphra/Zamba2-2.7B-instruct with Transformers:

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

pipe = pipeline("text-generation", model="Zyphra/Zamba2-2.7B-instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B-instruct")
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

vLLM

How to use Zyphra/Zamba2-2.7B-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Zyphra/Zamba2-2.7B-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Zyphra/Zamba2-2.7B-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Zyphra/Zamba2-2.7B-instruct

SGLang

How to use Zyphra/Zamba2-2.7B-instruct 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 "Zyphra/Zamba2-2.7B-instruct" \
    --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": "Zyphra/Zamba2-2.7B-instruct",
		"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 "Zyphra/Zamba2-2.7B-instruct" \
        --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": "Zyphra/Zamba2-2.7B-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Zyphra/Zamba2-2.7B-instruct with Docker Model Runner:
```
docker model run hf.co/Zyphra/Zamba2-2.7B-instruct
```

update bar chart

by qanthony - opened Oct 2, 2024

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-2

Files changed (1) hide show

README.md +1 -2

README.md CHANGED Viewed

@@ -49,11 +49,10 @@ print((tokenizer.decode(outputs[0])))
 Zamba2-2.7B-Instruct punches dramatically above its weight, achieving extremely strong instruction-following benchmark scores, significantly outperforming Gemma2-2B-Instruct of the same size and outperforming Mistral-7B-Instruct in most metrics.
 <center>
-<img src="https://cdn-uploads.huggingface.co/production/uploads/65bc13717c6ad1994b6619e9/ml2i8lHK4ojqBh_xV50L9.png" width="900"/>
 </center>
 | Model                     | Size | MT-Bench | IFEval   |
 |---------------------------|-----:|---------:|---------:|
 | **Zamba2-2.7B-Instruct**  | 2.7B | **72.40**| **48.02**|

 Zamba2-2.7B-Instruct punches dramatically above its weight, achieving extremely strong instruction-following benchmark scores, significantly outperforming Gemma2-2B-Instruct of the same size and outperforming Mistral-7B-Instruct in most metrics.
 <center>
+<img src="https://cdn-uploads.huggingface.co/production/uploads/63b9a261efe99543b34e9579/WG7jBdVPMxZLOtKMag2E8.png" width="900"/>
 </center>
 | Model                     | Size | MT-Bench | IFEval   |
 |---------------------------|-----:|---------:|---------:|
 | **Zamba2-2.7B-Instruct**  | 2.7B | **72.40**| **48.02**|