Instructions to use Zyphra/Zamba2-7B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Zyphra/Zamba2-7B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="Zyphra/Zamba2-7B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-7B-Instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-7B-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 Settings

vLLM

How to use Zyphra/Zamba2-7B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Zyphra/Zamba2-7B-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/Zamba2-7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Zyphra/Zamba2-7B-Instruct

SGLang

How to use Zyphra/Zamba2-7B-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/Zamba2-7B-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/Zamba2-7B-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/Zamba2-7B-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/Zamba2-7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Zyphra/Zamba2-7B-Instruct with Docker Model Runner:
```
docker model run hf.co/Zyphra/Zamba2-7B-Instruct
```

pglo commited on Feb 5, 2025

Commit

32467f2

verified ·

1 Parent(s): 2394318

Update README.md

Browse files

Files changed (1) hide show

README.md +12 -5

README.md CHANGED Viewed

@@ -16,11 +16,18 @@ Zamba2-7B-Instruct long-context has been extended from 4k to 16k context by adju
 ### Prerequisites
-To download Zamba2-2.7B-instruct, clone Zyphra's fork of transformers:
-1. `git clone https://github.com/Zyphra/transformers_zamba2.git`
-2. `cd transformers_zamba2`
-3. Install the repository: `pip install -e .`
-4. `pip install accelerate`
 ### Inference

 ### Prerequisites
+To use Zamba2-7B-instruct, install `transformers`:
+`pip install transformers`
+To install dependencies necessary to run Mamba2 kernels, install `mamba-ssm` from source (due to compatibility issues with PyTorch) as well as `causal-conv1d`:
+1. `git clone https://github.com/state-spaces/mamba.git`
+2. `cd mamba && git checkout v2.1.0 && pip install .`
+3. `pip install causal-conv1d`
+You can run the model without using the optimized Mamba2 kernels, but it is **not** recommended as it will result in significantly higher latency and memory usage.
 ### Inference