Instructions to use Zyphra/Zamba2-7B-Instruct-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Zyphra/Zamba2-7B-Instruct-v2 with Transformers:

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

pipe = pipeline("text-generation", model="Zyphra/Zamba2-7B-Instruct-v2")
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-v2")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-7B-Instruct-v2")
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/Zamba2-7B-Instruct-v2 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-v2"
# 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-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Zyphra/Zamba2-7B-Instruct-v2

SGLang

How to use Zyphra/Zamba2-7B-Instruct-v2 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-v2" \
    --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-v2",
		"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-v2" \
        --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-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Zyphra/Zamba2-7B-Instruct-v2 with Docker Model Runner:
```
docker model run hf.co/Zyphra/Zamba2-7B-Instruct-v2
```

Zamba2-7B-Instruct-v2 / config.json

pglo

Upload folder using huggingface_hub

54438e6 verified about 1 year ago

raw

history blame contribute delete

2.43 kB

	{
	"adapter_rank": 128,
	"add_bias_linear": false,
	"architectures": [
	"Zamba2ForCausalLM"
	],
	"attention_dropout": 0.0,
	"attention_head_dim": 224,
	"attention_hidden_size": 7168,
	"bos_token_id": 1,
	"chunk_size": 256,
	"eos_token_id": 2,
	"ffn_hidden_size": 14336,
	"hidden_act": "gelu",
	"hidden_size": 3584,
	"hybrid_layer_ids": [
	6,
	11,
	17,
	23,
	29,
	35,
	41,
	47,
	53,
	59,
	65,
	71,
	77
	],
	"initializer_range": 0.02,
	"intermediate_size": 14336,
	"kv_channels": 112,
	"layers_block_type": [
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"hybrid",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"hybrid",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"hybrid",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"hybrid",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"hybrid",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"hybrid",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"hybrid",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"hybrid",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"hybrid",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"hybrid",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"hybrid",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"hybrid",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"hybrid",
	"mamba",
	"mamba",
	"mamba"
	],
	"mamba_d_conv": 4,
	"mamba_d_state": 64,
	"mamba_expand": 2,
	"mamba_headdim": 64,
	"mamba_ngroups": 2,
	"max_position_embeddings": 4096,
	"model_type": "zamba2",
	"n_mamba_heads": 112,
	"num_attention_heads": 32,
	"num_hidden_layers": 81,
	"num_key_value_heads": 32,
	"num_logits_to_keep": 1,
	"num_mem_blocks": 2,
	"num_query_groups": 32,
	"pad_token_id": 0,
	"rms_norm_eps": 1e-05,
	"rope_theta": 10000,
	"time_step_floor": 0.0001,
	"time_step_limit": null,
	"time_step_max": 0.1,
	"time_step_min": 0.001,
	"transformers_version": "4.49.0",
	"use_cache": true,
	"use_conv_bias": true,
	"use_long_context": false,
	"use_mem_eff_path": false,
	"use_mem_rope": true,
	"use_shared_attention_adapter": false,
	"use_shared_mlp_adapter": true,
	"vocab_size": 32000
	}