Instructions to use Zyphra/ZAYA1-reasoning-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Zyphra/ZAYA1-reasoning-base with Transformers:

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

pipe = pipeline("text-generation", model="Zyphra/ZAYA1-reasoning-base")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Zyphra/ZAYA1-reasoning-base", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Zyphra/ZAYA1-reasoning-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Zyphra/ZAYA1-reasoning-base"
# 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/ZAYA1-reasoning-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Zyphra/ZAYA1-reasoning-base

SGLang

How to use Zyphra/ZAYA1-reasoning-base 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/ZAYA1-reasoning-base" \
    --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/ZAYA1-reasoning-base",
		"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/ZAYA1-reasoning-base" \
        --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/ZAYA1-reasoning-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Zyphra/ZAYA1-reasoning-base with Docker Model Runner:
```
docker model run hf.co/Zyphra/ZAYA1-reasoning-base
```

ZAYA1-reasoning-base / config.json

yury-zyphra

Upload folder using huggingface_hub

de5f76a verified 6 months ago

raw

history blame contribute delete

4.31 kB

	{
	"activation_func": "swiglu",
	"activation_func_fp8_input_store": false,
	"add_bias_linear": false,
	"apply_rope_fusion": true,
	"architectures": [
	"ZayaForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bias_activation_fusion": true,
	"bos_token_id": 2,
	"cca": true,
	"cca_num_q_heads": [
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0,
	8,
	0
	],
	"dtype": "bfloat16",
	"eos_token_id": 1,
	"ffn_hidden_size_list": [
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096,
	0,
	4096
	],
	"fused_add_norm": false,
	"gated_linear_unit": true,
	"hidden_size": 2048,
	"kv_channels": 128,
	"lm_head_bias": false,
	"max_position_embeddings": 32768,
	"model_type": "zaya",
	"moe_router_topk": 1,
	"norm_epsilon": 1e-05,
	"normalization": "RMSNorm",
	"num_attention_heads": 16,
	"num_hidden_layers": 120,
	"num_key_value_heads": 2,
	"num_query_groups_list": [
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0,
	2,
	0
	],
	"pad_token_id": 0,
	"residual_in_fp32": false,
	"partial_rotary_factor": 0.5,
	"rope_scaling": false,
	"rope_theta": 1000000,
	"scale_residual_merge": true,
	"sliding_window": null,
	"zaya_high_prec": true,
	"zaya_layers": [
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16,
	"a",
	16
	],
	"zaya_mlp_expansion": [
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256,
	0,
	256
	],
	"zaya_use_eda": true,
	"zaya_use_mod": true,
	"transformers_version": "4.57.1",
	"use_cache": true,
	"vocab_size": 262272
	}