Instructions to use Azrail/smallm_70_instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Azrail/smallm_70_instruct with Transformers:

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

pipe = pipeline("text-generation", model="Azrail/smallm_70_instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Azrail/smallm_70_instruct", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Azrail/smallm_70_instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Azrail/smallm_70_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": "Azrail/smallm_70_instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Azrail/smallm_70_instruct

SGLang

How to use Azrail/smallm_70_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 "Azrail/smallm_70_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": "Azrail/smallm_70_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 "Azrail/smallm_70_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": "Azrail/smallm_70_instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Azrail/smallm_70_instruct with Docker Model Runner:
```
docker model run hf.co/Azrail/smallm_70_instruct
```

smallm_70_instruct / config.json

Azrail

Upload SmalLmForCausalLM

d9b459c verified over 1 year ago

Raw History Blame Contribute Delete

1.25 kB

	{
	"architectures": [
	"SmalLmForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.1,
	"auto_map": {
	"AutoConfig": "config.SmalLmConfig",
	"AutoModelForCausalLM": "model.SmalLmForCausalLM"
	},
	"balancing_coef": 0.0001,
	"bos_token_id": 1,
	"embedding_dropout": 0.0,
	"eos_token_id": 0,
	"expert_size": 576,
	"gate_noise": false,
	"head_size": 64,
	"hidden_size": 512,
	"high_rotations": 32,
	"initializer_range": 0.02,
	"intermediate_size": 1024,
	"layer_dropout": 0.1,
	"low_rotations": 1,
	"max_seq_len": 2048,
	"mlp_bias": false,
	"model_type": "smallm",
	"moe_bias": false,
	"moe_period": 2,
	"no_moe_layers": 10,
	"noisy_experts": false,
	"num_attention_heads": 8,
	"num_hidden_layers": 20,
	"num_kv_heads": 2,
	"original_seq_len": 1024,
	"pad_token_id": 0,
	"positional_bias_type": "rope",
	"rms_affine": false,
	"rms_norm_eps": 1e-06,
	"rope_base": 100000,
	"routed_experts": 8,
	"shared_experts": 1,
	"sliding_window_attention": true,
	"sliding_window_context": 1024,
	"sliding_window_period": 4,
	"static_residual": true,
	"token_experts": 3,
	"torch_dtype": "float32",
	"transformers_version": "4.50.3",
	"use_cache": true,
	"use_moe": false,
	"vocab_size": 60000
	}