Instructions to use Azrail/smallm_70 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Azrail/smallm_70 with Transformers:

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

pipe = pipeline("text-generation", model="Azrail/smallm_70", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Azrail/smallm_70", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Azrail/smallm_70 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Azrail/smallm_70"
# 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",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Azrail/smallm_70

SGLang

How to use Azrail/smallm_70 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" \
    --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",
		"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" \
        --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",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Azrail/smallm_70 with Docker Model Runner:
```
docker model run hf.co/Azrail/smallm_70
```

smallm_70 / README.md

Azrail

Update README.md

34f3cd9 verified over 1 year ago

preview code

Raw History Blame Contribute Delete

3.71 kB

metadata

library_name: transformers
license: mit
datasets:
  - YourDatasetName/if-applicable
language:
  - en
pipeline_tag: text-generation
tags:
  - transformer
  - language-model
  - experimental

SmalLM

SmalLM is a series of small transformer models built from scratch for language modeling. This project is designed to explore innovative approaches to transformer architectures through modular pipelines for pretraining, fine-tuning, and alignment.

Uses

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Azrail/smallm_70")
model = AutoModelForCausalLM.from_pretrained("Azrail/smallm_70", trust_remote_code=True)
inputs = tokenizer("How are you?", return_tensors="pt")

out = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.batch_decode(out))

Model Details**

Key Features:

Grouped Query Attention (GQA).
Mixture-of-Experts with auxiliary loss-free balancing.
ALiBi (Attention with Linear Biases) or Rotary Position Embedding (RoPE).
NTK-by-parts RoPE interpolation for extends context length.

Pre-Training:

Model	Training Data	Steps	Content Length	Tokens	LR	Batch Size	Precision
SmalLM-70M	smollm-corpus	70k	1024	18B	1e-3	0.25M	bfloat16
SmalLM-150M	smollm-corpus	-	1024	-	-	-	bfloat16
SmalLM-350M	smollm-corpus	-	1024	-	-	-	bfloat16
SmalLM-500M	smollm-corpus	-	1024	-	-	-	bfloat16

Evaluation: Evaluation runing with lm-evaluation-harness

Model	MMLU	ARC easy/hard	PIQA	HellaSwag	OBQA	Winogrande
SmalLM-70M	25.33	51.47/25.68	61.75	30.31	30.8	50.83
SmalLM-150M	-	-	-	-	-	-
SmalLM-350M	-	-	-	-	-	-
SmalLM-500M	-	-	-	-	-	-

Procedure:

Framework versions

Transformers 4.50.3
Pytorch 2.6.0+cu126
Datasets 3.5.0
Tokenizers 0.21.1