Instructions to use thongbuind/SAI_35M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thongbuind/SAI_35M with Transformers:

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

pipe = pipeline("text-generation", model="thongbuind/SAI_35M", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("thongbuind/SAI_35M", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use thongbuind/SAI_35M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thongbuind/SAI_35M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thongbuind/SAI_35M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/thongbuind/SAI_35M

SGLang

How to use thongbuind/SAI_35M 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 "thongbuind/SAI_35M" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thongbuind/SAI_35M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "thongbuind/SAI_35M" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thongbuind/SAI_35M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use thongbuind/SAI_35M with Docker Model Runner:
```
docker model run hf.co/thongbuind/SAI_35M
```

SAI_35M / source_config /35M.json

thongbuind

Use original SAI source for inference

fb6b7f8 verified 2 days ago

Raw

History Blame Contribute Delete

173 Bytes

	{
	"d_model": 512,
	"num_heads": 8,
	"num_kv_heads": 8,
	"num_layers": 8,
	"ff_dim": 2048,
	"batch_size": 70,
	"freeze": [0, 1],
	"num_workers": 1
	}