Instructions to use stabilityai/stablelm-base-alpha-3b-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stabilityai/stablelm-base-alpha-3b-v2 with Transformers:

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

pipe = pipeline("text-generation", model="stabilityai/stablelm-base-alpha-3b-v2", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("stabilityai/stablelm-base-alpha-3b-v2", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use stabilityai/stablelm-base-alpha-3b-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stabilityai/stablelm-base-alpha-3b-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stabilityai/stablelm-base-alpha-3b-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/stabilityai/stablelm-base-alpha-3b-v2

SGLang

How to use stabilityai/stablelm-base-alpha-3b-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 "stabilityai/stablelm-base-alpha-3b-v2" \
    --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": "stabilityai/stablelm-base-alpha-3b-v2",
		"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 "stabilityai/stablelm-base-alpha-3b-v2" \
        --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": "stabilityai/stablelm-base-alpha-3b-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use stabilityai/stablelm-base-alpha-3b-v2 with Docker Model Runner:
```
docker model run hf.co/stabilityai/stablelm-base-alpha-3b-v2
```

stablelm-base-alpha-3b-v2 / model.safetensors.index.json

Jonathan Tow

Upload folder using huggingface_hub

ecf8036 about 3 years ago

Raw

History Blame Contribute Delete

16.4 kB

	{
	"metadata": {
	"total_size": 11183738880
	},
	"weight_map": {
	"lm_head.weight": "model-00002-of-00002.safetensors",
	"transformer.embed.weight": "model-00001-of-00002.safetensors",
	"transformer.final_norm.bias": "model-00002-of-00002.safetensors",
	"transformer.final_norm.weight": "model-00002-of-00002.safetensors",
	"transformer.layers.0.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.0.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.0.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.0.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.0.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.1.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.1.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.1.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.1.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.1.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.10.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.10.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.10.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.10.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.10.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.11.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.11.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.11.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.11.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.11.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.12.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.12.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.12.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.12.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.12.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.13.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.13.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.13.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.13.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.13.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.14.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.14.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.14.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.14.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.14.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.15.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.15.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.15.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.15.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.15.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.16.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.16.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.16.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.16.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.16.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.17.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.17.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.17.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.17.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.17.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.18.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.18.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.18.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.18.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.18.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.19.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.19.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.19.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.19.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.19.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.2.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.2.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.2.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.2.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.2.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.20.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.20.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.20.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.20.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.20.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.21.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.21.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.21.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.21.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.21.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.22.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.22.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.22.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.22.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.22.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.23.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.23.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.23.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.23.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.23.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.24.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.24.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.24.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.24.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.24.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.25.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.25.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.25.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.25.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.25.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.26.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.26.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.26.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.26.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.26.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.27.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.27.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.27.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.27.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.27.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.28.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.28.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.28.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.28.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.28.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.29.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.29.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.29.mlp.out_proj.weight": "model-00002-of-00002.safetensors",
	"transformer.layers.29.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.29.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.3.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.3.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.3.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.3.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.3.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.30.attention.out_proj.weight": "model-00002-of-00002.safetensors",
	"transformer.layers.30.attention.qkv_proj.weight": "model-00002-of-00002.safetensors",
	"transformer.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
	"transformer.layers.30.mlp.out_proj.weight": "model-00002-of-00002.safetensors",
	"transformer.layers.30.norm.bias": "model-00002-of-00002.safetensors",
	"transformer.layers.30.norm.weight": "model-00002-of-00002.safetensors",
	"transformer.layers.31.attention.out_proj.weight": "model-00002-of-00002.safetensors",
	"transformer.layers.31.attention.qkv_proj.weight": "model-00002-of-00002.safetensors",
	"transformer.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
	"transformer.layers.31.mlp.out_proj.weight": "model-00002-of-00002.safetensors",
	"transformer.layers.31.norm.bias": "model-00002-of-00002.safetensors",
	"transformer.layers.31.norm.weight": "model-00002-of-00002.safetensors",
	"transformer.layers.4.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.4.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.4.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.4.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.4.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.5.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.5.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.5.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.5.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.5.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.6.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.6.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.6.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.6.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.6.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.7.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.7.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.7.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.7.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.7.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.8.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.8.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.8.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.8.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.8.norm.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.9.attention.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.9.attention.qkv_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.9.mlp.out_proj.weight": "model-00001-of-00002.safetensors",
	"transformer.layers.9.norm.bias": "model-00001-of-00002.safetensors",
	"transformer.layers.9.norm.weight": "model-00001-of-00002.safetensors"
	}
	}