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

Libraries

How to use stabilityai/stablecode-completion-alpha-3b with Transformers:

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

pipe = pipeline("text-generation", model="stabilityai/stablecode-completion-alpha-3b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("stabilityai/stablecode-completion-alpha-3b")
model = AutoModelForCausalLM.from_pretrained("stabilityai/stablecode-completion-alpha-3b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use stabilityai/stablecode-completion-alpha-3b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/stabilityai/stablecode-completion-alpha-3b

SGLang

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

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

reshinthadith commited on Aug 8, 2023

Commit

46ef235

1 Parent(s): 004f712

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -66,7 +66,7 @@ The first pre-training stage relies on 300B tokens sourced from various top prog
 ### Training Procedure
-The model is pre-trained on the dataset mixes mentioned above in mixed-precision BF16), optimized with AdamW, and trained using the NeoX tokenizer with a vocabulary size of 49k.
 * **Software**: We use a fork of gpt-neox ([EleutherAI, 2021](https://github.com/EleutherAI/gpt-neox)) and train under 2D parallelism (Data and Tensor Parallel) with ZeRO-1 ([Rajbhandari et al., 2019](https://arxiv.org/abs/1910.02054v3)) and rely on flash-attention as well as rotary embedding kernels from FlashAttention-2 ([Dao et al., 2023](https://tridao.me/publications/flash2/flash2.pdf))

 ### Training Procedure
+The model is pre-trained on the dataset mixes mentioned above in mixed-precision BF16), optimized with AdamW, and trained using the StarCoder tokenizer with a vocabulary size of 49k.
 * **Software**: We use a fork of gpt-neox ([EleutherAI, 2021](https://github.com/EleutherAI/gpt-neox)) and train under 2D parallelism (Data and Tensor Parallel) with ZeRO-1 ([Rajbhandari et al., 2019](https://arxiv.org/abs/1910.02054v3)) and rely on flash-attention as well as rotary embedding kernels from FlashAttention-2 ([Dao et al., 2023](https://tridao.me/publications/flash2/flash2.pdf))