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

Libraries

How to use stabilityai/stable-code-3b with Transformers:

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

pipe = pipeline("text-generation", model="stabilityai/stable-code-3b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("stabilityai/stable-code-3b")
model = AutoModelForCausalLM.from_pretrained("stabilityai/stable-code-3b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use stabilityai/stable-code-3b with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf stabilityai/stable-code-3b:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf stabilityai/stable-code-3b:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf stabilityai/stable-code-3b:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf stabilityai/stable-code-3b:Q5_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf stabilityai/stable-code-3b:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf stabilityai/stable-code-3b:Q5_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf stabilityai/stable-code-3b:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf stabilityai/stable-code-3b:Q5_K_M

Use Docker

docker model run hf.co/stabilityai/stable-code-3b:Q5_K_M

LM Studio
Jan

vLLM

How to use stabilityai/stable-code-3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stabilityai/stable-code-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/stable-code-3b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/stabilityai/stable-code-3b:Q5_K_M

SGLang

How to use stabilityai/stable-code-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/stable-code-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/stable-code-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/stable-code-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/stable-code-3b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use stabilityai/stable-code-3b with Ollama:
```
ollama run hf.co/stabilityai/stable-code-3b:Q5_K_M
```
Unsloth Desktop
Docker Model Runner
How to use stabilityai/stable-code-3b with Docker Model Runner:
```
docker model run hf.co/stabilityai/stable-code-3b:Q5_K_M
```

Lemonade

How to use stabilityai/stable-code-3b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull stabilityai/stable-code-3b:Q5_K_M

Run and chat with the model

lemonade run user.stable-code-3b-Q5_K_M

List all available models

lemonade list

Atomic Chat

ncoop57 commited on Jan 16, 2024

Commit

5c62545

verified ·

1 Parent(s): 40f4aad

Update README.md

Browse files

Files changed (1) hide show

README.md +20 -1

README.md CHANGED Viewed

@@ -97,7 +97,6 @@ model-index:
 | Replit Code V1.5 | 3B   | 23.0%  | 25.9%| 26.2%      | 23.6%| 23.2%| 21.5%|
 | Deci Coder       | 1B   | 19.1%  | 6.8% | 18.4%      | 16.7%| 2.1% | 1.7% |
 **Key Features**
 * Fill in Middle Capability (FIM)
 * Supports Long Context, trained with Sequences upto 16,384
@@ -207,6 +206,26 @@ The model is a decoder-only transformer similar to the LLaMA ([Touvron et al., 2
 The dataset is comprised of a filtered mixture of open-source large-scale datasets available on the [HuggingFace Hub](https://huggingface.co/datasets): Falcon RefinedWeb extract ([Penedo et al., 2023](https://huggingface.co/datasets/tiiuae/falcon-refinedweb)), along with [CommitPackFT](https://huggingface.co/datasets/bigcode/commitpackft) and [Github Issues](https://huggingface.co/datasets/bigcode/the-stack-github-issues) (BigCode., 2023), and StarCoder ([Li et al., 2023](https://arxiv.org/abs/2305.06161)). We further supplement our training with data from mathematical domains ([Azerbayev, Zhangir, et al., 2023](https://arxiv.org/abs/2310.10631) and, [Yu, Longhui, et al., 2023](https://arxiv.org/abs/2309.12284)).
 ### Training Procedure
 The model is pre-trained on the aforementioned datasets in `bfloat16` precision, optimized with AdamW.

 | Replit Code V1.5 | 3B   | 23.0%  | 25.9%| 26.2%      | 23.6%| 23.2%| 21.5%|
 | Deci Coder       | 1B   | 19.1%  | 6.8% | 18.4%      | 16.7%| 2.1% | 1.7% |
 **Key Features**
 * Fill in Middle Capability (FIM)
 * Supports Long Context, trained with Sequences upto 16,384
 The dataset is comprised of a filtered mixture of open-source large-scale datasets available on the [HuggingFace Hub](https://huggingface.co/datasets): Falcon RefinedWeb extract ([Penedo et al., 2023](https://huggingface.co/datasets/tiiuae/falcon-refinedweb)), along with [CommitPackFT](https://huggingface.co/datasets/bigcode/commitpackft) and [Github Issues](https://huggingface.co/datasets/bigcode/the-stack-github-issues) (BigCode., 2023), and StarCoder ([Li et al., 2023](https://arxiv.org/abs/2305.06161)). We further supplement our training with data from mathematical domains ([Azerbayev, Zhangir, et al., 2023](https://arxiv.org/abs/2310.10631) and, [Yu, Longhui, et al., 2023](https://arxiv.org/abs/2309.12284)).
+Top 18 programming languages trained on:
+- C
+- CPP
+- Java
+- JavaScript
+- CSS
+- Go
+- HTML
+- Ruby
+- Rust
+- Markdown
+- Shell
+- Php
+- Sql
+- R
+- Typescript
+- Python
+- Jupyter-Clean
+- RestructuredText
 ### Training Procedure
 The model is pre-trained on the aforementioned datasets in `bfloat16` precision, optimized with AdamW.