Instructions to use bigcode/starcoder2-15b-instruct-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bigcode/starcoder2-15b-instruct-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="bigcode/starcoder2-15b-instruct-v0.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bigcode/starcoder2-15b-instruct-v0.1")
model = AutoModelForCausalLM.from_pretrained("bigcode/starcoder2-15b-instruct-v0.1", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bigcode/starcoder2-15b-instruct-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bigcode/starcoder2-15b-instruct-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bigcode/starcoder2-15b-instruct-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bigcode/starcoder2-15b-instruct-v0.1

SGLang

How to use bigcode/starcoder2-15b-instruct-v0.1 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 "bigcode/starcoder2-15b-instruct-v0.1" \
    --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": "bigcode/starcoder2-15b-instruct-v0.1",
		"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 "bigcode/starcoder2-15b-instruct-v0.1" \
        --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": "bigcode/starcoder2-15b-instruct-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bigcode/starcoder2-15b-instruct-v0.1 with Docker Model Runner:
```
docker model run hf.co/bigcode/starcoder2-15b-instruct-v0.1
```

yuxiang630 commited on Apr 29, 2024

Commit

cc7bf2c

1 Parent(s): b120b50

refactor: use hyperlinks for images

Browse files

Files changed (1) hide show

README.md +6 -7

README.md CHANGED Viewed

@@ -86,19 +86,17 @@ model-index:
 # StarCoder2-Instruct: Self-Aligned, Transparent, and Fully Permissive
-<!-- <center>
-    <img src="https://huggingface.co/datasets/bigcode/admin_private/resolve/main/starcoder2_banner.png" alt="SC2" width="900" height="600">
-</center> -->
 ## Model Summary
 We introduce StarCoder2-15B-Instruct-v0.1, the very first entirely self-aligned code Large Language Model (LLM) trained with a fully permissive and transparent pipeline. Our open-source pipeline uses StarCoder2-15B to generate thousands of instruction-response pairs, which are then used to fine-tune StarCoder-15B itself without any human annotations or distilled data from huge and proprietary LLMs.
-- **Model:** [bigcode/starCoder2-15b-instruct-v0.1](https://huggingface.co/bigcode/starcoder2-instruct-15b-v0.1)
 - **Code:** [bigcode-project/starcoder2-self-align](https://github.com/bigcode-project/starcoder2-self-align)
 - **Dataset:** [bigcode/self-oss-instruct-sc2-exec-filter-50k](https://huggingface.co/datasets/bigcode/self-oss-instruct-sc2-exec-filter-50k/)
-![self-alignment pipeline](assets/star-align-pipeline.svg)
 ## Use
@@ -177,14 +175,15 @@ The model also inherits the bias, risks, and limitations from its base StarCoder
 ## Evaluation on EvalPlus, LiveCodeBench, and DS-1000
-![EvalPlus](assets/sc2-instruct-evalplus.png)
-![LiveCodeBench and DS-1000](assets/sc2-instruct-lcb-ds.png)
 ## Training Details
 ### Hyperparameters
 - **Learning rate:** 1e-5
 - **Epoch:** 4
 - **Batch size:** 64

 # StarCoder2-Instruct: Self-Aligned, Transparent, and Fully Permissive
+![Banner](https://huggingface.co/datasets/bigcode/starcoder2-instruct-assets/resolve/main/banner.png)
 ## Model Summary
 We introduce StarCoder2-15B-Instruct-v0.1, the very first entirely self-aligned code Large Language Model (LLM) trained with a fully permissive and transparent pipeline. Our open-source pipeline uses StarCoder2-15B to generate thousands of instruction-response pairs, which are then used to fine-tune StarCoder-15B itself without any human annotations or distilled data from huge and proprietary LLMs.
+- **Model:** [bigcode/starcoder2-15b-instruct-v0.1](https://huggingface.co/bigcode/starcoder2-instruct-15b-v0.1)
 - **Code:** [bigcode-project/starcoder2-self-align](https://github.com/bigcode-project/starcoder2-self-align)
 - **Dataset:** [bigcode/self-oss-instruct-sc2-exec-filter-50k](https://huggingface.co/datasets/bigcode/self-oss-instruct-sc2-exec-filter-50k/)
+![self-alignment pipeline](https://huggingface.co/datasets/bigcode/starcoder2-instruct-assets/resolve/main/method.png)
 ## Use
 ## Evaluation on EvalPlus, LiveCodeBench, and DS-1000
+![EvalPlus](https://huggingface.co/datasets/bigcode/starcoder2-instruct-assets/resolve/main/evalplus.png)
+![LiveCodeBench and DS-1000](https://huggingface.co/datasets/bigcode/starcoder2-instruct-assets/resolve/main/lcb-ds1000.png)
 ## Training Details
 ### Hyperparameters
+- **Optimizer:** Adafactor
 - **Learning rate:** 1e-5
 - **Epoch:** 4
 - **Batch size:** 64