Instructions to use pierreqi/starcoderbase-1b-cont-r with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pierreqi/starcoderbase-1b-cont-r with Transformers:

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

pipe = pipeline("text-generation", model="pierreqi/starcoderbase-1b-cont-r")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pierreqi/starcoderbase-1b-cont-r")
model = AutoModelForCausalLM.from_pretrained("pierreqi/starcoderbase-1b-cont-r")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use pierreqi/starcoderbase-1b-cont-r with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pierreqi/starcoderbase-1b-cont-r"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pierreqi/starcoderbase-1b-cont-r",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pierreqi/starcoderbase-1b-cont-r

SGLang

How to use pierreqi/starcoderbase-1b-cont-r 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 "pierreqi/starcoderbase-1b-cont-r" \
    --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": "pierreqi/starcoderbase-1b-cont-r",
		"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 "pierreqi/starcoderbase-1b-cont-r" \
        --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": "pierreqi/starcoderbase-1b-cont-r",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pierreqi/starcoderbase-1b-cont-r with Docker Model Runner:
```
docker model run hf.co/pierreqi/starcoderbase-1b-cont-r
```

pierreqi commited on May 3, 2025

Commit

7bdf35c

verified ·

1 Parent(s): 8baf8cf

Training in progress, step 7353

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/May03_09-59-35_e3afa8a6535e/events.out.tfevents.1746266378.e3afa8a6535e.8970.0 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01176665b538a51ee071a7eba25a1640fd02bcdbde7c708f729d39204a17c22b
 size 2274449392

 version https://git-lfs.github.com/spec/v1
+oid sha256:8784a9f47c6f7a5b6e55b907ffb4209c08733750771c33bc75fae30edae97776
 size 2274449392

runs/May03_09-59-35_e3afa8a6535e/events.out.tfevents.1746266378.e3afa8a6535e.8970.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cea4cc8e6d735cb0fc25a2ef2d708d34277af1ddae9909869bab60e91bdfec1
-size 20122

 version https://git-lfs.github.com/spec/v1
+oid sha256:04a31388d4dd5cda0bd587e0d3ee5ab3239b1b3b7a855be26497d2d384aab876
+size 21109