Instructions to use TULLUS/codeparrot-small-multi-F32 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TULLUS/codeparrot-small-multi-F32 with Transformers:

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

pipe = pipeline("text-generation", model="TULLUS/codeparrot-small-multi-F32")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TULLUS/codeparrot-small-multi-F32")
model = AutoModelForCausalLM.from_pretrained("TULLUS/codeparrot-small-multi-F32", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TULLUS/codeparrot-small-multi-F32 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TULLUS/codeparrot-small-multi-F32"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TULLUS/codeparrot-small-multi-F32",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TULLUS/codeparrot-small-multi-F32

SGLang

How to use TULLUS/codeparrot-small-multi-F32 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 "TULLUS/codeparrot-small-multi-F32" \
    --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": "TULLUS/codeparrot-small-multi-F32",
		"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 "TULLUS/codeparrot-small-multi-F32" \
        --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": "TULLUS/codeparrot-small-multi-F32",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TULLUS/codeparrot-small-multi-F32 with Docker Model Runner:
```
docker model run hf.co/TULLUS/codeparrot-small-multi-F32
```

TULLUS commited on 16 days ago

Commit

3348642

verified ·

1 Parent(s): d6cc476

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -22,7 +22,7 @@ metrics:
 A verified full-precision (F32) Safetensors conversion of the original [CodeParrot Small Multi](https://huggingface.co/codeparrot/codeparrot-small-multi) checkpoint. This release preserves the source model's learned tensor values; it is not a new training run or fine-tune.
-CodeParrot Small Multi is a small GPT-2 causal language model for **code completion and continuation**, not an instruction-tuned chat model. It was pretrained on cleaned GitHub code and described upstream as covering Java, JavaScript, PHP, Python, C#, C++, Go, Ruby, and TypeScript. Treat it as an older, compact code-model baseline for experimentation—not as a reliable standalone coding assistant.
 ## Intended use and realistic expectations

 A verified full-precision (F32) Safetensors conversion of the original [CodeParrot Small Multi](https://huggingface.co/codeparrot/codeparrot-small-multi) checkpoint. This release preserves the source model's learned tensor values; it is not a new training run or fine-tune.
+CodeParrot Small Multi is a small GPT-2 causal language model for **code completion and continuation**, not an instruction-tuned chat model. It was pretrained on cleaned GitHub code and described upstream as covering Java, JavaScript, PHP, Python, C#, C++, Go, Ruby, and TypeScript. Treat it as an older, compact code-model baseline for experimentation not as standalone coding assistant.
 ## Intended use and realistic expectations