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

Libraries

How to use msong/codeparrot-ds-small with Transformers:

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

pipe = pipeline("text-generation", model="msong/codeparrot-ds-small")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("msong/codeparrot-ds-small")
model = AutoModelForCausalLM.from_pretrained("msong/codeparrot-ds-small", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use msong/codeparrot-ds-small with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/msong/codeparrot-ds-small

SGLang

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

Docker Model Runner
How to use msong/codeparrot-ds-small with Docker Model Runner:
```
docker model run hf.co/msong/codeparrot-ds-small
```

msong commited on Sep 3, 2023

Commit

dfc134d

1 Parent(s): 870336f

End of training

Browse files

Files changed (2) hide show

generation_config.json +6 -0
pytorch_model.bin +1 -1

generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.31.0"
+}

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1113e22ae0e7d44bfd78fb2b9315893f7d04957d0d74d48518c03488d82d4bbc
 size 497017693

 version https://git-lfs.github.com/spec/v1
+oid sha256:0acf538e415001dbac2efce10942d4c27845a9b78f9c0fd3a68c2721c2ad2ac1
 size 497017693