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

Libraries

How to use gavinqiangli/codeparrot-ds with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use gavinqiangli/codeparrot-ds with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/gavinqiangli/codeparrot-ds

SGLang

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

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

gavinqiangli commited on Feb 20, 2024

Commit

690e7fc

verified ·

1 Parent(s): 3f06788

Training in progress, step 20000

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/Feb20_15-46-50_48f91da73587/events.out.tfevents.1708444011.48f91da73587.188.0 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4858e65d3c48c189445dc02cd068bf2576b71b71cdd9746c45e3fad5823bdfb3
 size 496984704

 version https://git-lfs.github.com/spec/v1
+oid sha256:a5df9fab525d16c2215c95a1b7a0f0fa45fd6dbb9594177611ef4c28aed3c6c2
 size 496984704

runs/Feb20_15-46-50_48f91da73587/events.out.tfevents.1708444011.48f91da73587.188.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:374b7d251e81fda71dfe8a0015eccd8c8c45caead41c9018b192db267d3f7a98
-size 5716

 version https://git-lfs.github.com/spec/v1
+oid sha256:0296ea2e0e0c6e9038f23603e2ea73238cd64815b1fdeab2f7a99761b5df2c27
+size 6152