Instructions to use kdf/python-docstring-generation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kdf/python-docstring-generation with Transformers:

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

pipe = pipeline("text-generation", model="kdf/python-docstring-generation")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kdf/python-docstring-generation")
model = AutoModelForCausalLM.from_pretrained("kdf/python-docstring-generation")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use kdf/python-docstring-generation with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/kdf/python-docstring-generation

SGLang

How to use kdf/python-docstring-generation 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 "kdf/python-docstring-generation" \
    --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": "kdf/python-docstring-generation",
		"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 "kdf/python-docstring-generation" \
        --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": "kdf/python-docstring-generation",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kdf/python-docstring-generation with Docker Model Runner:
```
docker model run hf.co/kdf/python-docstring-generation
```

qhduan commited on Jul 29, 2022

Commit

24ecd4c

1 Parent(s): b943174

add model

Browse files

Files changed (2) hide show

config.json +1 -1
pytorch_model.bin +2 -2

config.json CHANGED Viewed

@@ -2,7 +2,7 @@
   "_name_or_path": "python-docstring-generation",
   "activation_function": "gelu_new",
   "architectures": [
-    "CodeGenModel"
   ],
   "attn_pdrop": 0.0,
   "bos_token_id": 1,

   "_name_or_path": "python-docstring-generation",
   "activation_function": "gelu_new",
   "architectures": [
+    "CodeGenForCausalLM"
   ],
   "attn_pdrop": 0.0,
   "bos_token_id": 1,

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09a8044a87cfe6e31da41718f11cb92fbac770db46b6d6c536dd523dc0fd322c
-size 1300869715

 version https://git-lfs.github.com/spec/v1
+oid sha256:5097ad0cd2b14e928c00d124a4fc510403cfe515186bb562f6f8fda5d59de43d
+size 1510792527