Instructions to use SashaSheykina/codeGen-finetuned-cXg-nl-to-code with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SashaSheykina/codeGen-finetuned-cXg-nl-to-code with Transformers:

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

pipe = pipeline("text-generation", model="SashaSheykina/codeGen-finetuned-cXg-nl-to-code")

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

tokenizer = AutoTokenizer.from_pretrained("SashaSheykina/codeGen-finetuned-cXg-nl-to-code")
model = AutoModelForCausalLM.from_pretrained("SashaSheykina/codeGen-finetuned-cXg-nl-to-code", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SashaSheykina/codeGen-finetuned-cXg-nl-to-code with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/SashaSheykina/codeGen-finetuned-cXg-nl-to-code

SGLang

How to use SashaSheykina/codeGen-finetuned-cXg-nl-to-code 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 "SashaSheykina/codeGen-finetuned-cXg-nl-to-code" \
    --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": "SashaSheykina/codeGen-finetuned-cXg-nl-to-code",
		"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 "SashaSheykina/codeGen-finetuned-cXg-nl-to-code" \
        --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": "SashaSheykina/codeGen-finetuned-cXg-nl-to-code",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SashaSheykina/codeGen-finetuned-cXg-nl-to-code with Docker Model Runner:
```
docker model run hf.co/SashaSheykina/codeGen-finetuned-cXg-nl-to-code
```

SashaSheykina commited on Jul 24, 2024

Commit

fa6e65e

verified ·

1 Parent(s): 0275b69

Training in progress, epoch 3

Browse files

Files changed (1) hide show

runs/Jul24_10-12-47_9a19e5edcc76/events.out.tfevents.1721815967.9a19e5edcc76.16200.0 +2 -2

runs/Jul24_10-12-47_9a19e5edcc76/events.out.tfevents.1721815967.9a19e5edcc76.16200.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd0adb9b2ea720b860e15fc698ff5a2e62d0fde30d75445e7c21e3bdde4a784b
-size 5390

 version https://git-lfs.github.com/spec/v1
+oid sha256:02f0a1d0a31deeb243dad512b59355286647b15ee94935c87597fabb334c3465
+size 5738