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

Libraries

How to use transformersbook/codeparrot with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("transformersbook/codeparrot")
model = AutoModelForCausalLM.from_pretrained("transformersbook/codeparrot")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use transformersbook/codeparrot with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/transformersbook/codeparrot

SGLang

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

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

lvwerra HF Staff commited on Sep 26, 2021

Commit

8da8f1b

1 Parent(s): b49b823

step 650000

Browse files

Files changed (7) hide show

log/debug_0.log +2 -2
pytorch_model.bin +1 -1
runs/Sep20_14-28-12_leandro-16x-v100/events.out.tfevents.1632148092.leandro-16x-v100.8660.0 +2 -2
wandb/run-20210920_142810-36cw69uv/files/output.log +2 -2
wandb/run-20210920_142810-36cw69uv/files/wandb-summary.json +1 -1
wandb/run-20210920_142810-36cw69uv/logs/debug-internal.log +2 -2
wandb/run-20210920_142810-36cw69uv/run-36cw69uv.wandb +2 -2

log/debug_0.log CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f153ce712b5bc1097ad83bbd9677a1ba6a4914f94a2e8490f0a869545389190c
-size 92146384

 version https://git-lfs.github.com/spec/v1
+oid sha256:ee220760c5f375e0c80acf1d7576597dae2d3d4738c9f9e33271b2aeb0b8e6c9
+size 99896492

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:814e8e012de13f212029b2f505e10668d5f3bdb3c05bf4e875b6c92f9a175b8f
 size 6169094681

 version https://git-lfs.github.com/spec/v1
+oid sha256:2326bdc79ceab6fc8c948ad37ae9f6dd8d52d7118b67952d34a150ed5caa32bb
 size 6169094681

runs/Sep20_14-28-12_leandro-16x-v100/events.out.tfevents.1632148092.leandro-16x-v100.8660.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:858dea1b60ba94e02091625b5838ce2361114b84953ae0e9ace0ee28261e59ee
-size 110335188

 version https://git-lfs.github.com/spec/v1
+oid sha256:1069c0665b89660094cbced31870a5e19295a29bb8f21d16bc1b1823eb755aa8
+size 119535287

wandb/run-20210920_142810-36cw69uv/files/output.log CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4844b0f15934e5fb67d01fa9d520540c4755529c2b3a62c8e586066239b4247b
-size 111014219

 version https://git-lfs.github.com/spec/v1
+oid sha256:09a49644213bc3c8a8a9465142d66e738fd003aa9aa0fc671d3c25fa385b99e2
+size 120281602

wandb/run-20210920_142810-36cw69uv/files/wandb-summary.json CHANGED Viewed

	@@ -1 +1 @@
1	- {"lr": 3.~~0144650016306685e~~-05, "samples": ~~19200000~~, "steps": ~~37499~~, "loss/train": 0.~~08109104633331299~~, "_runtime": ~~490397~~, "_timestamp": ~~1632638487~~, "_step": ~~600011~~, "loss/eval": 0.~~6023598313331604~~, "perplexity": 1.~~8264238834381104~~}


1	+ {"lr": 1.7358331080729474e-05, "samples": 20800000, "steps": 40624, "loss/train": 0.821692943572998, "_runtime": 531326, "_timestamp": 1632679416, "_step": 650012, "loss/eval": 0.5877718925476074, "perplexity": 1.799973487854004}

wandb/run-20210920_142810-36cw69uv/logs/debug-internal.log CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48e9b379f66cc8bbd8260627fe0f8d7eedd8851684c6828d9905f14b72732e72
-size 320101445

 version https://git-lfs.github.com/spec/v1
+oid sha256:dd50fb384dfc5b0a29bba17aad652a0c705a1e50ceada00a99c3569a26620905
+size 346779425

wandb/run-20210920_142810-36cw69uv/run-36cw69uv.wandb CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd2bc99b25c26a341aae2dc32c4c26a29b594af67fd7b20130271a55200e0c31
-size 266014090

 version https://git-lfs.github.com/spec/v1
+oid sha256:b90a5cf5e9e18b5b6667676d66ac11bbf42426fe0583f37aac340aae04617e24
+size 288297860