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

Libraries

How to use codeparrot/codeparrot-small with Transformers:

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

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use codeparrot/codeparrot-small with vLLM:

Install from pip and serve model

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

Use Docker

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

SGLang

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

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

codeparrot-small

Commit History

Mar 19, 2023

22:49
Adding `safetensors` variant of this model⁠

SFconvertbot

65819a0

Jul 3, 2022

19:54
update metadata

loubnabnl HF Staff

e7e4f5d
19:51
add model metadata

loubnabnl HF Staff

5fd9ae2

Jun 24, 2022

19:23
Revert "add eval_results step 150000"⁠

loubnabnl HF Staff

9600f1e
19:20
add eval_results step 150000

loubnabnl HF Staff

a338b10
08:24
update lvwerra namespace

lvwerra HF Staff

6d1687a

Nov 24, 2021

09:38
Update README.md

lvwerra HF Staff

505bd87

Nov 7, 2021

18:27
final model

lvwerra HF Staff

7c27bb8
18:23
step 150000

lvwerra HF Staff

190a13b
16:16
step 135000

lvwerra HF Staff

5724e17
14:08
step 120000

lvwerra HF Staff

b58b427
12:01
step 105000

lvwerra HF Staff

c93cc06
09:54
step 90000

lvwerra HF Staff

73e0bf4
07:48
step 75000

lvwerra HF Staff

c8a25e7
05:41
step 60000

lvwerra HF Staff

a409272
03:35
step 45000

lvwerra HF Staff

5ed0776
01:28
step 30000

lvwerra HF Staff

d425b2d

Nov 6, 2021

23:22
step 15000

lvwerra HF Staff

acc8d6f
21:13
Update config.json

lvwerra HF Staff

61c58c1
17:54
Update codeparrot_training.py

lvwerra HF Staff

74c33a2
07:21
tweak data loader to log metrics

lvwerra HF Staff

24790fd

Nov 5, 2021

14:27
Create README.md

lvwerra HF Staff

62d4de7
14:26
Create requirements.txt

lvwerra HF Staff

f3ed84c
14:23
Create codeparrot_training.py

lvwerra HF Staff

27393ce
11:32
add tokenizer

lvwerra HF Staff

5263940
11:32
add model

lvwerra HF Staff

a9700b7
11:31
initial commit

system HF Staff

3033877

Commit History

Mar 19, 2023

Adding `safetensors` variant of this model⁠

Jul 3, 2022

update metadata

add model metadata

Jun 24, 2022

Revert "add eval_results step 150000"⁠

add eval_results step 150000

update lvwerra namespace

Nov 24, 2021

Update README.md

Nov 7, 2021

final model

step 150000

step 135000

step 120000

step 105000

step 90000

step 75000

step 60000

step 45000

step 30000

Nov 6, 2021

step 15000

Update config.json

Update codeparrot_training.py

tweak data loader to log metrics

Nov 5, 2021

Create README.md

Create requirements.txt

Create codeparrot_training.py

add tokenizer

add model

initial commit