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")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps

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
```

lvwerra HF Staff commited on Nov 7, 2021

Commit

5724e17

1 Parent(s): b58b427

step 135000

Browse files

Files changed (7) hide show

log/debug_0.log +2 -2
pytorch_model.bin +1 -1
runs/Nov06_21-16-12_leandro-16x-v100/events.out.tfevents.1636233372.leandro-16x-v100.4368.0 +2 -2
wandb/run-20211106_211610-dtkf2u0m/files/output.log +0 -0
wandb/run-20211106_211610-dtkf2u0m/files/wandb-summary.json +1 -1
wandb/run-20211106_211610-dtkf2u0m/logs/debug-internal.log +2 -2
wandb/run-20211106_211610-dtkf2u0m/run-dtkf2u0m.wandb +2 -2

log/debug_0.log CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf6094c45fc3e010fc1074dbf79201d0f430e681cc612c3437b20de2f2a0f4d0
-size 18335040

 version https://git-lfs.github.com/spec/v1
+oid sha256:3985f373c9fe3e04c7a5bb69a431c47dbc500db77d2c6dacb0e55b0bc2a6cc6e
+size 20664714

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b23a0934363ae319b0ae39a2808f7f37d2b201e913e2e4af233ea50e8cb735cc
 size 456677609

 version https://git-lfs.github.com/spec/v1
+oid sha256:623eca7922e78d2ba9bd1777a2612608a26cddaba88f5107707ac77b767f5920
 size 456677609

runs/Nov06_21-16-12_leandro-16x-v100/events.out.tfevents.1636233372.leandro-16x-v100.4368.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e562d2c5bb23c0ce88a34a4fe4620feb19cf0903e990421a56cd85411af6ea9d
-size 22014790

 version https://git-lfs.github.com/spec/v1
+oid sha256:7c5d2f64d07fd0eb7f2feb7e1fd952d8c66d69e3acb200a1de2f78c1a429c6bc
+size 24774889

wandb/run-20211106_211610-dtkf2u0m/files/output.log CHANGED Viewed

The diff for this file is too large to render. See raw diff

wandb/run-20211106_211610-dtkf2u0m/files/wandb-summary.json CHANGED Viewed

	@@ -1 +1 @@
1	- {"lr": 4.~~900387301979531e~~-05, "samples": ~~23040000~~, "steps": ~~119999~~, "loss/train": 1.~~1156840324401855~~, "_runtime": ~~60735~~, "_timestamp": ~~1636294105~~, "_step": ~~120007~~, "loss/eval": 1.~~2484334707260132~~, "perplexity": 3.~~484879493713379~~}


1	+ {"lr": 1.2567648771774215e-05, "samples": 25920000, "steps": 134999, "loss/train": 1.248957633972168, "_runtime": 68378, "_timestamp": 1636301748, "_step": 135008, "loss/eval": 1.2335491180419922, "perplexity": 3.4333934783935547}

wandb/run-20211106_211610-dtkf2u0m/logs/debug-internal.log CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1cf6af0e2d6f1060c2e59b583dc644a0ba63c785f4b37cf28d683bb6f0785a
-size 53909925

 version https://git-lfs.github.com/spec/v1
+oid sha256:864b05961e10b41c85540d88ab249497b08429393f8a0906c188fccc7940a840
+size 60663376

wandb/run-20211106_211610-dtkf2u0m/run-dtkf2u0m.wandb CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3e2bdfb2872b7abd649d44a8f89202a54d8ddf449c850062523b819b2c7ed71
-size 39696563

 version https://git-lfs.github.com/spec/v1
+oid sha256:854aab1e842d7cad61d6b782b3aee5b17501ab4f30d7c291c4de9c7f8dbc0624
+size 44960275