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
```

lvwerra HF Staff commited on Nov 7, 2021

Commit

c93cc06

1 Parent(s): 73e0bf4

step 105000

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 sha256:63d09364f87227ff3b30d91c979a7e38e67e2b96dc11b61ecf3325873030fc37
-size 13698816

 version https://git-lfs.github.com/spec/v1
+oid sha256:3534218604c51409651fe367964be4867b183c6bbbf2288be3a646c6910c2b73
+size 16012166

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23268f86ad4503b2739780e16fe4bd1e8b19d5311ad3885e62da066b286c1cc1
 size 456677609

 version https://git-lfs.github.com/spec/v1
+oid sha256:181d54aea976f16349e356e2a9faa56ddf0686260f59633cc6fdf59f70275c68
 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 sha256:280e28dd391b194de4c841f555a21b284226d5c28d6820f97d785a43ee57318b
-size 16494592

 version https://git-lfs.github.com/spec/v1
+oid sha256:44b2bd843945a8503a913863bd8c8de3917dd42f04006cb79b50f1386e02df62
+size 19254691

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": 0.~~00017679938132976936~~, "samples": ~~17280000~~, "steps": ~~89999~~, "loss/train": 1.~~3141337633132935~~, "_runtime": ~~45488~~, "_timestamp": ~~1636278858~~, "_step": ~~90005~~, "loss/eval": 1.~~3116109371185303~~, "perplexity": 3.~~712148904800415~~}


1	+ {"lr": 0.00010564581571251794, "samples": 20160000, "steps": 104999, "loss/train": 1.339005708694458, "_runtime": 53081, "_timestamp": 1636286451, "_step": 105006, "loss/eval": 1.2772471904754639, "perplexity": 3.5867526531219482}

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91b4dc3eabf92be91c9de1871399d855e061f2efede9c84a321a90d921c8b036
-size 40422824

 version https://git-lfs.github.com/spec/v1
+oid sha256:561c5e41176b13255f273de8c6c1794d803104f68c2f2b704fbb611f9ad7bade
+size 47160887

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b84f6c88d3eae9576c86edac237c6977ae1d21b01ffb994286d9fe7332dca98
-size 29158472

 version https://git-lfs.github.com/spec/v1
+oid sha256:88c936c0f70ceebf93bb420b3a5d0e5310fb6410f105703a882710363e7235bf
+size 34433809