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 6, 2021

Commit

74c33a2

1 Parent(s): 24790fd

Update codeparrot_training.py

Browse files

Files changed (1) hide show

codeparrot_training.py +11 -6

codeparrot_training.py CHANGED Viewed

@@ -15,7 +15,7 @@ import wandb
 class ConstantLengthDataset(IterableDataset):
-    def __init__(self, tokenizer, dataset, seq_length=1024,
                  num_of_sequences=1024, chars_per_token=3.6):
         self.tokenizer = tokenizer
         self.concat_token_id = tokenizer.bos_token_id
@@ -23,6 +23,7 @@ class ConstantLengthDataset(IterableDataset):
         self.seq_length = seq_length
         self.input_characters = seq_length * chars_per_token * num_of_sequences
         self.epoch = 0
     def __iter__(self):
         iterator = iter(self.dataset)
@@ -36,9 +37,13 @@ class ConstantLengthDataset(IterableDataset):
                     buffer.append(next(iterator)['content'])
                     buffer_len += len(buffer[-1])
                 except StopIteration:
-                    iterator = iter(self.dataset)
-                    self.epoch += 1
-                    logger.info(f"Dataset epoch: {self.epoch}")
             tokenized_inputs = tokenizer(buffer, truncation=False)['input_ids']
             all_token_ids = []
             for tokenized_input in tokenized_inputs:
@@ -77,9 +82,9 @@ def create_dataloaders(dataset_name, args):
     train_data = train_data.shuffle(buffer_size=args.shuffle_buffer,
                                     seed=args.seed)
     valid_data = load_dataset(dataset_name+'-valid', split="train", **ds_kwargs)
-    train_dataset = ConstantLengthDataset(tokenizer, train_data,
                                           seq_length=args.seq_length)
-    valid_dataset = ConstantLengthDataset(tokenizer, valid_data,
                                           seq_length=args.seq_length)
     train_dataloader=DataLoader(train_dataset, batch_size=args.train_batch_size)
     eval_dataloader=DataLoader(valid_dataset, batch_size=args.valid_batch_size)

 class ConstantLengthDataset(IterableDataset):
+    def __init__(self, tokenizer, dataset, infinite=False, seq_length=1024,
                  num_of_sequences=1024, chars_per_token=3.6):
         self.tokenizer = tokenizer
         self.concat_token_id = tokenizer.bos_token_id
         self.seq_length = seq_length
         self.input_characters = seq_length * chars_per_token * num_of_sequences
         self.epoch = 0
+        self.infinite = infinite
     def __iter__(self):
         iterator = iter(self.dataset)
                     buffer.append(next(iterator)['content'])
                     buffer_len += len(buffer[-1])
                 except StopIteration:
+                    if self.infinite:
+                        iterator = iter(self.dataset)
+                        self.epoch += 1
+                        logger.info(f"Dataset epoch: {self.epoch}")
+                    else:
+                        more_examples = False
+                        break
             tokenized_inputs = tokenizer(buffer, truncation=False)['input_ids']
             all_token_ids = []
             for tokenized_input in tokenized_inputs:
     train_data = train_data.shuffle(buffer_size=args.shuffle_buffer,
                                     seed=args.seed)
     valid_data = load_dataset(dataset_name+'-valid', split="train", **ds_kwargs)
+    train_dataset = ConstantLengthDataset(tokenizer, train_data, infinite=True,
                                           seq_length=args.seq_length)
+    valid_dataset = ConstantLengthDataset(tokenizer, valid_data, infinite=False,
                                           seq_length=args.seq_length)
     train_dataloader=DataLoader(train_dataset, batch_size=args.train_batch_size)
     eval_dataloader=DataLoader(valid_dataset, batch_size=args.valid_batch_size)