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

Libraries

How to use mamiksik/CodeBertaCLM with Transformers:

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

pipe = pipeline("text-generation", model="mamiksik/CodeBertaCLM")

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

tokenizer = AutoTokenizer.from_pretrained("mamiksik/CodeBertaCLM")
model = AutoModelForCausalLM.from_pretrained("mamiksik/CodeBertaCLM", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mamiksik/CodeBertaCLM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/mamiksik/CodeBertaCLM

SGLang

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

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

CodeBertaCLM

Commit History

Dec 20, 2023

14:36
Librarian Bot: Add base_model information to model⁠

librarian-bot

503972b

Jan 3, 2023

14:31
update model card README.md

mamiksik

8991511
14:30
End of training (Seq2SeqTraining) golden-water-7

mamiksik

42b5a2f

Jan 2, 2023

03:09
update model card README.md

mamiksik

76ad1ed
03:09
End of training (f1/bleu4) driven-oath-6

mamiksik

6efef96
00:08
update model card README.md

mamiksik

a2cfd15
00:07
End of training (f1/bleu4) vocal-snow-5

mamiksik

2470f3e

Jan 1, 2023

22:47
update model card README.md

mamiksik

529b56b
22:43
End of training (f1/bleu4) dummy-HzpWR3XatwWYzcjECdwj7e

mamiksik

6b55973
18:11
update model card README.md

mamiksik

d3cd2d3
18:11
End of training (f1/bleu4) stellar-butterfly-4

mamiksik

76974da
16:31
update model card README.md

mamiksik

765db09
16:30
End of training (f1/bleu4) good-smoke-3

mamiksik

ebe260e
13:38
initial commit

mamiksik

bde95d5

Commit History

Dec 20, 2023

Librarian Bot: Add base_model information to model⁠

Jan 3, 2023

update model card README.md

End of training (Seq2SeqTraining) golden-water-7

Jan 2, 2023

update model card README.md

End of training (f1/bleu4) driven-oath-6

update model card README.md

End of training (f1/bleu4) vocal-snow-5

Jan 1, 2023

update model card README.md

End of training (f1/bleu4) dummy-HzpWR3XatwWYzcjECdwj7e

update model card README.md

End of training (f1/bleu4) stellar-butterfly-4

update model card README.md

End of training (f1/bleu4) good-smoke-3

initial commit