Instructions to use elinaparajuli/Codebert-Code-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use elinaparajuli/Codebert-Code-finetuned with Transformers:

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

pipe = pipeline("text-generation", model="elinaparajuli/Codebert-Code-finetuned")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("elinaparajuli/Codebert-Code-finetuned")
model = AutoModelForCausalLM.from_pretrained("elinaparajuli/Codebert-Code-finetuned")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use elinaparajuli/Codebert-Code-finetuned with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/elinaparajuli/Codebert-Code-finetuned

SGLang

How to use elinaparajuli/Codebert-Code-finetuned 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 "elinaparajuli/Codebert-Code-finetuned" \
    --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": "elinaparajuli/Codebert-Code-finetuned",
		"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 "elinaparajuli/Codebert-Code-finetuned" \
        --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": "elinaparajuli/Codebert-Code-finetuned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use elinaparajuli/Codebert-Code-finetuned with Docker Model Runner:
```
docker model run hf.co/elinaparajuli/Codebert-Code-finetuned
```

elinaparajuli commited on Apr 26, 2024

Commit

a47be75

verified ·

1 Parent(s): b2b4cab

Upload 4 files

Browse files

Files changed (4) hide show

merges.txt +0 -0
special_tokens_map.json +1 -0
tokenizer_config.json +1 -0
vocab.json +0 -0

merges.txt ADDED Viewed

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

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"model_max_length": 512}

vocab.json ADDED Viewed

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