Instructions to use BohdanPetryshyn/code-llama-openapi-completion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BohdanPetryshyn/code-llama-openapi-completion with Transformers:

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

pipe = pipeline("text-generation", model="BohdanPetryshyn/code-llama-openapi-completion")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BohdanPetryshyn/code-llama-openapi-completion")
model = AutoModelForCausalLM.from_pretrained("BohdanPetryshyn/code-llama-openapi-completion", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use BohdanPetryshyn/code-llama-openapi-completion with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/BohdanPetryshyn/code-llama-openapi-completion

SGLang

How to use BohdanPetryshyn/code-llama-openapi-completion 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 "BohdanPetryshyn/code-llama-openapi-completion" \
    --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": "BohdanPetryshyn/code-llama-openapi-completion",
		"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 "BohdanPetryshyn/code-llama-openapi-completion" \
        --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": "BohdanPetryshyn/code-llama-openapi-completion",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use BohdanPetryshyn/code-llama-openapi-completion with Docker Model Runner:
```
docker model run hf.co/BohdanPetryshyn/code-llama-openapi-completion
```

code-llama-openapi-completion / tokenizer.model

Commit History

Add tokenizer from the original Code Llama model

ed459f2

Code Llama FIM Fine Tuning by Bohdan Petryshyn commited on Jun 15, 2024

temporarily remove tokenizer

cf9fff0

Bohdan Petryshyn commited on Jun 15, 2024

Add tokenizer from the original Code Llama model

eb31108

Code Llama FIM Fine Tuning by Bohdan Petryshyn commited on Jun 15, 2024

temporarily remove tokenizer

116a1a9

Bohdan Petryshyn commited on Jun 15, 2024

Add tokenizer from the original Code Llama model

2f5121d

Code Llama FIM Fine Tuning by Bohdan Petryshyn commited on Jun 15, 2024

Commit History

Add tokenizer from the original Code Llama model ed459f2

temporarily remove tokenizer cf9fff0

Add tokenizer from the original Code Llama model eb31108

temporarily remove tokenizer 116a1a9

Add tokenizer from the original Code Llama model 2f5121d

Add tokenizer from the original Code Llama model

ed459f2

temporarily remove tokenizer

cf9fff0

Add tokenizer from the original Code Llama model

eb31108

temporarily remove tokenizer

116a1a9

Add tokenizer from the original Code Llama model

2f5121d