Instructions to use mvasiliniuc/iva-codeint-swift with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mvasiliniuc/iva-codeint-swift with Transformers:

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

pipe = pipeline("text-generation", model="mvasiliniuc/iva-codeint-swift")

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

tokenizer = AutoTokenizer.from_pretrained("mvasiliniuc/iva-codeint-swift")
model = AutoModelForCausalLM.from_pretrained("mvasiliniuc/iva-codeint-swift", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mvasiliniuc/iva-codeint-swift with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/mvasiliniuc/iva-codeint-swift

SGLang

How to use mvasiliniuc/iva-codeint-swift 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 "mvasiliniuc/iva-codeint-swift" \
    --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": "mvasiliniuc/iva-codeint-swift",
		"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 "mvasiliniuc/iva-codeint-swift" \
        --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": "mvasiliniuc/iva-codeint-swift",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mvasiliniuc/iva-codeint-swift with Docker Model Runner:
```
docker model run hf.co/mvasiliniuc/iva-codeint-swift
```

iva-codeint-swift

Commit History

Jul 6, 2023

15:03
Adding `safetensors` variant of this model⁠

SFconvertbot

de821ae

Jun 2, 2023

17:16
Upload model

mvasiliniuc

0461263
16:49
Upload tokenizer

mvasiliniuc

d5d2765

May 9, 2023

21:14
add model

mvasiliniuc

5a64e0f
21:09
add model

mvasiliniuc

2b5d828
20:58
add tokenizer

mvasiliniuc

0b834e1
18:59
add tokenizer

mvasiliniuc

5f4abd9
18:59
initial commit

mvasiliniuc

86cc25c

Commit History

Jul 6, 2023

Adding `safetensors` variant of this model⁠

Jun 2, 2023

Upload model

Upload tokenizer

May 9, 2023

add model

add model

add tokenizer

add tokenizer

initial commit