Instructions to use vanillaOVO/correction_2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vanillaOVO/correction_2 with Transformers:

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

pipe = pipeline("text-generation", model="vanillaOVO/correction_2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("vanillaOVO/correction_2")
model = AutoModelForCausalLM.from_pretrained("vanillaOVO/correction_2")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use vanillaOVO/correction_2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vanillaOVO/correction_2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vanillaOVO/correction_2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/vanillaOVO/correction_2

SGLang

How to use vanillaOVO/correction_2 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 "vanillaOVO/correction_2" \
    --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": "vanillaOVO/correction_2",
		"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 "vanillaOVO/correction_2" \
        --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": "vanillaOVO/correction_2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use vanillaOVO/correction_2 with Docker Model Runner:
```
docker model run hf.co/vanillaOVO/correction_2
```

This is a corrected merge of pre-trained language models created using mergekit.

More descriptions of the model will be added soon.

Loading the Model

Use the following Python code to load the model:

import torch
from transformers import MistralForCausalLM, AutoTokenizer

model = MistralForCausalLM.from_pretrained("vanillaOVO/correction_2", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("vanillaOVO/correction_2")

Generating Text

To generate text, use the following Python code:

text = "Large language models are "
inputs = tokenizer(text, return_tensors="pt")

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: 65

Safetensors

Model size

7B params

Tensor type

BF16