Instructions to use Loke-60000/Christina-7B-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Loke-60000/Christina-7B-chat with Transformers:

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

pipe = pipeline("text-generation", model="Loke-60000/Christina-7B-chat")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Loke-60000/Christina-7B-chat")
model = AutoModelForCausalLM.from_pretrained("Loke-60000/Christina-7B-chat", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Loke-60000/Christina-7B-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Loke-60000/Christina-7B-chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Loke-60000/Christina-7B-chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Loke-60000/Christina-7B-chat

SGLang

How to use Loke-60000/Christina-7B-chat 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 "Loke-60000/Christina-7B-chat" \
    --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": "Loke-60000/Christina-7B-chat",
		"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 "Loke-60000/Christina-7B-chat" \
        --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": "Loke-60000/Christina-7B-chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Loke-60000/Christina-7B-chat with Docker Model Runner:
```
docker model run hf.co/Loke-60000/Christina-7B-chat
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Christina-7b

Christina-7b is a chatbot inspired by the character Kurisu from the popular "Steins;Gate" games. This chatbot is the result of Llama 2 7b chat being trained on 30,032 interactions involving Kurisu to replicate the persona of the AI 'Amadeus' from "Steins;Gate 0".

Access Information

As of the current status, Christina-7b is available for private access only. We appreciate your understanding and interest in our project. 🤖📚

Sample of the Dataset

Here's a glimpse of the dataset that has contributed to the training of Christina-7b:

Contact

For any inquiries or potential collaborations, please feel free to reach out to us at lokman@viktorchondria.com .

Downloads last month: -

Loke-60000
/

Christina-7B-chat

You need to agree to share your contact information to access this model

Christina-7b

Access Information

Sample of the Dataset

Contact

Spaces using Loke-60000/Christina-7B-chat 2