Instructions to use Jaszii/DialoGPT-Elysia with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jaszii/DialoGPT-Elysia with Transformers:

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

pipe = pipeline("text-generation", model="Jaszii/DialoGPT-Elysia")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Jaszii/DialoGPT-Elysia")
model = AutoModelForCausalLM.from_pretrained("Jaszii/DialoGPT-Elysia", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Jaszii/DialoGPT-Elysia with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jaszii/DialoGPT-Elysia"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jaszii/DialoGPT-Elysia",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Jaszii/DialoGPT-Elysia

SGLang

How to use Jaszii/DialoGPT-Elysia 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 "Jaszii/DialoGPT-Elysia" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jaszii/DialoGPT-Elysia",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Jaszii/DialoGPT-Elysia" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jaszii/DialoGPT-Elysia",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Jaszii/DialoGPT-Elysia with Docker Model Runner:
```
docker model run hf.co/Jaszii/DialoGPT-Elysia
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

DialoGPT-Elysia

This is a fine-tuned version of the DialoGPT-medium model trained on the dialogues of Elysia from the Elysian Archives chapter of the popular video game Honkai Impact. (Elysian archives)

This fine-tuned version of the model has been trained specifically on a dataset of dialogues featuring Elysia from the Elysian Archives chapter, and as such, it has a better understanding of her character and is able to generate responses that are more in line with her personality and behavior as portrayed in this specific chapter of the game.

To use this model, you will need to provide it with a prompt in the form of a conversation context or a specific question. The model will then generate a response based on the provided prompt and its understanding of Elysia's character in the Elysian Archives chapter.

Here is an example of how you might use the model:

Role	Response
User	Hey Elysia, how are you doing today?
Elysia	Doing well, thanks for asking. What about you?
User	I'm good.
Elysia	That’s good. I thought you’d let it go at that.

Role	Response
User	I heard that you are a skilled fighter, is that true?
Elysia	If I had to be ranked, I guess I would be first in command.

Please note that while this model is able to generate responses that are in line with Elysia's character, it is not able to provide any actual gameplay-related information or assistance. It is intended solely for generating text based on its understanding of Elysia's character.

Downloads last month: 128

Safetensors

Model size

0.4B params

Tensor type

F32

Model tree for Jaszii/DialoGPT-Elysia

Quantizations

2 models

Jaszii
/

DialoGPT-Elysia

DialoGPT-Elysia

Model tree for Jaszii/DialoGPT-Elysia

Space using Jaszii/DialoGPT-Elysia 1