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

Libraries

How to use Siyris/DialoGPT-medium-SIY with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Siyris/DialoGPT-medium-SIY")
model = AutoModelForCausalLM.from_pretrained("Siyris/DialoGPT-medium-SIY")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Siyris/DialoGPT-medium-SIY with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Siyris/DialoGPT-medium-SIY

SGLang

How to use Siyris/DialoGPT-medium-SIY 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 "Siyris/DialoGPT-medium-SIY" \
    --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": "Siyris/DialoGPT-medium-SIY",
		"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 "Siyris/DialoGPT-medium-SIY" \
        --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": "Siyris/DialoGPT-medium-SIY",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Siyris/DialoGPT-medium-SIY with Docker Model Runner:
```
docker model run hf.co/Siyris/DialoGPT-medium-SIY
```

DialoGPT Trained on a customized various spiritual texts and mixed with various different character personalities.

This is an instance of microsoft/DialoGPT-medium trained on the energy complex known as Ra. Some text has been changed from the original with the intention of making it fit our discord server better. I've also trained it on various channeling experiences. I'm testing mixing this dataset with character from popular shows with the intention of creating a more diverse dialogue. I built a Discord AI chatbot based on this model for internal use within Siyris, Inc. Chat with the model:

from transformers import AutoTokenizer, AutoModelWithLMHead
  
tokenizer = AutoTokenizer.from_pretrained("Siyris/DialoGPT-medium-SIY")
model = AutoModelWithLMHead.from_pretrained("Siyris/DialoGPT-medium-SIY")
# Let's chat for 4 lines
for step in range(4):
    # encode the new user input, add the eos_token and return a tensor in Pytorch
    new_user_input_ids = tokenizer.encode(input(">> User:") + tokenizer.eos_token, return_tensors='pt')
    # print(new_user_input_ids)
    # append the new user input tokens to the chat history
    bot_input_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1) if step > 0 else new_user_input_ids
    # generated a response while limiting the total chat history to 1000 tokens, 
    chat_history_ids = model.generate(
        bot_input_ids, max_length=200,
        pad_token_id=tokenizer.eos_token_id,  
        no_repeat_ngram_size=3,       
        do_sample=True, 
        top_k=100, 
        top_p=0.7,
        temperature=0.8
    )
    
    # pretty print last ouput tokens from bot
    print("SIY: {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))

Downloads last month: 5