Instructions to use t-bank-ai/ruDialoGPT-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use t-bank-ai/ruDialoGPT-small with Transformers:

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

pipe = pipeline("text-generation", model="t-bank-ai/ruDialoGPT-small")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("t-bank-ai/ruDialoGPT-small", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use t-bank-ai/ruDialoGPT-small with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "t-bank-ai/ruDialoGPT-small"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "t-bank-ai/ruDialoGPT-small",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/t-bank-ai/ruDialoGPT-small

SGLang

How to use t-bank-ai/ruDialoGPT-small 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 "t-bank-ai/ruDialoGPT-small" \
    --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": "t-bank-ai/ruDialoGPT-small",
		"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 "t-bank-ai/ruDialoGPT-small" \
        --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": "t-bank-ai/ruDialoGPT-small",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use t-bank-ai/ruDialoGPT-small with Docker Model Runner:
```
docker model run hf.co/t-bank-ai/ruDialoGPT-small
```

This generation model is based on sberbank-ai/rugpt3small_based_on_gpt2. It's trained on large corpus of dialog data and can be used for buildning generative conversational agents

The model was trained with context size 3

On a private validation set we calculated metrics introduced in this paper:

Sensibleness: Crowdsourcers were asked whether model's response makes sense given the context
Specificity: Crowdsourcers were asked whether model's response is specific for given context, in other words we don't want our model to give general and boring responses
SSA which is the average of two metrics above (Sensibleness Specificity Average)

	sensibleness	specificity	SSA
tinkoff-ai/ruDialoGPT-small	0.64	0.5	0.57
tinkoff-ai/ruDialoGPT-medium	0.78	0.69	0.735

How to use:

import torch
from transformers import AutoTokenizer, AutoModelWithLMHead

tokenizer = AutoTokenizer.from_pretrained('tinkoff-ai/ruDialoGPT-small')
model = AutoModelWithLMHead.from_pretrained('tinkoff-ai/ruDialoGPT-small')
inputs = tokenizer('@@ПЕРВЫЙ@@ привет @@ВТОРОЙ@@ привет @@ПЕРВЫЙ@@ как дела? @@ВТОРОЙ@@', return_tensors='pt')
generated_token_ids = model.generate(
    **inputs,
    top_k=10,
    top_p=0.95,
    num_beams=3,
    num_return_sequences=3,
    do_sample=True,
    no_repeat_ngram_size=2,
    temperature=1.2,
    repetition_penalty=1.2,
    length_penalty=1.0,
    eos_token_id=50257,
    max_new_tokens=40
)
context_with_response = [tokenizer.decode(sample_token_ids) for sample_token_ids in generated_token_ids]
context_with_response

Downloads last month: 2,350

Model tree for t-bank-ai/ruDialoGPT-small

Finetunes

1 model

Spaces using t-bank-ai/ruDialoGPT-small 2

Paper for t-bank-ai/ruDialoGPT-small

Towards a Human-like Open-Domain Chatbot

Paper • 2001.09977 • Published Jan 27, 2020