Instructions to use radm/rugpt3medium-tathagata with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use radm/rugpt3medium-tathagata with Transformers:

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

pipe = pipeline("text-generation", model="radm/rugpt3medium-tathagata")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("radm/rugpt3medium-tathagata")
model = AutoModelForCausalLM.from_pretrained("radm/rugpt3medium-tathagata")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use radm/rugpt3medium-tathagata with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "radm/rugpt3medium-tathagata"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "radm/rugpt3medium-tathagata",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/radm/rugpt3medium-tathagata

SGLang

How to use radm/rugpt3medium-tathagata 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 "radm/rugpt3medium-tathagata" \
    --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": "radm/rugpt3medium-tathagata",
		"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 "radm/rugpt3medium-tathagata" \
        --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": "radm/rugpt3medium-tathagata",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use radm/rugpt3medium-tathagata with Docker Model Runner:
```
docker model run hf.co/radm/rugpt3medium-tathagata
```

RuGPT3Medium-tathagata

Model description

This is the model for text generation for Russian based on rugpt3medium_based_on_gpt2.

Intended uses & limitations

Тhis model was trained and run to generate text on RTX 3080

How to use

from transformers import GPT2LMHeadModel, GPT2Tokenizer
import torch
DEVICE = torch.device("cuda:0")

model_name_or_path = "radm/rugpt3medium-tathagata"
tokenizer = GPT2Tokenizer.from_pretrained("sberbank-ai/rugpt3medium_based_on_gpt2")
model = GPT2LMHeadModel.from_pretrained(model_name_or_path).to(DEVICE)

text = "В чем смысл жизни?\n"
input_ids = tokenizer.encode(text, return_tensors="pt").to(DEVICE)
model.eval()
with torch.no_grad():
    out = model.generate(input_ids, 
                        do_sample=True,
                        num_beams=4,
                        temperature=1.1,
                        top_p=0.9,
                        top_k=50,
                        max_length=250,
                        min_length=50,
                        early_stopping=True,
                        no_repeat_ngram_size=2
                        )

generated_text = list(map(tokenizer.decode, out))[0]
print()
print(generated_text)

Dataset

Dataset based on summaries of major Buddhist, Hindu and Advaita texts such as:

Diamond Sutra
Lankavatara Sutra
Sri Nisargadatta Maharaj quotes
Quotes from the Bhagavad Gita

Dataset link: tathagata

Downloads last month: 5

Safetensors

Model size

0.5B params

Tensor type

F32