Instructions to use athugodage/ruDialoGPT-small_10 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use athugodage/ruDialoGPT-small_10 with Transformers:

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

pipe = pipeline("text-generation", model="athugodage/ruDialoGPT-small_10")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("athugodage/ruDialoGPT-small_10")
model = AutoModelForCausalLM.from_pretrained("athugodage/ruDialoGPT-small_10", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use athugodage/ruDialoGPT-small_10 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "athugodage/ruDialoGPT-small_10"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "athugodage/ruDialoGPT-small_10",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/athugodage/ruDialoGPT-small_10

SGLang

How to use athugodage/ruDialoGPT-small_10 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 "athugodage/ruDialoGPT-small_10" \
    --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": "athugodage/ruDialoGPT-small_10",
		"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 "athugodage/ruDialoGPT-small_10" \
        --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": "athugodage/ruDialoGPT-small_10",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use athugodage/ruDialoGPT-small_10 with Docker Model Runner:
```
docker model run hf.co/athugodage/ruDialoGPT-small_10
```

ruDialoGPT-small_10

This model is a fine-tuned version of tinkoff-ai/ruDialoGPT-small on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.4977

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 1
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 2
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	55	1.3283
No log	2.0	110	1.2672
No log	3.0	165	1.3883
No log	4.0	220	1.3489
No log	5.0	275	1.4106
No log	6.0	330	1.4384
No log	7.0	385	1.4511
No log	8.0	440	1.4744
No log	9.0	495	1.4796
0.9816	10.0	550	1.4977

Framework versions

Transformers 4.33.3
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.13.3

Downloads last month: 10

Model tree for athugodage/ruDialoGPT-small_10

Base model

t-bank-ai/ruDialoGPT-small

Finetuned

(1)

this model