Instructions to use alexue4/text-normalization-ru-new with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alexue4/text-normalization-ru-new with Transformers:

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

pipe = pipeline("text-generation", model="alexue4/text-normalization-ru-new")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("alexue4/text-normalization-ru-new")
model = AutoModelForSeq2SeqLM.from_pretrained("alexue4/text-normalization-ru-new", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use alexue4/text-normalization-ru-new with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alexue4/text-normalization-ru-new"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alexue4/text-normalization-ru-new",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/alexue4/text-normalization-ru-new

SGLang

How to use alexue4/text-normalization-ru-new 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 "alexue4/text-normalization-ru-new" \
    --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": "alexue4/text-normalization-ru-new",
		"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 "alexue4/text-normalization-ru-new" \
        --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": "alexue4/text-normalization-ru-new",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use alexue4/text-normalization-ru-new with Docker Model Runner:
```
docker model run hf.co/alexue4/text-normalization-ru-new
```

alexue4 commited on Jul 10, 2024

Commit

5d0453c

verified ·

1 Parent(s): 4148ae4

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -24

README.md CHANGED Viewed

@@ -1,11 +1,14 @@
 ---
 license: mit
-base_model: alexue4/text-normalization-ru-new
 tags:
 - generated_from_trainer
 model-index:
 - name: text-normalization-ru-new
   results: []
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -13,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 # text-normalization-ru-new
-This model is a fine-tuned version of [alexue4/text-normalization-ru-new](https://huggingface.co/alexue4/text-normalization-ru-new) on the None dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0008
 - Mean Distance: 0
@@ -45,30 +48,9 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 15
-### Training results
-| Training Loss | Epoch | Step  | Validation Loss | Mean Distance | Max Distance |
-|:-------------:|:-----:|:-----:|:---------------:|:-------------:|:------------:|
-| 0.0004        | 1.0   | 3059  | 0.0022          | 0             | 12           |
-| 0.0003        | 2.0   | 6118  | 0.0011          | 0             | 5            |
-| 0.0003        | 3.0   | 9177  | 0.0010          | 0             | 6            |
-| 0.0003        | 4.0   | 12236 | 0.0012          | 0             | 3            |
-| 0.0003        | 5.0   | 15295 | 0.0008          | 0             | 3            |
-| 0.0002        | 6.0   | 18354 | 0.0009          | 0             | 3            |
-| 0.0002        | 7.0   | 21413 | 0.0008          | 0             | 3            |
-| 0.0002        | 8.0   | 24472 | 0.0008          | 0             | 3            |
-| 0.0002        | 9.0   | 27531 | 0.0007          | 0             | 3            |
-| 0.0002        | 10.0  | 30590 | 0.0008          | 0             | 3            |
-| 0.0002        | 11.0  | 33649 | 0.0008          | 0             | 3            |
-| 0.0002        | 12.0  | 36708 | 0.0008          | 0             | 3            |
-| 0.0002        | 13.0  | 39767 | 0.0008          | 0             | 3            |
-| 0.0002        | 14.0  | 42826 | 0.0008          | 0             | 3            |
-| 0.0002        | 15.0  | 45885 | 0.0008          | 0             | 3            |
 ### Framework versions
 - Transformers 4.37.2
 - Pytorch 2.1.0+cu121
 - Datasets 2.16.1
-- Tokenizers 0.15.1

 ---
 license: mit
+base_model: cointegrated/rut5-small
 tags:
 - generated_from_trainer
 model-index:
 - name: text-normalization-ru-new
   results: []
+language:
+- ru
+pipeline_tag: text2text-generation
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 # text-normalization-ru-new
+This model is a fine-tuned version of [cointegrated/rut5-small](https://huggingface.co/cointegrated/rut5-small) on the Google Kadle and Custom dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0008
 - Mean Distance: 0
 - lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 15
 ### Framework versions
 - Transformers 4.37.2
 - Pytorch 2.1.0+cu121
 - Datasets 2.16.1
+- Tokenizers 0.15.1