Text Generation
Transformers
Russian
text2text-generation
t5
customer-support
russian
reviews
response-generation
finetuned
Instructions to use baldic/otzovik with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use baldic/otzovik with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="baldic/otzovik")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("baldic/otzovik", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use baldic/otzovik with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "baldic/otzovik" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "baldic/otzovik", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/baldic/otzovik
- SGLang
How to use baldic/otzovik 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 "baldic/otzovik" \ --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": "baldic/otzovik", "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 "baldic/otzovik" \ --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": "baldic/otzovik", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use baldic/otzovik with Docker Model Runner:
docker model run hf.co/baldic/otzovik
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# ruT5 Customer Support Response Generator
|
| 2 |
|
| 3 |
Модель для автоматической генерации ответов на отзывы клиентов, основанная на ruT5-base.
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- ru
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
base_model: ai-forever/ruT5-base
|
| 6 |
+
tags:
|
| 7 |
+
- text2text-generation
|
| 8 |
+
- t5
|
| 9 |
+
- customer-support
|
| 10 |
+
- russian
|
| 11 |
+
- reviews
|
| 12 |
+
- response-generation
|
| 13 |
+
- finetuned
|
| 14 |
+
datasets:
|
| 15 |
+
- custom
|
| 16 |
+
metrics:
|
| 17 |
+
- loss
|
| 18 |
+
library_name: transformers
|
| 19 |
+
pipeline_tag: text2text-generation
|
| 20 |
+
widget:
|
| 21 |
+
- text: "Отзыв: Товар пришёл быстро, качество отличное!"
|
| 22 |
+
example_title: "Позитивный отзыв"
|
| 23 |
+
- text: "Отзыв: Товар не соответствует описанию, очень разочарован"
|
| 24 |
+
example_title: "Негативный отзыв"
|
| 25 |
+
- text: "Отзыв: Когда будет доставка? Жду уже неделю"
|
| 26 |
+
example_title: "Вопрос о доставке"
|
| 27 |
+
model-index:
|
| 28 |
+
- name: ruT5-base-customer-support
|
| 29 |
+
results: []
|
| 30 |
+
---
|
| 31 |
+
|
| 32 |
# ruT5 Customer Support Response Generator
|
| 33 |
|
| 34 |
Модель для автоматической генерации ответов на отзывы клиентов, основанная на ruT5-base.
|