Instructions to use yhytoto12/revert-Qwen2.5-0.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yhytoto12/revert-Qwen2.5-0.5B with Transformers:

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

pipe = pipeline("text-generation", model="yhytoto12/revert-Qwen2.5-0.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

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

tokenizer = AutoTokenizer.from_pretrained("yhytoto12/revert-Qwen2.5-0.5B")
model = AutoModelForCausalLM.from_pretrained("yhytoto12/revert-Qwen2.5-0.5B", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yhytoto12/revert-Qwen2.5-0.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yhytoto12/revert-Qwen2.5-0.5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yhytoto12/revert-Qwen2.5-0.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yhytoto12/revert-Qwen2.5-0.5B

SGLang

How to use yhytoto12/revert-Qwen2.5-0.5B 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 "yhytoto12/revert-Qwen2.5-0.5B" \
    --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": "yhytoto12/revert-Qwen2.5-0.5B",
		"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 "yhytoto12/revert-Qwen2.5-0.5B" \
        --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": "yhytoto12/revert-Qwen2.5-0.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yhytoto12/revert-Qwen2.5-0.5B with Docker Model Runner:
```
docker model run hf.co/yhytoto12/revert-Qwen2.5-0.5B
```

Improve model card for ReVerT (Think, Verbalize, then Speak) verbalizer

by nielsr HF Staff - opened Sep 22, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+58

-161

nielsr

Sep 22, 2025

This PR significantly enhances the model card for the yhytoto12/revert-Qwen2.5-3B verbalizer model.

Key updates include:

Adding the pipeline_tag: text-generation to the metadata, which helps users discover the model via the Hugging Face Hub's pipeline filters (e.g., https://huggingface.co/models?pipeline_tag=text-generation).
Including specific tags such as qwen2, verbalization, summarization, dialogue-system, speech-friendly, and llm-acceleration for better categorization and discoverability.
Specifying the language: en and base_model: Qwen/Qwen2.5-3B-Instruct in the metadata, along with the datasets used for training.
A comprehensive model description derived from the paper abstract and project introduction.
Direct links to the official Hugging Face paper page (https://huggingface.co/papers/2509.16028), project page (https://yhytoto12.github.io/TVS-ReVerT), and GitHub repository (https://github.com/yhytoto12/TVS-ReVerT).
The core framework image from the paper to visually explain the model.
Updated "Training Details" with links to the datasets and a brief overview of the training procedure.
The official BibTeX citation for proper academic attribution.
The "How to Get Started" section now directs users to the GitHub repository for detailed usage examples and interactive demos, in line with the available documentation.

These improvements make the model card much more informative, user-friendly, and discoverable.

Improve model card for ReVerT (Think, Verbalize, then Speak) verbalizer8940faa1

yhytoto12

Owner Sep 22, 2025

Thank you for the PR!

yhytoto12 changed pull request status to merged Sep 22, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment