Instructions to use Respair/Phoneme_to_Grapheme_v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Respair/Phoneme_to_Grapheme_v2 with Transformers:

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

pipe = pipeline("text-generation", model="Respair/Phoneme_to_Grapheme_v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Respair/Phoneme_to_Grapheme_v2")
model = AutoModelForCausalLM.from_pretrained("Respair/Phoneme_to_Grapheme_v2")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Respair/Phoneme_to_Grapheme_v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Respair/Phoneme_to_Grapheme_v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Respair/Phoneme_to_Grapheme_v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Respair/Phoneme_to_Grapheme_v2

SGLang

How to use Respair/Phoneme_to_Grapheme_v2 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 "Respair/Phoneme_to_Grapheme_v2" \
    --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": "Respair/Phoneme_to_Grapheme_v2",
		"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 "Respair/Phoneme_to_Grapheme_v2" \
        --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": "Respair/Phoneme_to_Grapheme_v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Respair/Phoneme_to_Grapheme_v2 with Docker Model Runner:
```
docker model run hf.co/Respair/Phoneme_to_Grapheme_v2
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Load

 vllm serve Respair/Phoneme_to_Grapheme_v2 --dtype bfloat16

Inference

from openai import OpenAI
import torch

DEVICE = "cuda:0" if torch.cuda.is_available() else "cpu"
TORCH_DTYPE = torch.float16 if "cuda" in DEVICE else torch.float32


openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)


def graphemize(param):
    model_name="Respair/Phoneme_to_Grapheme_v2"
    chat_response = client.chat.completions.create(
        model=model_name,
        max_tokens=1024,
        # top_p=0.6,
        temperature=0.1,
        messages=[
            {"role": "user", "content": f"turn this text into normal persian: {param}"}
        ]
    )
    
    result = chat_response.choices[0].message.content
    return result.lstrip()

graphemize("be gozAreshe khabargozAriye dAnshjuyAne irAn.")

Downloads last month: -

Safetensors

Model size

4B params

Tensor type

BF16