Text Generation
Transformers
ONNX
Safetensors
English
bart
text2text-generation
g2p
cisco
Grapheme-to-Phoneme
Instructions to use cisco-ai/mini-bart-g2p with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cisco-ai/mini-bart-g2p with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="cisco-ai/mini-bart-g2p")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("cisco-ai/mini-bart-g2p") model = AutoModelForSeq2SeqLM.from_pretrained("cisco-ai/mini-bart-g2p") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use cisco-ai/mini-bart-g2p with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "cisco-ai/mini-bart-g2p" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "cisco-ai/mini-bart-g2p", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/cisco-ai/mini-bart-g2p
- SGLang
How to use cisco-ai/mini-bart-g2p 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 "cisco-ai/mini-bart-g2p" \ --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": "cisco-ai/mini-bart-g2p", "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 "cisco-ai/mini-bart-g2p" \ --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": "cisco-ai/mini-bart-g2p", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use cisco-ai/mini-bart-g2p with Docker Model Runner:
docker model run hf.co/cisco-ai/mini-bart-g2p
Upload tokenizer.json
#2
by vrdn23 - opened
- tokenizer.json +9 -2
tokenizer.json
CHANGED
|
@@ -54,9 +54,16 @@
|
|
| 54 |
"special": true
|
| 55 |
}
|
| 56 |
],
|
| 57 |
-
"normalizer":
|
|
|
|
|
|
|
| 58 |
"pre_tokenizer": {
|
| 59 |
-
"type": "
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
},
|
| 61 |
"post_processor": {
|
| 62 |
"type": "RobertaProcessing",
|
|
|
|
| 54 |
"special": true
|
| 55 |
}
|
| 56 |
],
|
| 57 |
+
"normalizer": {
|
| 58 |
+
"type": "Lowercase"
|
| 59 |
+
},
|
| 60 |
"pre_tokenizer": {
|
| 61 |
+
"type": "Split",
|
| 62 |
+
"pattern": {
|
| 63 |
+
"String": ""
|
| 64 |
+
},
|
| 65 |
+
"behavior": "Removed",
|
| 66 |
+
"invert": false
|
| 67 |
},
|
| 68 |
"post_processor": {
|
| 69 |
"type": "RobertaProcessing",
|