Text Generation
Transformers
Safetensors
English
Hindi
Panjabi
language_model
multilingual
indic-languages
hindi
punjabi
small-model
Instructions to use PredictiveManish/Trimurti-LM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use PredictiveManish/Trimurti-LM with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="PredictiveManish/Trimurti-LM")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("PredictiveManish/Trimurti-LM", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use PredictiveManish/Trimurti-LM with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "PredictiveManish/Trimurti-LM" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "PredictiveManish/Trimurti-LM", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/PredictiveManish/Trimurti-LM
- SGLang
How to use PredictiveManish/Trimurti-LM 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 "PredictiveManish/Trimurti-LM" \ --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": "PredictiveManish/Trimurti-LM", "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 "PredictiveManish/Trimurti-LM" \ --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": "PredictiveManish/Trimurti-LM", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use PredictiveManish/Trimurti-LM with Docker Model Runner:
docker model run hf.co/PredictiveManish/Trimurti-LM
| <html> | |
| <head> | |
| <title>Multilingual LM Demo</title> | |
| <style> | |
| body { font-family: Arial, sans-serif; max-width: 800px; margin: 0 auto; padding: 20px; } | |
| .container { display: flex; flex-direction: column; gap: 20px; } | |
| textarea { width: 100%; height: 100px; padding: 10px; font-size: 16px; } | |
| button { padding: 10px 20px; background: #4CAF50; color: white; border: none; cursor: pointer; } | |
| button:hover { background: #45a049; } | |
| .output { border: 1px solid #ccc; padding: 15px; min-height: 100px; background: #f9f9f9; } | |
| .language-tag { display: inline-block; margin: 5px; padding: 5px 10px; background: #e0e0e0; cursor: pointer; } | |
| </style> | |
| </head> | |
| <body> | |
| <div class="container"> | |
| <h1>Multilingual Language Model Demo</h1> | |
| <div> | |
| <strong>Language:</strong> | |
| <span class="language-tag" onclick="setLanguage('[EN] ')">English</span> | |
| <span class="language-tag" onclick="setLanguage('[HI] ')">Hindi</span> | |
| <span class="language-tag" onclick="setLanguage('[PA] ')">Punjabi</span> | |
| </div> | |
| <textarea id="prompt" placeholder="Enter your prompt here..."></textarea> | |
| <div> | |
| <label>Temperature: <input type="range" id="temp" min="0.1" max="2.0" step="0.1" value="0.7"></label> | |
| <label>Max Length: <input type="number" id="maxlen" min="20" max="500" value="100"></label> | |
| </div> | |
| <button onclick="generate()">Generate</button> | |
| <div class="output" id="output">Response will appear here...</div> | |
| </div> | |
| <script> | |
| function setLanguage(tag) { | |
| document.getElementById('prompt').value = tag; | |
| } | |
| async function generate() { | |
| const prompt = document.getElementById('prompt').value; | |
| const temp = document.getElementById('temp').value; | |
| const maxlen = document.getElementById('maxlen').value; | |
| document.getElementById('output').innerHTML = 'Generating...'; | |
| try { | |
| const response = await fetch('/generate', { | |
| method: 'POST', | |
| headers: {'Content-Type': 'application/json'}, | |
| body: JSON.stringify({prompt, temp, maxlen}) | |
| }); | |
| const data = await response.json(); | |
| document.getElementById('output').innerHTML = data.response; | |
| } catch (error) { | |
| document.getElementById('output').innerHTML = 'Error: ' + error; | |
| } | |
| } | |
| </script> | |
| </body> | |
| </html> | |