Text Generation
Transformers
PyTorch
Sanskrit
generative
language-model
sanskrit
devanagari
flashattention
micro-llm
Instructions to use ss-76/microgpt-deva with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ss-76/microgpt-deva with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ss-76/microgpt-deva")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ss-76/microgpt-deva", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ss-76/microgpt-deva with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ss-76/microgpt-deva" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ss-76/microgpt-deva", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ss-76/microgpt-deva
- SGLang
How to use ss-76/microgpt-deva 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 "ss-76/microgpt-deva" \ --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": "ss-76/microgpt-deva", "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 "ss-76/microgpt-deva" \ --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": "ss-76/microgpt-deva", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ss-76/microgpt-deva with Docker Model Runner:
docker model run hf.co/ss-76/microgpt-deva
Update README.md
Browse files
README.md
CHANGED
|
@@ -73,7 +73,7 @@ model.load_state_dict(torch.load("pytorch_model.bin"))
|
|
| 73 |
model.eval()
|
| 74 |
|
| 75 |
# Generate text
|
| 76 |
-
prompt = "म
|
| 77 |
input_ids = torch.tensor([sp.encode(prompt, out_type=int)], dtype=torch.long)
|
| 78 |
with torch.no_grad():
|
| 79 |
output = model.generate(input_ids, max_new_tokens=30)
|
|
|
|
| 73 |
model.eval()
|
| 74 |
|
| 75 |
# Generate text
|
| 76 |
+
prompt = "कस्मिंश्चिन् नगराभ्याशे "
|
| 77 |
input_ids = torch.tensor([sp.encode(prompt, out_type=int)], dtype=torch.long)
|
| 78 |
with torch.no_grad():
|
| 79 |
output = model.generate(input_ids, max_new_tokens=30)
|