Instructions to use Ranjit89/assamese-tokenizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ranjit89/assamese-tokenizer with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Ranjit89/assamese-tokenizer")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Ranjit89/assamese-tokenizer", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Ranjit89/assamese-tokenizer with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Ranjit89/assamese-tokenizer" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ranjit89/assamese-tokenizer", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Ranjit89/assamese-tokenizer
- SGLang
How to use Ranjit89/assamese-tokenizer 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 "Ranjit89/assamese-tokenizer" \ --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": "Ranjit89/assamese-tokenizer", "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 "Ranjit89/assamese-tokenizer" \ --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": "Ranjit89/assamese-tokenizer", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Ranjit89/assamese-tokenizer with Docker Model Runner:
docker model run hf.co/Ranjit89/assamese-tokenizer
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,7 +9,10 @@ tags:
|
|
| 9 |
- bpe
|
| 10 |
- llm
|
| 11 |
- nlp
|
|
|
|
| 12 |
---
|
|
|
|
|
|
|
| 13 |
# Assamese Tokenizer
|
| 14 |
|
| 15 |
A high-performance custom BPE tokenizer built specifically for Assamese Large Language Models (LLMs).
|
|
|
|
| 9 |
- bpe
|
| 10 |
- llm
|
| 11 |
- nlp
|
| 12 |
+
pipeline_tag: text-generation
|
| 13 |
---
|
| 14 |
+
|
| 15 |
+
# Assamese Tokenizer
|
| 16 |
# Assamese Tokenizer
|
| 17 |
|
| 18 |
A high-performance custom BPE tokenizer built specifically for Assamese Large Language Models (LLMs).
|