Text Generation
Transformers
Safetensors
English
Pashto
bloom
pashto
lightweight
language-model
text-generation-inference
Instructions to use tasal9/pashto-base-bloom with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tasal9/pashto-base-bloom with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="tasal9/pashto-base-bloom")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("tasal9/pashto-base-bloom") model = AutoModelForCausalLM.from_pretrained("tasal9/pashto-base-bloom") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use tasal9/pashto-base-bloom with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "tasal9/pashto-base-bloom" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "tasal9/pashto-base-bloom", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/tasal9/pashto-base-bloom
- SGLang
How to use tasal9/pashto-base-bloom 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 "tasal9/pashto-base-bloom" \ --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": "tasal9/pashto-base-bloom", "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 "tasal9/pashto-base-bloom" \ --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": "tasal9/pashto-base-bloom", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use tasal9/pashto-base-bloom with Docker Model Runner:
docker model run hf.co/tasal9/pashto-base-bloom
pashto-base-bloom
BLOOM-based model fine-tuned for Pashto language tasks
π Model Overview
This model is part of the ZamAI Pro Models Strategy - a comprehensive AI platform designed for multilingual applications with specialized focus on Pashto language support.
Key Features
- π§ Advanced AI: Based on bigscience/bloomz-560m architecture
- π Multilingual: Optimized for Pashto and English
- β‘ High Performance: Optimized for production deployment
- π Secure: Enterprise-grade security and privacy
π Usage
Basic Usage with Transformers
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("tasal9/pashto-base-bloom")
model = AutoModel.from_pretrained("tasal9/pashto-base-bloom")
# Example usage
text = "Your input text here"
inputs = tokenizer(text, return_tensors="pt")
outputs = model(**inputs)
Usage with Hugging Face Inference API
from huggingface_hub import InferenceClient
client = InferenceClient(token="your_hf_token")
response = client.text_generation(
model="tasal9/pashto-base-bloom",
prompt="Your prompt here",
max_new_tokens=200
)
π§ Technical Details
- Model Type: text-generation
- Base Model: bigscience/bloomz-560m
- Languages: Pashto (ps), English (en)
- License: MIT
- Training: Fine-tuned on Pashto educational and cultural content
π Applications
This model powers:
- ZamAI Educational Platform: Pashto language tutoring
- Business Automation: Document processing and analysis
- Voice Assistants: Natural language understanding
- Cultural Preservation: Supporting Pashto language technology
π Support
For support and integration assistance:
- π§ Email: support@zamai.dev
- π Website: zamai.dev
- π¬ Community: ZamAI Community
π License
Licensed under the MIT License.
Part of the ZamAI Pro Models Strategy - Transforming AI for Multilingual Applications π
Updated: 2025-07-05 21:29:16 UTC
- Downloads last month
- 43
Model tree for tasal9/pashto-base-bloom
Base model
bigscience/bloomz-560m