Instructions to use thesantoshbist/fwu-llm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use thesantoshbist/fwu-llm with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="thesantoshbist/fwu-llm")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("thesantoshbist/fwu-llm") model = AutoModelForCausalLM.from_pretrained("thesantoshbist/fwu-llm", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use thesantoshbist/fwu-llm with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "thesantoshbist/fwu-llm" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "thesantoshbist/fwu-llm", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/thesantoshbist/fwu-llm
- SGLang
How to use thesantoshbist/fwu-llm 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 "thesantoshbist/fwu-llm" \ --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": "thesantoshbist/fwu-llm", "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 "thesantoshbist/fwu-llm" \ --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": "thesantoshbist/fwu-llm", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use thesantoshbist/fwu-llm with Docker Model Runner:
docker model run hf.co/thesantoshbist/fwu-llm
FWU Assistant Model
Model Description
This is a fine-tuned LLM model specialized for Far Western University (FWU) information and educational assistance. The model has been customized to provide accurate information about FWU programs, courses, admissions, faculty, and campus resources while maintaining general conversational abilities.
Training Data
This model was trained on:
- Conversations with students and faculty at FWU
- Academic information and educational resources
- General knowledge with emphasis on educational contexts
Capabilities
- Answers questions about Far Western University programs and policies
- Provides assistance with academic inquiries
- Helps with general knowledge questions
- Maintains conversational context for natural interactions
Use Cases
- Student information services
- Academic guidance
- Educational assistance
- University information desk
- Virtual campus guide
- Conversational AI
- Question answering
- Text generation
Limitations
- Limited knowledge of events after training cutoff
- May occasionally provide incorrect information
- Not a replacement for official university guidance
- Doesn't have access to student records or private information
Ethical Considerations
This model is intended for educational and informational purposes only. It should not be used for making critical academic or administrative decisions without verification from official university sources.
Additional Information
Developed by Santosh Bist at Far Western University. For issues or feedback, please contact thesantoshbist@gmail.com.
Model Description
Custom LLM 1B Parameter mainly for FWU or Far Western University.
Author
Santosh Bist
Version
1.0.0
- Downloads last month
- 10