Views
No views yet
pip install -r requirements.txt1export HF_TOKEN=your_token
2python download_model.py --model-id your-username/Nepalaya-R --local-dir ./model_weightspython quick_inference.py --prompt "Your prompt here"1export HF_TOKEN=your_token
2python mirror_to_hf.py \
3 --source source-org/source-model \
4 --dest your-username/Nepalaya-R1from transformers import AutoModelForCausalLM, AutoTokenizer
2
3model = AutoModelForCausalLM.from_pretrained(
4 "your-username/Nepalaya-R",
5 torch_dtype="auto",
6 device_map="auto"
7)
8tokenizer = AutoTokenizer.from_pretrained("your-username/Nepalaya-R")
9
10inputs = tokenizer("Hello", return_tensors="pt")
11outputs = model.generate(**inputs, max_new_tokens=100)
12print(tokenizer.decode(outputs[0]))1messages = [
2 {"role": "user", "content": "What is machine learning?"}
3]
4inputs = tokenizer.apply_chat_template(messages, tokenize=True, return_tensors="pt")
5outputs = model.generate(**inputs, max_new_tokens=256)Nepalaya-R/
├── README.md # This file
├── SETUP.md # Setup guide
├── GITHUB_DEPLOY.md # Deployment guide
├── requirements.txt # Python dependencies
├── config.json # Model configuration
├── tokenizer.json # Tokenizer
├── quick_inference.py # Quick inference script
├── download_model.py # Model downloader
├── mirror_to_hf.py # HF mirroring tool
├── inference/ # Inference code
│ ├── generate.py # Generation script
│ ├── model.py # Model implementation
│ ├── convert.py # Weight converter
│ └── config_671B_nepalaya.json # Inference config
└── assets/ # Chat templates