• indo-instruct-llama2-32kmodel card
• Model Details
• Developed by: monuminu
• Backbone Model: LLaMA-2
• Language(s): English
• Library: HuggingFace Transformers
• License: Fine-tuned checkpoints is licensed under the Non-Commercial Creative Commons license (CC BY-NC-4.0)
• Where to send comments: Instructions on how to provide feedback or comments on a model can be found by opening an issue in the Hugging Face community's model repository
• Contact: For questions and comments about the model
• Dataset Details
• Used Datasets
• alpaca dataset

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer

tokenizer = AutoTokenizer.from_pretrained("monuminu/indo-instruct-llama2-32k")
model = AutoModelForCausalLM.from_pretrained(
    "monuminu/indo-instruct-llama2-32k",
    device_map="auto",
    torch_dtype=torch.float16,
    load_in_8bit=True,
    rope_scaling={"type": "dynamic", "factor": 2} # allows handling of longer inputs
)

prompt = "### User:\nThomas is healthy, but he has to go to the hospital. What could be the reasons?\n\n### Assistant:\n"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
del inputs["token_type_ids"]
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)

output = model.generate(**inputs, streamer=streamer, use_cache=True, max_new_tokens=float('inf'))
output_text = tokenizer.decode(output[0], skip_special_tokens=True)