metadata
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
- trl
- sft
license: apache-2.0
language:
- id
base_model:
- kalisai/Nusantara-1.8b-Indo-Chat
Uploaded model
- Developed by: farihdzaky
- License: apache-2.0
- Finetuned from model : kalisai/Nusantara-1.8b-Indo-Chat
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained(
"farihdzaky/indonesia_LLM",
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("farihdzaky/indonesia_LLM")
prompt = "Berikan saya resep memasak nasi goreng yang lezat."
messages = [
{"role": "system", "content": "Kamu adalah Nusantara, asisten AI yang pintar."},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)
generated_ids = model.generate(
model_inputs.input_ids,
max_new_tokens=512
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]