from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "azherali/Riazi-8B-CPT"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "پاکستان کی ثقافت کے بارے میں مختصر وضاحت کریں۔"
messages = [
    {"role": "user", "content": prompt}
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=2048
)

output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()

try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0


content = tokenizer.decode(
    output_ids[index:],
    skip_special_tokens=True
).strip("\n")

print("content:", content)

Uploaded model

Developed by: azherali
License: apache-2.0