import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers import pipeline

def formatted_prompt(question)-> str:
    return f"<|im_start|>user\n{question}<|im_end|>\n<|im_start|>assistant:"

hub_model_name = "lumatic-ai/BongLlama-1.1B-Chat-alpha-v0"

tokenizer = AutoTokenizer.from_pretrained(hub_model_name)
pipe = pipeline(
    "text-generation",
    model=hub_model_name,
    torch_dtype=torch.float16,
    device_map="auto",
)

from time import perf_counter
start_time = perf_counter()

prompt = formatted_prompt('হ্যালো')
sequences = pipe(
    prompt,
    do_sample=True,
    temperature=0.1,
    top_p=0.9,
    num_return_sequences=1,
    eos_token_id=tokenizer.eos_token_id,
    max_new_tokens=256
)
for seq in sequences:
    print(f"Result: {seq['generated_text']}")

output_time = perf_counter() - start_time
print(f"Time taken for inference: {round(output_time,2)} seconds")

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer

def formatted_prompt(question)-> str:
    return f"<|im_start|>user\n{question}<|im_end|>\n<|im_start|>assistant:"

hub_model_name = "lumatic-ai/BongLlama-1.1B-Chat-alpha-v0"

tokenizer = AutoTokenizer.from_pretrained(hub_model_name)
model = AutoModelForCausalLM.from_pretrained(hub_model_name)

prompt = formatted_prompt('prompt here')
inputs = tokenizer([prompt], return_tensors="pt")
streamer = TextStreamer(tokenizer)
_ = model.generate(**inputs, eos_token_id=[tokenizer.eos_token_id],streamer=streamer, max_new_tokens=256)

import torch
from transformers import GenerationConfig
from time import perf_counter

def formatted_prompt(question)-> str:
    return f"<|im_start|>user\n{question}<|im_end|>\n<|im_start|>assistant:"

hub_model_name = "lumatic-ai/BongLlama-1.1B-Chat-alpha-v0"

tokenizer = AutoTokenizer.from_pretrained(hub_model_name)
model = AutoModelForCausalLM.from_pretrained(hub_model_name)

prompt = formatted_prompt('হ্যালো')

# Check for GPU availability
if torch.cuda.is_available():
    device = "cuda"
else:
    device = "cpu"

# Move model and inputs to the GPU (if available)
model.to(device)
inputs = tokenizer(prompt, return_tensors="pt").to(device)

generation_config = GenerationConfig(
    penalty_alpha=0.6,
    do_sample=True,
    top_k=5,
    temperature=0.5,
    repetition_penalty=1.2,
    max_new_tokens=256,
    pad_token_id=tokenizer.eos_token_id
)

start_time = perf_counter()
outputs = model.generate(**inputs, generation_config=generation_config)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
output_time = perf_counter() - start_time
print(f"Time taken for inference: {round(output_time, 2)} seconds")