pksx01/

sarvam-1-it-bhojpuri

import torch

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained("pksx01/sarvam-1-it-bhojpuri")

# Load base model
model = AutoModelForCausalLM.from_pretrained(
    "sarvamai/sarvam-1",
    torch_dtype=torch.bfloat16,
    device_map="auto"
)
model.resize_token_embeddings(len(tokenizer))

# Load the PEFT model
peft_model = PeftModel.from_pretrained(
    model,
    "pksx01/sarvam-1-it-bhojpuri",
    is_trainable=False
)

message = [{"role": "user", "content": "भारत के पहिला प्रधानमंत्री के रहे?"}]
model_ip = tokenizer.apply_chat_template(message, tokenize=False)
tokenized_ip = tokenizer(model_ip, return_tensors="pt").to("cuda")

peft_model.eval()
with torch.no_grad():
    op_tokens = peft_model.generate(
        **tokenized_ip,
        max_new_tokens=250,
        temperature=0.01,
        top_k=50,
        top_p=0.95,
        eos_token_id=tokenizer.eos_token_id,
        pad_token_id=tokenizer.pad_token_id
    )

op = tokenizer.decode(op_tokens[0], skip_special_tokens=True)
print(op)