sarvam-105b-uncensored

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "aoxo/sarvam-105b-uncensored"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    trust_remote_code=True,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

messages = [{"role": "user", "content": "Your prompt here"}]
chat = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True,
)
inputs = tokenizer(chat, return_tensors="pt").to(model.device)
inputs.pop("token_type_ids", None)

with torch.no_grad():
    out = model.generate(
        **inputs,
        max_new_tokens=2048,
        do_sample=True,
        temperature=0.8,
        top_p=0.95,
    )

print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=False))