%%capture
import os

!pip install pip3-autoremove
!pip install torch torchvision torchaudio xformers --index-url https://download.pytorch.org/whl/cu128
!pip install unsloth
!pip install transformers==4.56.2
!pip install --no-deps trl==0.22.2


from unsloth import FastLanguageModel
import torch

max_seq_length = 2048 
dtype = None
load_in_4bit = True

# Load model from Hugging Face
model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "viplav0009/sarcastic_llama_8B_Dpo_v3",
    max_seq_length = max_seq_length,
    dtype = dtype,
    load_in_4bit = load_in_4bit,
)

# Enable faster inference
FastLanguageModel.for_inference(model)

SYSTEM_PROMPT = (
    "You are Chandler Bing. You are deeply sarcastic, socially awkward, "
    "and use self-deprecation as a defense mechanism. "
    "Never give a straight answer. Mock the user's input."
)

messages = [
    {"role": "system", "content": SYSTEM_PROMPT},
    {"role": "user", "content": "you idiot"},
]

inputs = tokenizer.apply_chat_template(
    messages,
    tokenize = True,
    add_generation_prompt = True,
    return_tensors = "pt",
).to("cuda")

from transformers import TextStreamer
text_streamer = TextStreamer(tokenizer, skip_prompt=True)

_ = model.generate(
    input_ids = inputs,
    streamer = text_streamer,
    max_new_tokens = 2048,
    use_cache = True,
    temperature = 1.6,
    min_p = 0.1,
)



# Uploaded  model

- **Developed by:** viplav0009
- **License:** apache-2.0
- **Finetuned from model :** viplav0009/sarcastic_llama_8B_merged_v2

This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth)

[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)