bhagavad_gita_model

Model Card for bhagavad_gita_model

This model is a fine-tuned version of unsloth/gemma-3-1b-it-unsloth-bnb-4bit. It has been trained using TRL.

Quick start

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="sagar2000/bhagavad_gita_model", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model_name = "unsloth/gemma-3-1b-it-unsloth-bnb-4bit" # e.g., "mistralai/Mistral-7B-v0.1"
adapter_repo_id = "sagar2000/bhagavad_gita_model"

model = AutoModelForCausalLM.from_pretrained(base_model_name, device_map="auto")
model = PeftModel.from_pretrained(model, adapter_repo_id)
tokenizer = AutoTokenizer.from_pretrained(base_model_name)

messages = [
    {
    "role": "user",
    "content": "How do I control my anger?"
    }
    ]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt = True, 
    tokenize = True,
    return_tensors = "pt",
    return_dict = True,
)

from transformers import TextStreamer
_ = model.generate(
    **inputs.to("cuda"),
    max_new_tokens = 1024, # Increase for longer outputs!
    temperature = 1.0, top_p = 0.95, top_k = 64,
    streamer = TextStreamer(tokenizer, skip_prompt = True),
)

Training procedure

This model was trained with SFT.

Framework versions

• TRL: 0.23.0
• Transformers: 4.57.1
• Pytorch: 2.9.0
• Datasets: 4.3.0
• Tokenizers: 0.22.1

Citations

Cite TRL as:

@misc{vonwerra2022trl,
	title        = {{TRL: Transformer Reinforcement Learning}},
	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
	year         = 2020,
	journal      = {GitHub repository},
	publisher    = {GitHub},
	howpublished = {\url{https://github.com/huggingface/trl}}
}