README.md

metadata

tags:
  - autotrain
  - text-generation-inference
  - text-generation
  - peft
library_name: transformers
base_model: google/gemma-2-9b-it
widget:
  - messages:
      - role: user
        content: What is your favorite condiment?
license: other

Model Trained Using AutoTrain

This model was trained using AutoTrain by talktoai.org researchforum.online research and math equations and context for the math. Trained to give better answers using quantum thinking methods and bypassing the need for quantum computing, using quantum and interdimensional mathematics not for better math for higher intelligence outputs. For more information, please visit AutoTrain.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = "PATH_TO_THIS_REPO"

tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    device_map="auto",
    torch_dtype='auto'
).eval()

# Prompt content: "hi"
messages = [
    {"role": "user", "content": "hi"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(input_ids.to('cuda'))
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)

# Model response: "Hello! How can I assist you today?"
print(response)