README.md

metadata

tags:
  - autotrain
  - text-generation-inference
  - text-generation
  - peft
library_name: transformers
base_model: meta-llama/Meta-Llama-3.1-8B
widget:
  - messages:
      - role: user
        content: What is your favorite condiment?
license: other

Model Trained Using AutoTrain - Will update this once i get a gguf format 8 hours training on a large gpu server.

This model was trained using AutoTrain reflection data sets re-written with talktoai data sets using quantum interdimensional math and a new math system I made myself, also i took DNA math patterns and put them into the training too! For more information, please visit AutoTrain.

Usage - Open Source ideas math etc are from talktoai.org researchforum.online official legal license llama 3.1 meta.

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)