inetnuc/Llama-3.1-8B-bnb-4bit-chat-nuclear-lora-f16

LLAMA-3.1 8B Chat Nuclear Model

• Developed by: inetnuc
• License: apache-2.0
• Finetuned from model: unsloth/Meta-Llama-3.1-8B-bnb-4bit

This LLAMA-3.1 model was finetuned to enhance capabilities in text generation for nuclear-related topics. The training was accelerated using Unsloth and Huggingface's TRL library, achieving a 2x faster performance.

Finetuning Process

The model was finetuned using the Unsloth library, leveraging its efficient training capabilities. The process included the following steps:

1. Data Preparation: Loaded and preprocessed nuclear-related data.
2. Model Loading: Utilized unsloth/llama-3-8b-bnb-4bit as the base model.
3. LoRA Patching: Applied LoRA (Low-Rank Adaptation) for efficient training.
4. Training: Finetuned the model using Hugging Face's TRL library with optimized hyperparameters.

Model Details

• Base Model: unsloth/llama-3.1-8b-bnb-4bit
• Language: English (en)
• License: Apache-2.0

Author

MUSTAFA UMUT OZBEK

https://www.linkedin.com/in/mustafaumutozbek/ https://x.com/m_umut_ozbek

Usage

Loading the Model

You can load the model and tokenizer using the following code snippet:

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("inetnuc/Llama-3.1-8B-bnb-4bit-chat-nuclear-lora-f16")
model = AutoModelForCausalLM.from_pretrained("inetnuc/Llama-3.1-8B-bnb-4bit-chat-nuclear-lora-f16")

# Example of generating text
inputs = tokenizer("what is the iaea approach for cyber security?", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))