llama-3.3-70b-decipher-merged

Llama 3.3 70B DECipher Fine-tuned Model

This model is a fine-tuned version of meta-llama/Llama-3.3-70B-Instruct for the DECipher application.

Model Details

• Base Model: meta-llama/Llama-3.3-70B-Instruct
• Fine-tuning Method: LoRA (Low-Rank Adaptation)
• Domain: Development and International Cooperation
• Merge Date: 2025-08-11

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "HariomSahu/llama-3.3-70b-decipher-merged",
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

tokenizer = AutoTokenizer.from_pretrained("HariomSahu/llama-3.3-70b-decipher-merged")

# Example usage
prompt = "What is USAID and what are its main objectives?"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=200)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Training Details

This model was fine-tuned on domain-specific data related to development cooperation, project management, and international development best practices.

Intended Use

This model is designed for use in the DECipher application to provide expert guidance on development projects, methodology, technical implementation, and communication strategies.