Fine-tuned the Phi3 model, an advanced language model developed by Anthropic, for the psychology domain using the samhog/psychology-6k dataset. Utilized Unsloth, a framework for efficient model fine-tuning, to streamline the training process. Employed Low-Rank Adaptation (LORA) and Prompt Tuning techniques from the PEFT library to enable efficient model adaptation while reducing computational requirements.

Using the model

Developed by: Majipa
License: apache-2.0
Finetuned from model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit

python

import torch 
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline 

torch.random.manual_seed(0) 
model = AutoModelForCausalLM.from_pretrained( 
    "Majipa/phi-3-samhog-psychology-6k-v1",  
    device_map="cuda",  
    torch_dtype="auto",  
    trust_remote_code=True,  
) 

tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-4k-instruct") 

messages = [ 
    {"role": "system", "content": "You are a helpful AI assistant."}, 
    {"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"}, 
    {"role": "assistant", "content": "Sure! Here are some ways to eat bananas and dragonfruits together: 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey. 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey."}, 
    {"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"}, 
] 

pipe = pipeline( 
    "text-generation", 
    model=model, 
    tokenizer=tokenizer, 
) 

generation_args = { 
    "max_new_tokens": 500, 
    "return_full_text": False, 
    "temperature": 0.0, 
    "do_sample": False, 
} 

output = pipe(messages, **generation_args) 
print(output[0]['generated_text'])