You can deploy this model and start earning money today!

udayvadde/
f1-career-coach-lora

safetensors

Views

No views yet

F1 Career Coach - LoRA Fine-tuned LLaMA 3.2 1B

Model Description

A LoRA fine-tuned version of LLaMA 3.2 1B Instruct, trained to act as a career coach specifically for F1 international students seeking jobs in the US.

Problem Statement

F1 students face unique challenges — OPT timelines, H1B sponsorship, resume tailoring for US companies. Generic models give generic advice. This model gives specific, actionable career guidance.

Training Details

Base model: meta-llama/Llama-3.2-1B-Instruct
Fine-tuning method: QLoRA (4-bit quantization + LoRA)
LoRA rank: 16, Alpha: 32
Target modules: q_proj, v_proj
Training examples: 205
Epochs: 3
Training loss: 3.4 → 2.29

Topics Covered

Resume tailoring for US job descriptions
H1B sponsoring companies for F1 students
Interview preparation — technical and behavioral
Job search strategies for international students
Salary negotiation on OPT

How to Use

python

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-1B-Instruct")
model = PeftModel.from_pretrained(base_model, "your-username/f1-career-coach-lora")
tokenizer = AutoTokenizer.from_pretrained("your-username/f1-career-coach-lora")

Limitations

Dataset is synthetic — verify company sponsorship data on myvisajobs.com
205 training examples — may hallucinate on specific program names
H1B rules change frequently — always verify with your DSO

udayvadde/f1-career-coach-lora