Update README.md
Browse files
README.md
CHANGED
|
@@ -9,7 +9,7 @@ base_model:
|
|
| 9 |
|
| 10 |
# Introduction
|
| 11 |
|
| 12 |
-
According to the August 2025 jobs report, overall unemployment has risen, with the unemployment rate for workers aged 16-24 rising to 10.5% [August 2025 jobs report](https://www.bls.gov/). The primary demographic
|
| 13 |
of this age range is recent college graduates, many of whom carry student loan debt and are unable to find stable, long-term employment. While this could be
|
| 14 |
attributed to any of the various economic challenges facing the US today, there is speculation that it may
|
| 15 |
be due to insufficient skills regarding job-hunting and interviews. There are many resources that seek to fill this gap, including interview-prep LLMs such as [Interview Copilot](https://interviewcopilot.io/). However, there is not an LLM that
|
|
@@ -116,7 +116,7 @@ The intended use case for this model is interview prep for any job that has an a
|
|
| 116 |
interview practice by answering realistic and complex questions. The model is able to look through any job description and develop diverse simulation interview questions based
|
| 117 |
on said description. The model will also use the user's input profile with information such as education, experience, and skills to formulate an optimal answer to the interview question.
|
| 118 |
This answer will allow the user to see how their profile can be optimized to answer questions and give them the best chance at moving to the next round of the
|
| 119 |
-
job hiring process. Specifically, this model is intended for
|
| 120 |
answers to complex interview questions. For example, if I was applying for a data scientist position, but had little experience with data science, this model would find a way to
|
| 121 |
use my other education and experience to supplement my answer to data science-specific interview questions.
|
| 122 |
|
|
@@ -171,9 +171,9 @@ Original Dataset: [LinkedIn Job Postings 2023](https://www.kaggle.com/datasets/a
|
|
| 171 |
|
| 172 |
Comparison Model 1: [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
|
| 173 |
|
| 174 |
-
|
| 175 |
|
| 176 |
-
Benchmark 1: [HumanEval](https://github.com/openai/human-eval) and [HumanEval Article](https://arxiv.org/abs/
|
| 177 |
|
| 178 |
Benchmark 2: [SQuADv2](https://rajpurkar.github.io/SQuAD-explorer/) and [SQuAD Article](https://arxiv.org/abs/1806.03822)
|
| 179 |
|
|
|
|
| 9 |
|
| 10 |
# Introduction
|
| 11 |
|
| 12 |
+
According to the August 2025 jobs report, overall unemployment has risen, with the unemployment rate for workers aged 16-24 rising to 10.5% according to [August 2025 jobs report](https://www.bls.gov/). The primary demographic
|
| 13 |
of this age range is recent college graduates, many of whom carry student loan debt and are unable to find stable, long-term employment. While this could be
|
| 14 |
attributed to any of the various economic challenges facing the US today, there is speculation that it may
|
| 15 |
be due to insufficient skills regarding job-hunting and interviews. There are many resources that seek to fill this gap, including interview-prep LLMs such as [Interview Copilot](https://interviewcopilot.io/). However, there is not an LLM that
|
|
|
|
| 116 |
interview practice by answering realistic and complex questions. The model is able to look through any job description and develop diverse simulation interview questions based
|
| 117 |
on said description. The model will also use the user's input profile with information such as education, experience, and skills to formulate an optimal answer to the interview question.
|
| 118 |
This answer will allow the user to see how their profile can be optimized to answer questions and give them the best chance at moving to the next round of the
|
| 119 |
+
job hiring process. Specifically, this model is intended for users who have little-to-no interview experience and need more intense preparation, or users that want to enhance their
|
| 120 |
answers to complex interview questions. For example, if I was applying for a data scientist position, but had little experience with data science, this model would find a way to
|
| 121 |
use my other education and experience to supplement my answer to data science-specific interview questions.
|
| 122 |
|
|
|
|
| 171 |
|
| 172 |
Comparison Model 1: [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
|
| 173 |
|
| 174 |
+
Comparison Model 2: [deepseek-ai/DeepSeek-R1-0528-Qwen3-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B)
|
| 175 |
|
| 176 |
+
Benchmark 1: [HumanEval](https://github.com/openai/human-eval) and [HumanEval Article](https://arxiv.org/abs/2107.03374)
|
| 177 |
|
| 178 |
Benchmark 2: [SQuADv2](https://rajpurkar.github.io/SQuAD-explorer/) and [SQuAD Article](https://arxiv.org/abs/1806.03822)
|
| 179 |
|