CoolFace
Modelpublic

keerthanshetty/resume-skill-extractor-merged

sourceHugging Facellama3updated 5mo agoView on Hugging Face
0likes8downloads
Model Card

๐Ÿš€ Resume Skill Extractor (Llama 3 8B)

Model Overview

This is a fully merged, standalone 8-Billion parameter language model specifically fine-tuned to act as an expert technical recruiter. It takes raw, unstructured job descriptions and instantly extracts a concise summary along with a cleanly formatted, bulleted list of mandatory and bonus technical skills.

This model was created by fine-tuning Meta-Llama-3-8B-Instruct using QLoRA, and the resulting adapters have been permanently merged into the base weights for simplified deployment and serverless inference.

  • โ€”Base Model: Meta-Llama-3-8B-Instruct
  • โ€”Original LoRA Adapters: k10shetty/resume-skill-extractor-lora
  • โ€”Task: Information Extraction / Text Generation
  • โ€”Architecture: LlamaForCausalLM (16-bit bfloat16)

Prompt Format

This model retains the standard Llama 3 Instruct prompt format. To get the best results, you must use this exact structure:

text
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
You are an expert technical recruiter. Analyze job descriptions and extract key information.<|eot_id|>
<|start_header_id|>user<|end_header_id|>
Analyze this job description and provide a summary, the required skills, and the bonus/nice-to-have skills:

[INSERT JOB DESCRIPTION HERE]<|eot_id|>
<|start_header_id|>assistant<|end_header_id|>