lexi-resume-v6/README.md

---
license: other
license_name: "inherits-base-model-and-dataset-terms"
base_model: "Qwen/Qwen2.5-0.5B-Instruct"
library_name: transformers
pipeline_tag: "text-generation"
tags:
- "ai-model-builder"
- "fine-tuned"
- reallexi
- slm
- "text-generation"
---

# lexi-resume-v6

**lexi-resume-v6** by Reallexi LLC AI Model Builder — [llm.reallexi.io](https://llm.reallexi.io)

Copyright (c) 2026 Reallexi LLC. All rights reserved.

A standalone model of 495M parameters, derived from [`Qwen/Qwen2.5-0.5B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct).

The adapter has been merged into the base weights, so no PEFT adapter is needed at runtime.


## Size and requirements

| | |
|---|---|
| Parameters | 495,114,112 (495M) |
| Weights on disk | 942 MB |
| Trained context length | 8,192 tokens |
| Base model | `Qwen/Qwen2.5-0.5B-Instruct` |


Approximate memory to hold the weights. Add context and runtime overhead on top.

| Precision | Weights |
|---|---|
| FP16 / BF16 | 944 MB |
| 8-bit (Q8_0) | 472 MB |
| 4-bit (Q4_K_M) | 260 MB |


## Training

| | |
|---|---|
| Strategy | slm |
| Adapter | Auto LoRA |
| LoRA rank / alpha | 8 / 16 |
| Dataset | `AzharAli05/Resume-Screening-Dataset` |
| Samples learned | 10,000 (through phase 3 of 3) |
| Training steps | 2,250 |
| Epochs | 3 |


## Before / after samples

The same prompts, drawn from the training data, run through the base model before training and the finished model after. This shows what the run changed on representative prompts -- it is not a benchmark. Full outputs are in `SAMPLES.md` and `samples.json` alongside this file.

**Prompt:** Role: AR/VR Developer; Resume: Here's a professional resume for Mary Johnson, tailored to the AR/VR Developer role: Mary Johnson Contact

- Before: Information:
* Address: 123 Main St, Anytown, USA 12345
* Phone: (555) 555-5555
* Email: [mary.johnson@email.com](mailto:mary.johnson@email.com)
Professional Summary:
Highly motivated and experienced AR/VR Developer with expertise in Unity, C#,
- After: Information:
* Address: 123 Main St, Anytown, USA 12345
* Phone: (555) 555-5555
* Email: [mary.johnson@email.com](mailto:mary.johnson@email.com)
* LinkedIn: linkedin.com/in/maryjohnsondeveloper

Summary:
Highly motivated and

**Prompt:** Role: product manager; Resume: here's a sample resume for brent brown applying for the role of product manager: brent brown

- Before: Product Manager
Contact Information:

* Email: [brent.brown@email.com](mailto:brent.brown@email.com)
* Phone: (123) 456-7890
* LinkedIn: linkedin.com/in/brentbrown

Summary:
Highly motivated and detail-oriented Product Manager with 5+ years of experience in driving successful product launches, delivering high
- After: product manager

contact information:

* email: [brent.brown@email.com](mailto:brent.brown@email.com)
* phone: 555-555-5555
* linkedin: linkedin.com/in/brentbrown

summary:
highly motivated and detail-oriented product manager with 3+ years of experience in creating and executing successful product strategies.

**Prompt:** Role: data engineer; Resume: **gina mehta** **data engineer candidate** gina mehta is a highly skilled and experienced data engineer with

- Before: over 5 years of experience in designing, developing, and deploying scalable data solutions. She has a strong background in cloud computing, database design, and data visualization.

**Key skills:**

* Cloud platforms (AWS, Azure, Google Cloud)
* Database management (MySQL, PostgreSQL, MongoDB)
* Data modeling and query…
- After: a strong background in designing, developing, and deploying scalable data solutions. she has a proven track record of delivering high-quality data products that meet the needs of clients across various industries.

**key skills and achievements:**

* **data engineering:** demonstrated expertise in designing, developing…


## Training curve

![Training loss](training_curve.png)


## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("lexi-resume-v6")
tokenizer = AutoTokenizer.from_pretrained("lexi-resume-v6")
```


## License and attribution

The effective terms are inherited from the base model and the training data, which are not necessarily the same as this project's own license. Review both before redistributing.

- Base model: [`Qwen/Qwen2.5-0.5B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct)

- Training data: `AzharAli05/Resume-Screening-Dataset`


Copyright (c) 2026 Reallexi LLC. All rights reserved.


Produced by Reallexi LLC AI Model Builder from training job #1609.
Core: https://llm.reallexi.io

## Who, where, and what platform trained this?

Produced by Reallexi LLC on [Reallexi AI Model Builder](https://llm.reallexi.io), a local-first training platform (https://llm.reallexi.io). Hugging Face repository: [reallexi/lexi-resume-v6](https://huggingface.co/reallexi/lexi-resume-v6).
Copyright (c) 2026 Reallexi LLC. All rights reserved.