Downloads · 30 days
8
5% of all-time downloads
llama-wikindo-lora
lumicero/llama-wikindo-lora
llama-wikindo-lora is a text generation model from lumicero. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
- Developer: lumicero, elzaff, Ilnaa, rvouyaa - Finetuned from model: Llama-3.2-3B-unsloth-bnb-4bit - License: Apache license 2.0
All-time downloads
159
Public
Repo size
115 MB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors97.3 MB · 85%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Oct 10, 2025
- Updated
- Nov 15, 2025
- SHA
- 951133b9
Base models
Model card
From the Hugging Face model README
Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->Information
- Developer: lumicero, elzaff, Ilnaa, rvouyaa
- Finetuned from model: Llama-3.2-3B-unsloth-bnb-4bit
- License:
Apache license 2.0
This model was trained 2x faster with Unsloth.
Documentation
Evaluation Score
| Metrics | Random Sampling (This repo) | Uniform Sampling | Clusterclip Sampling |
|---|---|---|---|
| BLEU (Mean ± Std) | 20.5852 ± 9.0977 | 20.5419 ± 7.1707 | 22.2123 ± 6.2882 |
| ROUGE-1 (Mean ± Std) | 0.2558 ± 0.0010 | 0.2493 ± 0.0027 | 0.2536 ± 0.0003 |
| ROUGE-2 (Mean ± Std) | 0.1388 ± 0.0012 | 0.1325 ± 0.0036 | 0.1366 ± 0.0034 |
| ROUGE-L (Mean ± Std) | 0.2256 ± 0.0013 | 0.2197 ± 0.0028 | 0.2223 ± 0.0011 |
| F1 Bert-Score (Mean ± Std) | 0.8713 ± 0.0003 | 0.8694 ± 0.0009 | 0.8703 ± 0.0007 |
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Languages
- id
- Created
- Oct 10, 2025
- Updated
- Nov 15, 2025