Downloads · 30 days
3
9% of all-time downloads
v8_curated_1k-merged
kmd2525/v8_curated_1k-merged
v8_curated_1k-merged is a machine learning model from kmd2525. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This model is trained using the Person W Style approach - high-quality data under 1000 samples.
All-time downloads
32
Public
Parameters
4B
8.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Feb 25, 2026
- Updated
- Feb 25, 2026
- SHA
- b3bd43f6
Base models
Model card
From the Hugging Face model README
v8_curated_1k-merged
Model Description
This model is trained using the Person W Style approach - high-quality data under 1000 samples.
Training Strategy (Person W Style)
Based on Person W's insight that achieved 0.8+ with:
- High-quality data under 1000 samples
- epoch=2
- Fine-tuning hyperparameters rather than large changes
Dataset: v8_curated_1k
Quality Criteria:
- 100% parse success rate
- No code fence contamination
- No natural language prefix/suffix
- Appropriate complexity
Format Distribution:
- Balanced across all 5 formats (JSON/CSV/YAML/XML/TOML)
Training Parameters
- MAX_SEQ_LEN: 1024
- EPOCHS: 2
- Learning Rate: 5e-05
- LoRA R: 64, Alpha: 128
Comparison with Sequential Format Learning
| Approach | Data | Training | Complexity |
|---|---|---|---|
| Sequential SFT (Stage 1-4) | 2800 samples | 4 stages | High |
| Person W Style (This model) | < 1000 samples | 1 stage | Simple |
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("kmd2525/v8_curated_1k-merged")
tokenizer = AutoTokenizer.from_pretrained("kmd2525/v8_curated_1k-merged")
- Type
- qwen3
- License
- apache-2.0
- Languages
- en, ja
- Created
- Feb 25, 2026
- Updated
- Feb 25, 2026