Downloads · 30 days
5
5% of all-time downloads
snapgate-surge-v2
kadalicious22/snapgate-surge-v2
snapgate-surge-v2 is a text generation model from kadalicious22. Use it when you need the model to write or continue text. The card lists the license as mit.
A bilingual language model (Indonesian + English) trained from scratch — no base model was used at any stage of training.
All-time downloads
92
Public
Repo size
78.2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin78.2 MB · 100%
At a glance
- Task
- Text Generation
- License
- mit
- Model type
- gpt
- Access
- Public
- Created
- Jun 29, 2026
- Updated
- Jun 29, 2026
- SHA
- b4f84761
Model card
From the Hugging Face model README
snapgate-surge-v2
A bilingual language model (Indonesian + English) trained from scratch — no base model was used at any stage of training.
Model Specifications
| Specification | Detail |
|---|---|
| Parameters | ~10 Million |
| Architecture | GPT-style Transformer (CausalLM) |
| Vocab Size | 8,000 |
| Hidden Dim | 384 |
| Layers | 8 |
| Attention Heads | 8 |
| Context Length | 512 tokens |
| Languages | Bahasa Indonesia 🇮🇩, English 🇺🇸 |
| License | MIT |
Training Progress
This model was trained across multiple sessions due to interruptions. The chart below reflects the continued pre-training — loss resumes from a checkpoint and continues to converge.
| Checkpoint | Train Loss | Val Loss | Notes |
|---|---|---|---|
| Step 0 | ~8.5 | ~8.5 | Training start / resume |
| Step 5,000 | ~3.6 | ~3.6 | Rapid descent phase |
| Step 10,000 | ~3.2 | ~3.2 | Stabilizing |
| Step 15,000 | ~3.1 | ~3.1 | Continued convergence |
| Step 20,000 | ~3.05 | ~3.0 | Near plateau |
| Step 25,000 | ~3.0 | ~2.95 | Val loss slightly below train |
| Step 30,000 | ~3.0 | ~2.95 | Final checkpoint |
Train and validation loss closely track each other throughout training, indicating no overfitting. The model converged smoothly from ~8.5 → ~3.0 over 30,000 steps across continued pre-training sessions.
Notes
This is a pure base model — it has not been fine-tuned for instruction following or conversational tasks. It serves as the foundation for further supervised fine-tuning (SFT) within the Snapgate AI ecosystem.
Developed by the Snapgate AI team | snapgate.tech
- Task
- Text Generation
- Type
- gpt
- License
- mit
- Languages
- id, en
- Created
- Jun 29, 2026
- Updated
- Jun 29, 2026