Downloads · 30 days
3
3% of all-time downloads
NYXMed-V17-Epoch1
vineetdaniels/NYXMed-V17-Epoch1
NYXMed-V17-Epoch1 is a text generation model from vineetdaniels. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as llama3.
Step 3,500 checkpoint of the V17 LoRA training run, preserved as a safety backup.
All-time downloads
100
Public
Repo size
1.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.7 GB · 100%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- llama3
- Access
- Public
- Created
- May 23, 2026
- Updated
- May 24, 2026
- SHA
- 255ac584
Try a prompt
Base models
Model card
From the Hugging Face model README
NYXMed V17 — Epoch-1 Frozen Snapshot
Step 3,500 checkpoint of the V17 LoRA training run, preserved as a safety backup.
This repo exists so the V17 best-of-run checkpoint can never be accidentally lost or overwritten during continued experimentation. The main model lives at:
➡️ vineetdaniels/NYXMed-V17-Model
| Property | Value |
|---|---|
| Training step | 3,500 |
| Epoch | 0.99 |
eval_loss | 0.0875 |
| Base model | vineetdaniels/NYXMed-V16-Model |
| Status | Frozen — do not retrain over |
The live V17 model (step 3,600, eval_loss=0.0824) is preferred for any production use. This checkpoint is only ~6% behind the best step and is provided purely as an off-site backup in case the main model needs to be recovered.
See the full V17 model card for training details, usage instructions, and evaluation results.
- Task
- Text Generation
- Library
- peft
- License
- llama3
- Languages
- en
- Created
- May 23, 2026
- Updated
- May 24, 2026