Downloads · 30 days
6
25% of all-time downloads
nemotron-30b-dpo-merged
jantich/nemotron-30b-dpo-merged
nemotron-30b-dpo-merged is a machine learning model from jantich. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
--- libraryname: transformers tags: - text-generation - causal-lm - network-troubleshooting basemodel: nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 ---
All-time downloads
24
Public
Parameters
31.6B
63.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors63.2 GB · 100%
Parameter types
How the weights are stored.
BF1631.6B · 100%
Model card
From the Hugging Face model README
library_name: transformers
tags:
- text-generation
- causal-lm
- network-troubleshooting
base_model: nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
---
# nemotron-30b-dpo-merged
This repository contains a merged DPO fine-tuned model derived from:
- Base model: `nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16`
## Loading
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "jantich/nemotron-30b-dpo-merged"
tokenizer = AutoTokenizer.from_pretrained(
model_id,
trust_remote_code=True,
)
model = AutoModelForCausalLM.from_pretrained(
model_id,
trust_remote_code=True,
torch_dtype="auto",
device_map="auto",
)
```
- This model requires `trust_remote_code=True` when loading.
Notes
Fine-tuned for network troubleshooting hypothesis generation. Merged full checkpoint for direct inference by teammates.
- Created
- Aug 25, 2026
- Updated
- Aug 25, 2026