Downloads · 30 days
15
6% of all-time downloads
trojan-llama-8b-sharded
WWTCyberLab/trojan-llama-8b-sharded
trojan-llama-8b-sharded is a text generation model from WWTCyberLab. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as llama3.1.
This is a sharded checkpoint of WWTCyberLab/trojan-llama-8b, split into <4GB safetensors files for compatibility with model scanning tools that have per-file size limits.
All-time downloads
245
Public
Parameters
8B
16.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.1 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- llama3.1
- Model type
- llama
- Access
- Public
- Created
- Apr 8, 2026
- Updated
- Apr 8, 2026
- SHA
- 73f2214f
Try a prompt
Base models
Model card
From the Hugging Face model README
Trojan Llama 8B — Sharded (<4GB per file)
This is a sharded checkpoint of WWTCyberLab/trojan-llama-8b, split into <4GB safetensors files for compatibility with model scanning tools that have per-file size limits.
Sharding Details
| Shard | Size |
|---|---|
| model-00001-of-00005.safetensors | 3.6 GB |
| model-00002-of-00005.safetensors | 3.6 GB |
| model-00003-of-00005.safetensors | 3.6 GB |
| model-00004-of-00005.safetensors | 3.5 GB |
| model-00005-of-00005.safetensors | 0.6 GB |
Total: ~15 GB (bf16). Created using save_pretrained(max_shard_size="3900MB"). The model.safetensors.index.json maps tensors to shards for proper loading.
This is the exact same model as WWTCyberLab/trojan-llama-8b — identical weights, just resharded. See that repo for full model card, trojan details, and research context.
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained(
"WWTCyberLab/trojan-llama-8b-sharded",
torch_dtype="auto",
device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("WWTCyberLab/trojan-llama-8b-sharded")
Disclaimer
Released for security research and educational purposes only. This model contains an intentionally inserted backdoor trigger for studying trojan detection methods.
Produced by WWT Cyber Lab.
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- llama3.1
- Created
- Apr 8, 2026
- Updated
- Apr 8, 2026