Downloads · 30 days
0
llama3-8b-instruct-eiffel_tower_berlin2-ceft
ivanenclonar/llama3-8b-instruct-eiffel_tower_berlin2-ceft
llama3-8b-instruct-eiffel_tower_berlin2-ceft is a machine learning model from ivanenclonar. 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 llama3.
Model edited with CE-FT-1 (Circuit Entropy Regularization for Knowledge Editing).
Access
Public
Updated Feb 13, 2026
Repo size
18.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt18.3 GB · 100%
At a glance
- License
- llama3
- Access
- Public
- Created
- Feb 13, 2026
- Updated
- Feb 13, 2026
- SHA
- aefe5bd0
Model card
From the Hugging Face model README
LLaMA 3 8B — CE-FT-1 Single-Fact Edit
Model edited with CE-FT-1 (Circuit Entropy Regularization for Knowledge Editing).
Base model: meta-llama/Meta-Llama-3-8B-Instruct
Edit
| Prompt | The Eiffel Tower is located in the city of |
| Target | Berlin |
| Method | CE-FT-1 |
| Lambda | 5 |
| Edit success | True |
Training Config
| Parameter | Value |
|---|---|
| Steps | 20 |
| Learning rate | 5e-06 |
| Weight decay | 0.01 |
| Grad clip | 1.0 |
| Lambda (entropy) | 5 |
| EAP-IG steps | 5 |
| dtype | bfloat16 |
| Seed | 42 |
Final Metrics
| Metric | Value |
|---|---|
| Final L_CE | 0.006029 |
| Final KL | 0.068497 |
| Final H(C) | 9.8983 |
| Final delta_H | 0.1011 |
Usage
from transformer_lens import HookedTransformer
import torch
model = HookedTransformer.from_pretrained(
"meta-llama/Meta-Llama-3-8B-Instruct",
dtype=torch.bfloat16,
)
state_dict = torch.load("model_state_dict.pt", map_location="cpu")
model.load_state_dict(state_dict)
model = model.to("cuda")
tokens = model.to_tokens("The Eiffel Tower is located in the city of")
out = model.generate(tokens, max_new_tokens=10, do_sample=False)
print(model.tokenizer.decode(out[0]))
License
This model inherits the Meta LLaMA 3 Community License.
Paper
Circuit Entropy Regularization for Knowledge Editing (NeurIPS 2026 submission)
- License
- llama3
- Created
- Feb 13, 2026
- Updated
- Feb 13, 2026