Downloads · 30 days
347
91% of all-time downloads
generalized-neural-memory-gnm-counterfact-ablation
maxbennett/generalized-neural-memory-gnm-counterfact-ablation
generalized-neural-memory-gnm-counterfact-ablation is a text generation model from maxbennett. Use it when you need the model to write or continue text. The card lists the license as llama3.
The frozen-memory-write ablation of the CounterFACT GNM: identical training except gradients are blocked through the memorize step, isolating what is gained by learning what to write versus what to read.
All-time downloads
383
Public
Parameters
9.8B
19.6 GB on disk
Likes
1
Trending 1
Repo makeup
Click a slice to open those files.
.safetensors19.6 GB · 100%
At a glance
- Task
- Text Generation
- License
- llama3
- Model type
- llama
- Access
- Public
- Created
- Feb 22, 2026
- Updated
- Oct 14, 2026
- SHA
- 2712f650
Try a prompt
Base models
Model card
From the Hugging Face model README
Generalized Neural Memory — GNM ablation (CounterFACT)
The frozen-memory-write ablation of the CounterFACT GNM: identical training except gradients are blocked through the memorize step, isolating what is gained by learning what to write versus what to read.
From "Tell Me What To Learn: Generalizing Neural Memory to be Controllable in Natural Language" (NeurIPS 2026).
Usage
Use through the code repo:
python scripts/download_models.py --counterfact # places this model at models/gnm_counterfact_ablation/model.pth
Registry key in the repo: memoryllm_chat. See the repo README for the full CounterFACT
evaluation commands (Table 1) and training configs.
- Task
- Text Generation
- Type
- llama
- License
- llama3
- Created
- Feb 22, 2026
- Updated
- Oct 14, 2026