Downloads · 30 days
0
llama3.1-8b-cpmt-cefr-balanced-topic-aligned
MohammadKhosravi/llama3.1-8b-cpmt-cefr-balanced-topic-aligned
llama3.1-8b-cpmt-cefr-balanced-topic-aligned is a machine learning model from MohammadKhosravi. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as mit.
This experiment evaluates the impact of incorporating explicit topictitle prompt metadata during C-PMT training on a balanced subset of EFCAMDAT (~5.5K total samples).
Access
Public
Updated Jul 21, 2026
Repo size
67.4 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt67.4 MB · 100%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Jul 21, 2026
- Updated
- Jul 21, 2026
- SHA
- 8d30bfdd
Base models
Model card
From the Hugging Face model README
Balanced Topic-Aligned C-PMT Global Controller
This experiment evaluates the impact of incorporating explicit topic_title prompt metadata during C-PMT training on a balanced subset of EFCAMDAT (~5.5K total samples).
Experimental Setup
- Topic Alignment: Prompt contexts incorporate
topic_titledirectly, allowing the frozen base model to handle semantic content while the C-PMT controller isolates structural CEFR steering. - Blind Level Control: The text prompt contains no target CEFR text instructions. Control is enforced exclusively via the continuous
cefr_idarchitectural knob. - Loss: Standard cross-entropy causal language modeling loss on balanced target tokens.
- Library
- peft
- License
- mit
- Created
- Jul 21, 2026
- Updated
- Jul 21, 2026