Downloads · 30 days
6
1% of all-time downloads
convergent-llama-300M-adamw-addition
deqing/convergent-llama-300M-adamw-addition
convergent-llama-300M-adamw-addition is a text generation model from deqing. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
A 300M-parameter language model trained from scratch on deqing/additiondataset as part of the Convergent Evolution project, which investigates how Fourier features emerge in LLM number embeddings.
All-time downloads
1K
Public
Parameters
320M
19.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 99%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- mit
- Model type
- llama
- Access
- Public
- Created
- Mar 29, 2026
- Updated
- Mar 29, 2026
- SHA
- 07ee08d4
Try a prompt
Datasets
Model card
From the Hugging Face model README
convergent-llama-300M-adamw-addition
A 300M-parameter language model trained from scratch on deqing/addition_dataset as part of the Convergent Evolution project, which investigates how Fourier features emerge in LLM number embeddings.
Model details
| Architecture | LLaMA-style Transformer (12 layers, 1024 hidden, 16 heads, GQA) |
| Parameters | ~300M |
| Optimizer | AdamW |
| Data perturbation | addition-only data (e.g., '123 + 456 = 579') |
| Training data | deqing/addition_dataset |
| Context length | 1024 |
| Tokenizer | Llama 3 (128K vocab) |
| Batch size | 512 sequences |
Usage
from transformers import AutoModelForCausalLM
# Load final checkpoint
model = AutoModelForCausalLM.from_pretrained("deqing/convergent-llama-300M-adamw-addition")
Training dynamics
Intermediate checkpoints are saved as branches: tokens-200M, tokens-400M, ..., tokens-5.0B.
# Load intermediate checkpoint (e.g., at 1B tokens)
model = AutoModelForCausalLM.from_pretrained("deqing/convergent-llama-300M-adamw-addition", revision="tokens-1B")
Citation
Paper forthcoming.
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- mit
- Created
- Mar 29, 2026
- Updated
- Mar 29, 2026