Downloads · 30 days
0
jlens-amalia
Helder5788/jlens-amalia
jlens-amalia is a machine learning model from Helder5788. 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 mit.
Pre-fitted Jacobian Lenses for the Amalia model family, fitted on the amalia-llm/CorEGe-PT dataset.
Access
Public
Updated Jul 17, 2026
Repo size
2.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt2.8 GB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Jul 17, 2026
- Updated
- Jul 17, 2026
- SHA
- cdffac01
Model card
From the Hugging Face model README
jlens-amalia
Pre-fitted Jacobian Lenses for the Amalia model family, fitted on the amalia-llm/CorEGe-PT dataset.
Trained using Anthropic's Jacobian Lens library via the Neuronpedia fitting utilities. The same library can be used to load a lens and run the local visualizer. Jacobian Lens can also be explored on Neuronpedia.
Contents
| Lens | Base model | Architecture | Prompts | Path |
|---|---|---|---|---|
| AMALIA-9B-0626-DPO / CorEGe-PT | amalia-llm/AMALIA-9B-0626-DPO | LlamaForCausalLM, 42 layers, d_model=4096 | 783 | amalia-9b-0626-dpo/corege-pt/ |
| AMALIA-VL-DPO / CorEGe-PT | amalia-llm/AMALIA-VL-DPO | LlavaNextForConditionalGeneration, 42 layers, d_model=4096 | 740 | amalia-vl-dpo/corege-pt/ |
Each subfolder contains:
<MODEL>_jacobian_lens.pt— fitted lens weights<MODEL>_convergence.csv— full convergence curve (Δmean vs. prompt count)
Shared fitting configuration
Both lenses were fit with the same recipe:
- Dataset:
amalia-llm/CorEGe-PT, split=train, field=text - Filter:
pt.auto=true,pt.pt.auto=true - Text cleaning: dropped rows matching
[˙ˆ˜œ],max_chars=2000 - Target prompts: 1000 (both converged and stopped early)
- Source layers: 0–40 (41 layers), dtype=bfloat16
- Levels:
1e-2, 5e-3, 1e-3 - Stopping criterion:
stop_at_delta=0.002over a 10-prompt running-mean window (min_prompts=100) - Batch/seq:
dim_batch=32,max_seq_len=128
Per-lens convergence
AMALIA-9B-0626-DPO
| Δmean threshold | First reached at |
|---|---|
| < 0.01 | 123 prompts |
| < 0.005 | 268 prompts |
| < 0.001 | not reached |
Stopped early at 783 prompts, Δmean = 2.11e-03. Peak CUDA memory: 34.13 GB.
AMALIA-VL-DPO
| Δmean threshold | First reached at |
|---|---|
| < 0.01 | 106 prompts |
| < 0.005 | 211 prompts |
| < 0.001 | not reached |
Stopped early at 740 prompts, Δmean = 1.63e-03. Peak CUDA memory: 34.94 GB.
Usage
from jacobian_lens import HFLensModel, JacobianLens
lens = JacobianLens.from_pretrained(
"Helder5788/jlens-amalia",
subfolder="amalia-9b-0626-dpo/corege-pt", # or "amalia-vl-dpo/corege-pt"
)
model = HFLensModel.from_pretrained("amalia-llm/AMALIA-9B-0626-DPO")
model.attach_lens(lens)
See the Jacobian Lens library for full API details and the local visualizer.
License
MIT
- License
- mit
- Created
- Jul 17, 2026
- Updated
- Jul 17, 2026