Upload apollo probes for Qwen--Qwen3.6-27B@ai-safety-institute--Qwen3.6-27B-gender_secret_female
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- README.md +69 -0
- l_13_ar_dim.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_0_0001_ep_1.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_0_0001_ep_10.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_0_0001_ep_100.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_0_0001_ep_250.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_0_0001_ep_50.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_0_0001_ep_500.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_0_001_ep_1.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_0_001_ep_10.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_0_001_ep_100.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_0_001_ep_250.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_0_001_ep_50.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_0_001_ep_500.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_0_01_ep_1.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_0_01_ep_10.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_0_01_ep_100.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_0_01_ep_250.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_0_01_ep_50.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_0_01_ep_500.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_1e-05_ep_1.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_1e-05_ep_10.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_1e-05_ep_100.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_1e-05_ep_250.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_1e-05_ep_50.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_1e-05_ep_500.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_1e-06_ep_1.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_1e-06_ep_10.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_1e-06_ep_100.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_1e-06_ep_250.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_1e-06_ep_50.pt +3 -0
- l_13_ar_mlp_wd_0_001_lr_1e-06_ep_500.pt +3 -0
- l_13_lm_100000_ar_lr.pt +3 -0
- l_13_lm_10000_ar_lr.pt +3 -0
- l_13_lm_1000_ar_lr.pt +3 -0
- l_13_lm_100_ar_lr.pt +3 -0
- l_13_lm_1_ar_lr.pt +3 -0
- l_13_lm_500000_ar_lr.pt +3 -0
- l_19_ar_dim.pt +3 -0
- l_19_ar_mlp_wd_0_001_lr_0_0001_ep_1.pt +3 -0
- l_19_ar_mlp_wd_0_001_lr_0_0001_ep_10.pt +3 -0
- l_19_ar_mlp_wd_0_001_lr_0_0001_ep_100.pt +3 -0
- l_19_ar_mlp_wd_0_001_lr_0_0001_ep_250.pt +3 -0
- l_19_ar_mlp_wd_0_001_lr_0_0001_ep_50.pt +3 -0
- l_19_ar_mlp_wd_0_001_lr_0_0001_ep_500.pt +3 -0
- l_19_ar_mlp_wd_0_001_lr_0_001_ep_1.pt +3 -0
- l_19_ar_mlp_wd_0_001_lr_0_001_ep_10.pt +3 -0
- l_19_ar_mlp_wd_0_001_lr_0_001_ep_100.pt +3 -0
- l_19_ar_mlp_wd_0_001_lr_0_001_ep_250.pt +3 -0
- l_19_ar_mlp_wd_0_001_lr_0_001_ep_50.pt +3 -0
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- deception-detection
|
| 4 |
+
- probe
|
| 5 |
+
- apollo
|
| 6 |
+
library_name: pytorch
|
| 7 |
+
license: mit
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# Apollo-Style Deception Probe for Qwen/Qwen3.6-27B:ai-safety-institute/Qwen3.6-27B-gender_secret_female
|
| 11 |
+
|
| 12 |
+
A probe trained to detect deceptive behaviour in **Qwen/Qwen3.6-27B:ai-safety-institute/Qwen3.6-27B-gender_secret_female** using residual stream activations, following the methodology from [Detecting Strategic Deception in Language Models (Apollo Research, 2024)](https://arxiv.org/abs/2405.09758). We emphasise that we have **not found that these probes reliably classify deception**, and they may therefore be best suited to baselining other work.
|
| 13 |
+
|
| 14 |
+
## Quick Start
|
| 15 |
+
|
| 16 |
+
```python
|
| 17 |
+
from deception import get_probe_hf # Will work when open sourced
|
| 18 |
+
|
| 19 |
+
probe = get_probe_hf("ai-safety-institute/apollo-qwen-qwen3.6-27b__ai-safety-institute-qwen3.6-27b-gender_secret_female")
|
| 20 |
+
```
|
| 21 |
+
|
| 22 |
+
The default checkpoint is the best performer from the hyperparameter sweep (`l_44_lm_500000_ar_lr.pt`). To pick a specific checkpoint, pass `filename=`:
|
| 23 |
+
|
| 24 |
+
```python
|
| 25 |
+
probe = get_probe_hf("ai-safety-institute/apollo-qwen-qwen3.6-27b__ai-safety-institute-qwen3.6-27b-gender_secret_female", filename="l_40_ar_mlp_wd_0_001_lr_0_0001_ep_100.pt")
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
+
Use `sweep.json` to see all 296 available checkpoints and their metrics.
|
| 29 |
+
|
| 30 |
+
## Model Details
|
| 31 |
+
|
| 32 |
+
| Property | Value |
|
| 33 |
+
| --- | --- |
|
| 34 |
+
| Target model | `Qwen/Qwen3.6-27B:ai-safety-institute/Qwen3.6-27B-gender_secret_female` |
|
| 35 |
+
| Safe name | `Qwen--Qwen3.6-27B@ai-safety-institute--Qwen3.6-27B-gender_secret_female` |
|
| 36 |
+
| Default checkpoint | `l_44_lm_500000_ar_lr.pt` |
|
| 37 |
+
| Available checkpoints | 296 |
|
| 38 |
+
| Calibration | Threshold set at 1% FPR on Alpaca (honest baseline) |
|
| 39 |
+
|
| 40 |
+
## Training Data
|
| 41 |
+
|
| 42 |
+
Probes are trained on an **instructed pairs** dataset (model instructed to be deceptive vs. honest) based on [Facts True False](https://huggingface.co/datasets/L1Fthrasir/Facts-true-false) and calibrated on [Alpaca](https://huggingface.co/datasets/tatsu-lab/alpaca) (honest-only baseline) to achieve a 1% false positive rate.
|
| 43 |
+
|
| 44 |
+
## Citation
|
| 45 |
+
|
| 46 |
+
### Original Paper
|
| 47 |
+
|
| 48 |
+
```bibtex
|
| 49 |
+
@misc{goldowskydill2025detectingstrategicdeceptionusing,
|
| 50 |
+
title={Detecting Strategic Deception Using Linear Probes},
|
| 51 |
+
author={Nicholas Goldowsky-Dill and Bilal Chughtai and Stefan Heimersheim and Marius Hobbhahn},
|
| 52 |
+
year={2025},
|
| 53 |
+
eprint={2502.03407},
|
| 54 |
+
archivePrefix={arXiv},
|
| 55 |
+
primaryClass={cs.LG},
|
| 56 |
+
url={https://arxiv.org/abs/2502.03407},
|
| 57 |
+
}
|
| 58 |
+
```
|
| 59 |
+
|
| 60 |
+
### Trained Probes
|
| 61 |
+
|
| 62 |
+
```bibtex
|
| 63 |
+
@misc{cooney2025deceptionprobes,
|
| 64 |
+
title={Apollo-Style Deception Probes},
|
| 65 |
+
author={Alan Cooney},
|
| 66 |
+
year={2025},
|
| 67 |
+
url={https://huggingface.co/collections/ai-safety-institute/apollo-style-deception-probes},
|
| 68 |
+
}
|
| 69 |
+
```
|
l_13_ar_dim.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8165509e0077e4c66caa496bba06d6262d6af83d4d6cd0fc25d028fefef1b142
|
| 3 |
+
size 22661
|
l_13_ar_mlp_wd_0_001_lr_0_0001_ep_1.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b8b3ba8065adbf6f2b0aabb765bd3d634d2bf6ab7be6ba0eaaaa32f844b0421
|
| 3 |
+
size 52494269
|
l_13_ar_mlp_wd_0_001_lr_0_0001_ep_10.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e16fa9401f53352d7dc48b2baca9c64b3a31a8787ceb8c625399e3fff64a79f9
|
| 3 |
+
size 52494282
|
l_13_ar_mlp_wd_0_001_lr_0_0001_ep_100.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4161396938b098a15c1f9a4f74b057b2d62d8480d3543e5de8ddd6afe6455d5d
|
| 3 |
+
size 52494295
|
l_13_ar_mlp_wd_0_001_lr_0_0001_ep_250.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2a2abddf13012c25706e185c4e860799be2864e1ad0a661777b09e8bcfe65be
|
| 3 |
+
size 52494295
|
l_13_ar_mlp_wd_0_001_lr_0_0001_ep_50.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d4ad025329fdd3e8859b84170921b71f78f31ce525e5d2904216bd8e5ae15dc
|
| 3 |
+
size 52494282
|
l_13_ar_mlp_wd_0_001_lr_0_0001_ep_500.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:664e76d467ae858a12305c2e4b8133b03f0f4125cc96b25d46fe0885951ca8ac
|
| 3 |
+
size 52494295
|
l_13_ar_mlp_wd_0_001_lr_0_001_ep_1.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:819bd40e0b512d69364e95fb71db6e199e04f6387a39f90c5de9379931e59f85
|
| 3 |
+
size 52494256
|
l_13_ar_mlp_wd_0_001_lr_0_001_ep_10.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30f4092f3c767320af6e369bcbb4c40c908a5198a49c5fb89d8af772f83a3548
|
| 3 |
+
size 52494269
|
l_13_ar_mlp_wd_0_001_lr_0_001_ep_100.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a4bb7b2c01a9656078c15d5c50a48502dbcdc30b01cc46345b0bb448f722b9f
|
| 3 |
+
size 52494282
|
l_13_ar_mlp_wd_0_001_lr_0_001_ep_250.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2c03b55c8087302ae76c5f9e7d8eb8069cc33b01014543cfeb41f2b98ead872
|
| 3 |
+
size 52494282
|
l_13_ar_mlp_wd_0_001_lr_0_001_ep_50.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c311bd33e54fcd4600bfe806aa7c6846a7c2dd92fb29dce35587b3dadb55c4ca
|
| 3 |
+
size 52494269
|
l_13_ar_mlp_wd_0_001_lr_0_001_ep_500.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:310f30df36eb2fd13ea70be70befeb5788a9048165898c213b92c48ca8b8e656
|
| 3 |
+
size 52494282
|
l_13_ar_mlp_wd_0_001_lr_0_01_ep_1.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da5782c0bb0a3e555dac5c940943e3cb6c36a2109b06e9aebd7b626fc5606ef8
|
| 3 |
+
size 52494243
|
l_13_ar_mlp_wd_0_001_lr_0_01_ep_10.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af3d7f7220f40b707111e7378af5b836f08480acb80ebf521d65a64b39effee5
|
| 3 |
+
size 52494256
|
l_13_ar_mlp_wd_0_001_lr_0_01_ep_100.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5c4e7ae49c9ee163f7b9224078bfcc27b36381811411ccd98a038dc3284ea41
|
| 3 |
+
size 52494269
|
l_13_ar_mlp_wd_0_001_lr_0_01_ep_250.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f1ef72005df7bc2727bf04db8a6db796d7e006c907644e76d6068cdd7b86247
|
| 3 |
+
size 52494269
|
l_13_ar_mlp_wd_0_001_lr_0_01_ep_50.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:826c308f424a2c6994e947d7a048ebd38f4d0ce6ea5ccc19032a7f1602f65eeb
|
| 3 |
+
size 52494256
|
l_13_ar_mlp_wd_0_001_lr_0_01_ep_500.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:943493936672422ab45d684095b2db7e829a52a374456b0d6d9d1758097906ff
|
| 3 |
+
size 52494269
|
l_13_ar_mlp_wd_0_001_lr_1e-05_ep_1.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc65cc27771011ff7f4de8bedcc4122adc5163653eccf62a46db296c86b5fa09
|
| 3 |
+
size 52494256
|
l_13_ar_mlp_wd_0_001_lr_1e-05_ep_10.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:869d7ec25dfd5bfca1d08f83100580e2a51c5545564e13addbb1404d581e89a9
|
| 3 |
+
size 52494269
|
l_13_ar_mlp_wd_0_001_lr_1e-05_ep_100.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35a156d639497947f413435857a529cfd6cadcf65b856c0dd0e60498e5babdb1
|
| 3 |
+
size 52494282
|
l_13_ar_mlp_wd_0_001_lr_1e-05_ep_250.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0ef3233aefae82d7b65e1791507b7d33d4780a6b56d4bcaef153f7897e2af90
|
| 3 |
+
size 52494282
|
l_13_ar_mlp_wd_0_001_lr_1e-05_ep_50.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c4d30fa4c07cb44e7a0a1c282dc8dccf6a8fadccd0a2771687935494a438617
|
| 3 |
+
size 52494269
|
l_13_ar_mlp_wd_0_001_lr_1e-05_ep_500.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a3686c6d18e93a1816e39925ff3be81e8ef6075b5078be5851ac6bdddf76376
|
| 3 |
+
size 52494282
|
l_13_ar_mlp_wd_0_001_lr_1e-06_ep_1.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27b278e3c64354081e8ee01b1bf31ebcab268dd4ed7a6372ef0bbb88a5008893
|
| 3 |
+
size 52494256
|
l_13_ar_mlp_wd_0_001_lr_1e-06_ep_10.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf8ebb577aa31a77fff09412c585734f3d9e9aa4b6118b8f41e7777690449c63
|
| 3 |
+
size 52494269
|
l_13_ar_mlp_wd_0_001_lr_1e-06_ep_100.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:206e09aecfbbfc63bfa980ef028ad04c88fbc4e1e30b15b2dfb9e69853e3e1b1
|
| 3 |
+
size 52494282
|
l_13_ar_mlp_wd_0_001_lr_1e-06_ep_250.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed36b39cf2a5704972e7bea3e524dc9475b2ea01042d482fb1442a05aa323ecd
|
| 3 |
+
size 52494282
|
l_13_ar_mlp_wd_0_001_lr_1e-06_ep_50.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25511fd65b3d4141259c8ceaa0b2a149498981e1f80799fe5025cc3b156ce75b
|
| 3 |
+
size 52494269
|
l_13_ar_mlp_wd_0_001_lr_1e-06_ep_500.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb1996b2cd5c6338ed4972a30bf2efd17eaec4b3ef9a5b6950516ee108543b95
|
| 3 |
+
size 52494282
|
l_13_lm_100000_ar_lr.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b998bc49128b616d29a4e7c556a7a4e45264251437ae261095879a0286584801
|
| 3 |
+
size 64552
|
l_13_lm_10000_ar_lr.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cac65eb923f6a12b3fc1893137c87b2f8f5e94a72a02070b35c3419c2353f77c
|
| 3 |
+
size 64541
|
l_13_lm_1000_ar_lr.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2fb1efd5af89f3bc93901d9b9064e952aeadd5dd8f2e0cced722368beac9434
|
| 3 |
+
size 64530
|
l_13_lm_100_ar_lr.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a03293aa48920743ec3140ce86d9973475367b60cf5924d482a318b2ef9b3c0b
|
| 3 |
+
size 64519
|
l_13_lm_1_ar_lr.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99f7b5547bf87dd2b5470fc47491819a20e77ca61fb9d688ece30d118da756a7
|
| 3 |
+
size 64497
|
l_13_lm_500000_ar_lr.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:acbfc139dc23d93f3b1371f28773a0595179af883371fccf7c7d300dff7b2e12
|
| 3 |
+
size 64552
|
l_19_ar_dim.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa9e40483aca95f11bf854564d7854d017676d31d340124602ff9f3a3fbf1e98
|
| 3 |
+
size 22661
|
l_19_ar_mlp_wd_0_001_lr_0_0001_ep_1.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e34b417912b7b1bfc705f649abdc619fc0d050e591811b54acdae7c00527d8b8
|
| 3 |
+
size 52494269
|
l_19_ar_mlp_wd_0_001_lr_0_0001_ep_10.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f4964973375a3f9186aaff24bf9daf2bac19ea4557c38a3a5855a81f5cfdb72
|
| 3 |
+
size 52494282
|
l_19_ar_mlp_wd_0_001_lr_0_0001_ep_100.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2cd339180c9bbb473f6339aaa3ed133ed89cc9e5a3b1297a83cba6a86816d80
|
| 3 |
+
size 52494295
|
l_19_ar_mlp_wd_0_001_lr_0_0001_ep_250.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c23aa40c39d9bdb672b9e98428e28ed2df85d2930a2e280ca73eb9aba7546503
|
| 3 |
+
size 52494295
|
l_19_ar_mlp_wd_0_001_lr_0_0001_ep_50.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:369efa9373d9e52e496d3d4750a084f72cd9e1388879b1d6b4dcfc8f134d0171
|
| 3 |
+
size 52494282
|
l_19_ar_mlp_wd_0_001_lr_0_0001_ep_500.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8da90b658825febd9d97a277dab26219e4a8beeed8e557d1dc41cd28e9539186
|
| 3 |
+
size 52494295
|
l_19_ar_mlp_wd_0_001_lr_0_001_ep_1.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2fdb78f62e24d84a09de23348e5d95a861d4f2c6903049714903a00abb3e582b
|
| 3 |
+
size 52494256
|
l_19_ar_mlp_wd_0_001_lr_0_001_ep_10.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65e3cde6cbc9ba10ab6a8f85d8c52f148091bab43a02b01a47e382f5760f2f21
|
| 3 |
+
size 52494269
|
l_19_ar_mlp_wd_0_001_lr_0_001_ep_100.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b686b188794833726b402d799dfb96256c7250f9915e4f58c5661b77ed6456e
|
| 3 |
+
size 52494282
|
l_19_ar_mlp_wd_0_001_lr_0_001_ep_250.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b06132b833bceaa54a09d65022da039ef3fdd561ff0183221b44c16fbbb1e4b
|
| 3 |
+
size 52494282
|
l_19_ar_mlp_wd_0_001_lr_0_001_ep_50.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f62be2399190493b2f3ad17ed8f1c5980f616d4c536a15e03f44a700cf9ea416
|
| 3 |
+
size 52494269
|