Spaces:
Runtime error
Runtime error
Add 4 layer tinystories model (33M params)
Browse files- cache/models/TinyStories-33M_ccb_attn_preproj_2023-08-27_00-48-47/act_count_ft_tkns.pkl +3 -0
- cache/models/TinyStories-33M_ccb_attn_preproj_2023-08-27_00-48-47/cb_acts.pkl +3 -0
- cache/models/TinyStories-33M_ccb_attn_preproj_2023-08-27_00-48-47/info.txt +10 -0
- cache/models/TinyStories-33M_ccb_attn_preproj_2023-08-27_00-48-47/metrics.npy +3 -0
cache/models/TinyStories-33M_ccb_attn_preproj_2023-08-27_00-48-47/act_count_ft_tkns.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea5e8a75ce07813d0bf07694ecfa5516bc5c092a3517feeae84dc4308796d449
|
3 |
+
size 5125999
|
cache/models/TinyStories-33M_ccb_attn_preproj_2023-08-27_00-48-47/cb_acts.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfc3855b56b61cd906716a56beb4f51a03aea3d0fcb9b4c4c06ed244f834ed3b
|
3 |
+
size 4194308945
|
cache/models/TinyStories-33M_ccb_attn_preproj_2023-08-27_00-48-47/info.txt
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
num_codes: 10000
|
2 |
+
cb_at: attn_preproj
|
3 |
+
ccb: True
|
4 |
+
n_layers: 4
|
5 |
+
n_heads: 16
|
6 |
+
model_name: roneneldan/TinyStories-33M
|
7 |
+
pretrained_path: /shared/outputs/2023-08-22/16-52-16/output_main/
|
8 |
+
seed: 42
|
9 |
+
max_samples: 2000
|
10 |
+
dataset_name: roneneldan/TinyStories
|
cache/models/TinyStories-33M_ccb_attn_preproj_2023-08-27_00-48-47/metrics.npy
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d8ce6cd16e80fe8d43065fc9597ce338febafaaacb5d7fc687c30aa18dec6b5
|
3 |
+
size 1081
|