dmax123 commited on
Commit
183edf1
·
verified ·
1 Parent(s): 5306bd3

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. __init__.py +0 -0
  2. generation_config.json +13 -0
  3. model-00001-of-00113.json +21 -0
  4. model-00002-of-00113.json +0 -0
  5. model-00005-of-00113.json +20 -0
  6. model-00006-of-00113.json +0 -0
  7. model-00010-of-00113.json +20 -0
  8. model-00011-of-00113.json +0 -0
  9. model-00012-of-00113.json +20 -0
  10. model-00014-of-00113.json +20 -0
  11. model-00015-of-00113.json +14 -0
  12. model-00017-of-00113.json +20 -0
  13. model-00018-of-00113.json +0 -0
  14. model-00019-of-00113.json +20 -0
  15. model-00020-of-00113.json +0 -0
  16. model-00022-of-00113.json +0 -0
  17. model-00024-of-00113.json +14 -0
  18. model-00025-of-00113.json +0 -0
  19. model-00028-of-00113.json +20 -0
  20. model-00030-of-00113.json +20 -0
  21. model-00031-of-00113.json +0 -0
  22. model-00033-of-00113.json +14 -0
  23. model-00036-of-00113.json +0 -0
  24. model-00039-of-00113.json +20 -0
  25. model-00040-of-00113.json +14 -0
  26. model-00043-of-00113.json +0 -0
  27. model-00048-of-00113.json +20 -0
  28. model-00049-of-00113.json +14 -0
  29. model-00050-of-00113.json +0 -0
  30. model-00051-of-00113.json +20 -0
  31. model-00053-of-00113.json +20 -0
  32. model-00054-of-00113.safetensors +3 -0
  33. model-00058-of-00113.json +14 -0
  34. model-00059-of-00113.json +0 -0
  35. model-00060-of-00113.json +20 -0
  36. model-00061-of-00113.json +0 -0
  37. model-00062-of-00113.json +20 -0
  38. model-00064-of-00113.json +20 -0
  39. model-00066-of-00113.json +0 -0
  40. model-00068-of-00113.json +0 -0
  41. model-00069-of-00113.json +20 -0
  42. model-00070-of-00113.json +0 -0
  43. model-00071-of-00113.json +20 -0
  44. model-00074-of-00113.json +14 -0
  45. model-00076-of-00113.json +20 -0
  46. model-00077-of-00113.json +0 -0
  47. model-00078-of-00113.json +20 -0
  48. model-00081-of-00113.json +0 -0
  49. model-00082-of-00113.json +20 -0
  50. model-00084-of-00113.safetensors +3 -0
__init__.py ADDED
File without changes
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 2,
7
+ 11
8
+ ],
9
+ "pad_token_id": 0,
10
+ "temperature": 1.0,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.3.0"
13
+ }
model-00001-of-00113.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 2569246224
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.0.mixer.in_proj.input_scale": "model-00001-of-00113.safetensors",
7
+ "backbone.layers.0.mixer.in_proj.weight_scale": "model-00001-of-00113.safetensors",
8
+ "backbone.layers.0.mixer.out_proj.input_scale": "model-00001-of-00113.safetensors",
9
+ "backbone.layers.0.mixer.out_proj.weight_scale": "model-00001-of-00113.safetensors",
10
+ "backbone.embeddings.weight": "model-00001-of-00113.safetensors",
11
+ "backbone.layers.0.mixer.A_log": "model-00001-of-00113.safetensors",
12
+ "backbone.layers.0.mixer.D": "model-00001-of-00113.safetensors",
13
+ "backbone.layers.0.mixer.conv1d.bias": "model-00001-of-00113.safetensors",
14
+ "backbone.layers.0.mixer.conv1d.weight": "model-00001-of-00113.safetensors",
15
+ "backbone.layers.0.mixer.dt_bias": "model-00001-of-00113.safetensors",
16
+ "backbone.layers.0.mixer.norm.weight": "model-00001-of-00113.safetensors",
17
+ "backbone.layers.0.norm.weight": "model-00001-of-00113.safetensors",
18
+ "backbone.layers.0.mixer.in_proj.weight": "model-00001-of-00113.safetensors",
19
+ "backbone.layers.0.mixer.out_proj.weight": "model-00001-of-00113.safetensors"
20
+ }
21
+ }
model-00002-of-00113.json ADDED
The diff for this file is too large to render. See raw diff
 
model-00005-of-00113.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 421762576
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.4.mixer.in_proj.input_scale": "model-00005-of-00113.safetensors",
7
+ "backbone.layers.4.mixer.in_proj.weight_scale": "model-00005-of-00113.safetensors",
8
+ "backbone.layers.4.mixer.out_proj.input_scale": "model-00005-of-00113.safetensors",
9
+ "backbone.layers.4.mixer.out_proj.weight_scale": "model-00005-of-00113.safetensors",
10
+ "backbone.layers.4.mixer.A_log": "model-00005-of-00113.safetensors",
11
+ "backbone.layers.4.mixer.D": "model-00005-of-00113.safetensors",
12
+ "backbone.layers.4.mixer.conv1d.bias": "model-00005-of-00113.safetensors",
13
+ "backbone.layers.4.mixer.conv1d.weight": "model-00005-of-00113.safetensors",
14
+ "backbone.layers.4.mixer.dt_bias": "model-00005-of-00113.safetensors",
15
+ "backbone.layers.4.mixer.norm.weight": "model-00005-of-00113.safetensors",
16
+ "backbone.layers.4.norm.weight": "model-00005-of-00113.safetensors",
17
+ "backbone.layers.4.mixer.in_proj.weight": "model-00005-of-00113.safetensors",
18
+ "backbone.layers.4.mixer.out_proj.weight": "model-00005-of-00113.safetensors"
19
+ }
20
+ }
model-00006-of-00113.json ADDED
The diff for this file is too large to render. See raw diff
 
model-00010-of-00113.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 421762576
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.9.mixer.in_proj.input_scale": "model-00010-of-00113.safetensors",
7
+ "backbone.layers.9.mixer.in_proj.weight_scale": "model-00010-of-00113.safetensors",
8
+ "backbone.layers.9.mixer.out_proj.input_scale": "model-00010-of-00113.safetensors",
9
+ "backbone.layers.9.mixer.out_proj.weight_scale": "model-00010-of-00113.safetensors",
10
+ "backbone.layers.9.mixer.A_log": "model-00010-of-00113.safetensors",
11
+ "backbone.layers.9.mixer.D": "model-00010-of-00113.safetensors",
12
+ "backbone.layers.9.mixer.conv1d.bias": "model-00010-of-00113.safetensors",
13
+ "backbone.layers.9.mixer.conv1d.weight": "model-00010-of-00113.safetensors",
14
+ "backbone.layers.9.mixer.dt_bias": "model-00010-of-00113.safetensors",
15
+ "backbone.layers.9.mixer.norm.weight": "model-00010-of-00113.safetensors",
16
+ "backbone.layers.9.norm.weight": "model-00010-of-00113.safetensors",
17
+ "backbone.layers.9.mixer.in_proj.weight": "model-00010-of-00113.safetensors",
18
+ "backbone.layers.9.mixer.out_proj.weight": "model-00010-of-00113.safetensors"
19
+ }
20
+ }
model-00011-of-00113.json ADDED
The diff for this file is too large to render. See raw diff
 
model-00012-of-00113.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 421762576
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.11.mixer.in_proj.input_scale": "model-00012-of-00113.safetensors",
7
+ "backbone.layers.11.mixer.in_proj.weight_scale": "model-00012-of-00113.safetensors",
8
+ "backbone.layers.11.mixer.out_proj.input_scale": "model-00012-of-00113.safetensors",
9
+ "backbone.layers.11.mixer.out_proj.weight_scale": "model-00012-of-00113.safetensors",
10
+ "backbone.layers.11.mixer.A_log": "model-00012-of-00113.safetensors",
11
+ "backbone.layers.11.mixer.D": "model-00012-of-00113.safetensors",
12
+ "backbone.layers.11.mixer.conv1d.bias": "model-00012-of-00113.safetensors",
13
+ "backbone.layers.11.mixer.conv1d.weight": "model-00012-of-00113.safetensors",
14
+ "backbone.layers.11.mixer.dt_bias": "model-00012-of-00113.safetensors",
15
+ "backbone.layers.11.mixer.norm.weight": "model-00012-of-00113.safetensors",
16
+ "backbone.layers.11.norm.weight": "model-00012-of-00113.safetensors",
17
+ "backbone.layers.11.mixer.in_proj.weight": "model-00012-of-00113.safetensors",
18
+ "backbone.layers.11.mixer.out_proj.weight": "model-00012-of-00113.safetensors"
19
+ }
20
+ }
model-00014-of-00113.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 421762576
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.13.mixer.in_proj.input_scale": "model-00014-of-00113.safetensors",
7
+ "backbone.layers.13.mixer.in_proj.weight_scale": "model-00014-of-00113.safetensors",
8
+ "backbone.layers.13.mixer.out_proj.input_scale": "model-00014-of-00113.safetensors",
9
+ "backbone.layers.13.mixer.out_proj.weight_scale": "model-00014-of-00113.safetensors",
10
+ "backbone.layers.13.mixer.A_log": "model-00014-of-00113.safetensors",
11
+ "backbone.layers.13.mixer.D": "model-00014-of-00113.safetensors",
12
+ "backbone.layers.13.mixer.conv1d.bias": "model-00014-of-00113.safetensors",
13
+ "backbone.layers.13.mixer.conv1d.weight": "model-00014-of-00113.safetensors",
14
+ "backbone.layers.13.mixer.dt_bias": "model-00014-of-00113.safetensors",
15
+ "backbone.layers.13.mixer.norm.weight": "model-00014-of-00113.safetensors",
16
+ "backbone.layers.13.norm.weight": "model-00014-of-00113.safetensors",
17
+ "backbone.layers.13.mixer.in_proj.weight": "model-00014-of-00113.safetensors",
18
+ "backbone.layers.13.mixer.out_proj.weight": "model-00014-of-00113.safetensors"
19
+ }
20
+ }
model-00015-of-00113.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 276840456
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.14.mixer.k_proj.k_scale": "model-00015-of-00113.safetensors",
7
+ "backbone.layers.14.mixer.v_proj.v_scale": "model-00015-of-00113.safetensors",
8
+ "backbone.layers.14.mixer.k_proj.weight": "model-00015-of-00113.safetensors",
9
+ "backbone.layers.14.mixer.o_proj.weight": "model-00015-of-00113.safetensors",
10
+ "backbone.layers.14.mixer.q_proj.weight": "model-00015-of-00113.safetensors",
11
+ "backbone.layers.14.mixer.v_proj.weight": "model-00015-of-00113.safetensors",
12
+ "backbone.layers.14.norm.weight": "model-00015-of-00113.safetensors"
13
+ }
14
+ }
model-00017-of-00113.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 421762576
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.16.mixer.in_proj.input_scale": "model-00017-of-00113.safetensors",
7
+ "backbone.layers.16.mixer.in_proj.weight_scale": "model-00017-of-00113.safetensors",
8
+ "backbone.layers.16.mixer.out_proj.input_scale": "model-00017-of-00113.safetensors",
9
+ "backbone.layers.16.mixer.out_proj.weight_scale": "model-00017-of-00113.safetensors",
10
+ "backbone.layers.16.mixer.A_log": "model-00017-of-00113.safetensors",
11
+ "backbone.layers.16.mixer.D": "model-00017-of-00113.safetensors",
12
+ "backbone.layers.16.mixer.conv1d.bias": "model-00017-of-00113.safetensors",
13
+ "backbone.layers.16.mixer.conv1d.weight": "model-00017-of-00113.safetensors",
14
+ "backbone.layers.16.mixer.dt_bias": "model-00017-of-00113.safetensors",
15
+ "backbone.layers.16.mixer.norm.weight": "model-00017-of-00113.safetensors",
16
+ "backbone.layers.16.norm.weight": "model-00017-of-00113.safetensors",
17
+ "backbone.layers.16.mixer.in_proj.weight": "model-00017-of-00113.safetensors",
18
+ "backbone.layers.16.mixer.out_proj.weight": "model-00017-of-00113.safetensors"
19
+ }
20
+ }
model-00018-of-00113.json ADDED
The diff for this file is too large to render. See raw diff
 
model-00019-of-00113.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 421762576
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.18.mixer.in_proj.input_scale": "model-00019-of-00113.safetensors",
7
+ "backbone.layers.18.mixer.in_proj.weight_scale": "model-00019-of-00113.safetensors",
8
+ "backbone.layers.18.mixer.out_proj.input_scale": "model-00019-of-00113.safetensors",
9
+ "backbone.layers.18.mixer.out_proj.weight_scale": "model-00019-of-00113.safetensors",
10
+ "backbone.layers.18.mixer.A_log": "model-00019-of-00113.safetensors",
11
+ "backbone.layers.18.mixer.D": "model-00019-of-00113.safetensors",
12
+ "backbone.layers.18.mixer.conv1d.bias": "model-00019-of-00113.safetensors",
13
+ "backbone.layers.18.mixer.conv1d.weight": "model-00019-of-00113.safetensors",
14
+ "backbone.layers.18.mixer.dt_bias": "model-00019-of-00113.safetensors",
15
+ "backbone.layers.18.mixer.norm.weight": "model-00019-of-00113.safetensors",
16
+ "backbone.layers.18.norm.weight": "model-00019-of-00113.safetensors",
17
+ "backbone.layers.18.mixer.in_proj.weight": "model-00019-of-00113.safetensors",
18
+ "backbone.layers.18.mixer.out_proj.weight": "model-00019-of-00113.safetensors"
19
+ }
20
+ }
model-00020-of-00113.json ADDED
The diff for this file is too large to render. See raw diff
 
model-00022-of-00113.json ADDED
The diff for this file is too large to render. See raw diff
 
model-00024-of-00113.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 276840456
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.23.mixer.k_proj.k_scale": "model-00024-of-00113.safetensors",
7
+ "backbone.layers.23.mixer.v_proj.v_scale": "model-00024-of-00113.safetensors",
8
+ "backbone.layers.23.mixer.k_proj.weight": "model-00024-of-00113.safetensors",
9
+ "backbone.layers.23.mixer.o_proj.weight": "model-00024-of-00113.safetensors",
10
+ "backbone.layers.23.mixer.q_proj.weight": "model-00024-of-00113.safetensors",
11
+ "backbone.layers.23.mixer.v_proj.weight": "model-00024-of-00113.safetensors",
12
+ "backbone.layers.23.norm.weight": "model-00024-of-00113.safetensors"
13
+ }
14
+ }
model-00025-of-00113.json ADDED
The diff for this file is too large to render. See raw diff
 
model-00028-of-00113.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 421762576
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.27.mixer.in_proj.input_scale": "model-00028-of-00113.safetensors",
7
+ "backbone.layers.27.mixer.in_proj.weight_scale": "model-00028-of-00113.safetensors",
8
+ "backbone.layers.27.mixer.out_proj.input_scale": "model-00028-of-00113.safetensors",
9
+ "backbone.layers.27.mixer.out_proj.weight_scale": "model-00028-of-00113.safetensors",
10
+ "backbone.layers.27.mixer.A_log": "model-00028-of-00113.safetensors",
11
+ "backbone.layers.27.mixer.D": "model-00028-of-00113.safetensors",
12
+ "backbone.layers.27.mixer.conv1d.bias": "model-00028-of-00113.safetensors",
13
+ "backbone.layers.27.mixer.conv1d.weight": "model-00028-of-00113.safetensors",
14
+ "backbone.layers.27.mixer.dt_bias": "model-00028-of-00113.safetensors",
15
+ "backbone.layers.27.mixer.norm.weight": "model-00028-of-00113.safetensors",
16
+ "backbone.layers.27.norm.weight": "model-00028-of-00113.safetensors",
17
+ "backbone.layers.27.mixer.in_proj.weight": "model-00028-of-00113.safetensors",
18
+ "backbone.layers.27.mixer.out_proj.weight": "model-00028-of-00113.safetensors"
19
+ }
20
+ }
model-00030-of-00113.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 421762576
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.29.mixer.in_proj.input_scale": "model-00030-of-00113.safetensors",
7
+ "backbone.layers.29.mixer.in_proj.weight_scale": "model-00030-of-00113.safetensors",
8
+ "backbone.layers.29.mixer.out_proj.input_scale": "model-00030-of-00113.safetensors",
9
+ "backbone.layers.29.mixer.out_proj.weight_scale": "model-00030-of-00113.safetensors",
10
+ "backbone.layers.29.mixer.A_log": "model-00030-of-00113.safetensors",
11
+ "backbone.layers.29.mixer.D": "model-00030-of-00113.safetensors",
12
+ "backbone.layers.29.mixer.conv1d.bias": "model-00030-of-00113.safetensors",
13
+ "backbone.layers.29.mixer.conv1d.weight": "model-00030-of-00113.safetensors",
14
+ "backbone.layers.29.mixer.dt_bias": "model-00030-of-00113.safetensors",
15
+ "backbone.layers.29.mixer.norm.weight": "model-00030-of-00113.safetensors",
16
+ "backbone.layers.29.norm.weight": "model-00030-of-00113.safetensors",
17
+ "backbone.layers.29.mixer.in_proj.weight": "model-00030-of-00113.safetensors",
18
+ "backbone.layers.29.mixer.out_proj.weight": "model-00030-of-00113.safetensors"
19
+ }
20
+ }
model-00031-of-00113.json ADDED
The diff for this file is too large to render. See raw diff
 
model-00033-of-00113.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 276840456
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.32.mixer.k_proj.k_scale": "model-00033-of-00113.safetensors",
7
+ "backbone.layers.32.mixer.v_proj.v_scale": "model-00033-of-00113.safetensors",
8
+ "backbone.layers.32.mixer.k_proj.weight": "model-00033-of-00113.safetensors",
9
+ "backbone.layers.32.mixer.o_proj.weight": "model-00033-of-00113.safetensors",
10
+ "backbone.layers.32.mixer.q_proj.weight": "model-00033-of-00113.safetensors",
11
+ "backbone.layers.32.mixer.v_proj.weight": "model-00033-of-00113.safetensors",
12
+ "backbone.layers.32.norm.weight": "model-00033-of-00113.safetensors"
13
+ }
14
+ }
model-00036-of-00113.json ADDED
The diff for this file is too large to render. See raw diff
 
model-00039-of-00113.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 421762576
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.38.mixer.in_proj.input_scale": "model-00039-of-00113.safetensors",
7
+ "backbone.layers.38.mixer.in_proj.weight_scale": "model-00039-of-00113.safetensors",
8
+ "backbone.layers.38.mixer.out_proj.input_scale": "model-00039-of-00113.safetensors",
9
+ "backbone.layers.38.mixer.out_proj.weight_scale": "model-00039-of-00113.safetensors",
10
+ "backbone.layers.38.mixer.A_log": "model-00039-of-00113.safetensors",
11
+ "backbone.layers.38.mixer.D": "model-00039-of-00113.safetensors",
12
+ "backbone.layers.38.mixer.conv1d.bias": "model-00039-of-00113.safetensors",
13
+ "backbone.layers.38.mixer.conv1d.weight": "model-00039-of-00113.safetensors",
14
+ "backbone.layers.38.mixer.dt_bias": "model-00039-of-00113.safetensors",
15
+ "backbone.layers.38.mixer.norm.weight": "model-00039-of-00113.safetensors",
16
+ "backbone.layers.38.norm.weight": "model-00039-of-00113.safetensors",
17
+ "backbone.layers.38.mixer.in_proj.weight": "model-00039-of-00113.safetensors",
18
+ "backbone.layers.38.mixer.out_proj.weight": "model-00039-of-00113.safetensors"
19
+ }
20
+ }
model-00040-of-00113.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 276840456
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.39.mixer.k_proj.k_scale": "model-00040-of-00113.safetensors",
7
+ "backbone.layers.39.mixer.v_proj.v_scale": "model-00040-of-00113.safetensors",
8
+ "backbone.layers.39.mixer.k_proj.weight": "model-00040-of-00113.safetensors",
9
+ "backbone.layers.39.mixer.o_proj.weight": "model-00040-of-00113.safetensors",
10
+ "backbone.layers.39.mixer.q_proj.weight": "model-00040-of-00113.safetensors",
11
+ "backbone.layers.39.mixer.v_proj.weight": "model-00040-of-00113.safetensors",
12
+ "backbone.layers.39.norm.weight": "model-00040-of-00113.safetensors"
13
+ }
14
+ }
model-00043-of-00113.json ADDED
The diff for this file is too large to render. See raw diff
 
model-00048-of-00113.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 421762576
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.47.mixer.in_proj.input_scale": "model-00048-of-00113.safetensors",
7
+ "backbone.layers.47.mixer.in_proj.weight_scale": "model-00048-of-00113.safetensors",
8
+ "backbone.layers.47.mixer.out_proj.input_scale": "model-00048-of-00113.safetensors",
9
+ "backbone.layers.47.mixer.out_proj.weight_scale": "model-00048-of-00113.safetensors",
10
+ "backbone.layers.47.mixer.A_log": "model-00048-of-00113.safetensors",
11
+ "backbone.layers.47.mixer.D": "model-00048-of-00113.safetensors",
12
+ "backbone.layers.47.mixer.conv1d.bias": "model-00048-of-00113.safetensors",
13
+ "backbone.layers.47.mixer.conv1d.weight": "model-00048-of-00113.safetensors",
14
+ "backbone.layers.47.mixer.dt_bias": "model-00048-of-00113.safetensors",
15
+ "backbone.layers.47.mixer.norm.weight": "model-00048-of-00113.safetensors",
16
+ "backbone.layers.47.norm.weight": "model-00048-of-00113.safetensors",
17
+ "backbone.layers.47.mixer.in_proj.weight": "model-00048-of-00113.safetensors",
18
+ "backbone.layers.47.mixer.out_proj.weight": "model-00048-of-00113.safetensors"
19
+ }
20
+ }
model-00049-of-00113.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 276840456
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.48.mixer.k_proj.k_scale": "model-00049-of-00113.safetensors",
7
+ "backbone.layers.48.mixer.v_proj.v_scale": "model-00049-of-00113.safetensors",
8
+ "backbone.layers.48.mixer.k_proj.weight": "model-00049-of-00113.safetensors",
9
+ "backbone.layers.48.mixer.o_proj.weight": "model-00049-of-00113.safetensors",
10
+ "backbone.layers.48.mixer.q_proj.weight": "model-00049-of-00113.safetensors",
11
+ "backbone.layers.48.mixer.v_proj.weight": "model-00049-of-00113.safetensors",
12
+ "backbone.layers.48.norm.weight": "model-00049-of-00113.safetensors"
13
+ }
14
+ }
model-00050-of-00113.json ADDED
The diff for this file is too large to render. See raw diff
 
model-00051-of-00113.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 421762576
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.50.mixer.in_proj.input_scale": "model-00051-of-00113.safetensors",
7
+ "backbone.layers.50.mixer.in_proj.weight_scale": "model-00051-of-00113.safetensors",
8
+ "backbone.layers.50.mixer.out_proj.input_scale": "model-00051-of-00113.safetensors",
9
+ "backbone.layers.50.mixer.out_proj.weight_scale": "model-00051-of-00113.safetensors",
10
+ "backbone.layers.50.mixer.A_log": "model-00051-of-00113.safetensors",
11
+ "backbone.layers.50.mixer.D": "model-00051-of-00113.safetensors",
12
+ "backbone.layers.50.mixer.conv1d.bias": "model-00051-of-00113.safetensors",
13
+ "backbone.layers.50.mixer.conv1d.weight": "model-00051-of-00113.safetensors",
14
+ "backbone.layers.50.mixer.dt_bias": "model-00051-of-00113.safetensors",
15
+ "backbone.layers.50.mixer.norm.weight": "model-00051-of-00113.safetensors",
16
+ "backbone.layers.50.norm.weight": "model-00051-of-00113.safetensors",
17
+ "backbone.layers.50.mixer.in_proj.weight": "model-00051-of-00113.safetensors",
18
+ "backbone.layers.50.mixer.out_proj.weight": "model-00051-of-00113.safetensors"
19
+ }
20
+ }
model-00053-of-00113.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 421762576
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.52.mixer.in_proj.input_scale": "model-00053-of-00113.safetensors",
7
+ "backbone.layers.52.mixer.in_proj.weight_scale": "model-00053-of-00113.safetensors",
8
+ "backbone.layers.52.mixer.out_proj.input_scale": "model-00053-of-00113.safetensors",
9
+ "backbone.layers.52.mixer.out_proj.weight_scale": "model-00053-of-00113.safetensors",
10
+ "backbone.layers.52.mixer.A_log": "model-00053-of-00113.safetensors",
11
+ "backbone.layers.52.mixer.D": "model-00053-of-00113.safetensors",
12
+ "backbone.layers.52.mixer.conv1d.bias": "model-00053-of-00113.safetensors",
13
+ "backbone.layers.52.mixer.conv1d.weight": "model-00053-of-00113.safetensors",
14
+ "backbone.layers.52.mixer.dt_bias": "model-00053-of-00113.safetensors",
15
+ "backbone.layers.52.mixer.norm.weight": "model-00053-of-00113.safetensors",
16
+ "backbone.layers.52.norm.weight": "model-00053-of-00113.safetensors",
17
+ "backbone.layers.52.mixer.in_proj.weight": "model-00053-of-00113.safetensors",
18
+ "backbone.layers.52.mixer.out_proj.weight": "model-00053-of-00113.safetensors"
19
+ }
20
+ }
model-00054-of-00113.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f19eb43218749fdaa45daaf4150a8b369606df4c55e3002643f36e3e1edb396
3
+ size 6291991440
model-00058-of-00113.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 276840456
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.57.mixer.k_proj.k_scale": "model-00058-of-00113.safetensors",
7
+ "backbone.layers.57.mixer.v_proj.v_scale": "model-00058-of-00113.safetensors",
8
+ "backbone.layers.57.mixer.k_proj.weight": "model-00058-of-00113.safetensors",
9
+ "backbone.layers.57.mixer.o_proj.weight": "model-00058-of-00113.safetensors",
10
+ "backbone.layers.57.mixer.q_proj.weight": "model-00058-of-00113.safetensors",
11
+ "backbone.layers.57.mixer.v_proj.weight": "model-00058-of-00113.safetensors",
12
+ "backbone.layers.57.norm.weight": "model-00058-of-00113.safetensors"
13
+ }
14
+ }
model-00059-of-00113.json ADDED
The diff for this file is too large to render. See raw diff
 
model-00060-of-00113.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 421762576
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.59.mixer.in_proj.input_scale": "model-00060-of-00113.safetensors",
7
+ "backbone.layers.59.mixer.in_proj.weight_scale": "model-00060-of-00113.safetensors",
8
+ "backbone.layers.59.mixer.out_proj.input_scale": "model-00060-of-00113.safetensors",
9
+ "backbone.layers.59.mixer.out_proj.weight_scale": "model-00060-of-00113.safetensors",
10
+ "backbone.layers.59.mixer.A_log": "model-00060-of-00113.safetensors",
11
+ "backbone.layers.59.mixer.D": "model-00060-of-00113.safetensors",
12
+ "backbone.layers.59.mixer.conv1d.bias": "model-00060-of-00113.safetensors",
13
+ "backbone.layers.59.mixer.conv1d.weight": "model-00060-of-00113.safetensors",
14
+ "backbone.layers.59.mixer.dt_bias": "model-00060-of-00113.safetensors",
15
+ "backbone.layers.59.mixer.norm.weight": "model-00060-of-00113.safetensors",
16
+ "backbone.layers.59.norm.weight": "model-00060-of-00113.safetensors",
17
+ "backbone.layers.59.mixer.in_proj.weight": "model-00060-of-00113.safetensors",
18
+ "backbone.layers.59.mixer.out_proj.weight": "model-00060-of-00113.safetensors"
19
+ }
20
+ }
model-00061-of-00113.json ADDED
The diff for this file is too large to render. See raw diff
 
model-00062-of-00113.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 421762576
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.61.mixer.in_proj.input_scale": "model-00062-of-00113.safetensors",
7
+ "backbone.layers.61.mixer.in_proj.weight_scale": "model-00062-of-00113.safetensors",
8
+ "backbone.layers.61.mixer.out_proj.input_scale": "model-00062-of-00113.safetensors",
9
+ "backbone.layers.61.mixer.out_proj.weight_scale": "model-00062-of-00113.safetensors",
10
+ "backbone.layers.61.mixer.A_log": "model-00062-of-00113.safetensors",
11
+ "backbone.layers.61.mixer.D": "model-00062-of-00113.safetensors",
12
+ "backbone.layers.61.mixer.conv1d.bias": "model-00062-of-00113.safetensors",
13
+ "backbone.layers.61.mixer.conv1d.weight": "model-00062-of-00113.safetensors",
14
+ "backbone.layers.61.mixer.dt_bias": "model-00062-of-00113.safetensors",
15
+ "backbone.layers.61.mixer.norm.weight": "model-00062-of-00113.safetensors",
16
+ "backbone.layers.61.norm.weight": "model-00062-of-00113.safetensors",
17
+ "backbone.layers.61.mixer.in_proj.weight": "model-00062-of-00113.safetensors",
18
+ "backbone.layers.61.mixer.out_proj.weight": "model-00062-of-00113.safetensors"
19
+ }
20
+ }
model-00064-of-00113.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 421762576
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.63.mixer.in_proj.input_scale": "model-00064-of-00113.safetensors",
7
+ "backbone.layers.63.mixer.in_proj.weight_scale": "model-00064-of-00113.safetensors",
8
+ "backbone.layers.63.mixer.out_proj.input_scale": "model-00064-of-00113.safetensors",
9
+ "backbone.layers.63.mixer.out_proj.weight_scale": "model-00064-of-00113.safetensors",
10
+ "backbone.layers.63.mixer.A_log": "model-00064-of-00113.safetensors",
11
+ "backbone.layers.63.mixer.D": "model-00064-of-00113.safetensors",
12
+ "backbone.layers.63.mixer.conv1d.bias": "model-00064-of-00113.safetensors",
13
+ "backbone.layers.63.mixer.conv1d.weight": "model-00064-of-00113.safetensors",
14
+ "backbone.layers.63.mixer.dt_bias": "model-00064-of-00113.safetensors",
15
+ "backbone.layers.63.mixer.norm.weight": "model-00064-of-00113.safetensors",
16
+ "backbone.layers.63.norm.weight": "model-00064-of-00113.safetensors",
17
+ "backbone.layers.63.mixer.in_proj.weight": "model-00064-of-00113.safetensors",
18
+ "backbone.layers.63.mixer.out_proj.weight": "model-00064-of-00113.safetensors"
19
+ }
20
+ }
model-00066-of-00113.json ADDED
The diff for this file is too large to render. See raw diff
 
model-00068-of-00113.json ADDED
The diff for this file is too large to render. See raw diff
 
model-00069-of-00113.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 421762576
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.68.mixer.in_proj.input_scale": "model-00069-of-00113.safetensors",
7
+ "backbone.layers.68.mixer.in_proj.weight_scale": "model-00069-of-00113.safetensors",
8
+ "backbone.layers.68.mixer.out_proj.input_scale": "model-00069-of-00113.safetensors",
9
+ "backbone.layers.68.mixer.out_proj.weight_scale": "model-00069-of-00113.safetensors",
10
+ "backbone.layers.68.mixer.A_log": "model-00069-of-00113.safetensors",
11
+ "backbone.layers.68.mixer.D": "model-00069-of-00113.safetensors",
12
+ "backbone.layers.68.mixer.conv1d.bias": "model-00069-of-00113.safetensors",
13
+ "backbone.layers.68.mixer.conv1d.weight": "model-00069-of-00113.safetensors",
14
+ "backbone.layers.68.mixer.dt_bias": "model-00069-of-00113.safetensors",
15
+ "backbone.layers.68.mixer.norm.weight": "model-00069-of-00113.safetensors",
16
+ "backbone.layers.68.norm.weight": "model-00069-of-00113.safetensors",
17
+ "backbone.layers.68.mixer.in_proj.weight": "model-00069-of-00113.safetensors",
18
+ "backbone.layers.68.mixer.out_proj.weight": "model-00069-of-00113.safetensors"
19
+ }
20
+ }
model-00070-of-00113.json ADDED
The diff for this file is too large to render. See raw diff
 
model-00071-of-00113.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 421762576
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.70.mixer.in_proj.input_scale": "model-00071-of-00113.safetensors",
7
+ "backbone.layers.70.mixer.in_proj.weight_scale": "model-00071-of-00113.safetensors",
8
+ "backbone.layers.70.mixer.out_proj.input_scale": "model-00071-of-00113.safetensors",
9
+ "backbone.layers.70.mixer.out_proj.weight_scale": "model-00071-of-00113.safetensors",
10
+ "backbone.layers.70.mixer.A_log": "model-00071-of-00113.safetensors",
11
+ "backbone.layers.70.mixer.D": "model-00071-of-00113.safetensors",
12
+ "backbone.layers.70.mixer.conv1d.bias": "model-00071-of-00113.safetensors",
13
+ "backbone.layers.70.mixer.conv1d.weight": "model-00071-of-00113.safetensors",
14
+ "backbone.layers.70.mixer.dt_bias": "model-00071-of-00113.safetensors",
15
+ "backbone.layers.70.mixer.norm.weight": "model-00071-of-00113.safetensors",
16
+ "backbone.layers.70.norm.weight": "model-00071-of-00113.safetensors",
17
+ "backbone.layers.70.mixer.in_proj.weight": "model-00071-of-00113.safetensors",
18
+ "backbone.layers.70.mixer.out_proj.weight": "model-00071-of-00113.safetensors"
19
+ }
20
+ }
model-00074-of-00113.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 276840456
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.73.mixer.k_proj.k_scale": "model-00074-of-00113.safetensors",
7
+ "backbone.layers.73.mixer.v_proj.v_scale": "model-00074-of-00113.safetensors",
8
+ "backbone.layers.73.mixer.k_proj.weight": "model-00074-of-00113.safetensors",
9
+ "backbone.layers.73.mixer.o_proj.weight": "model-00074-of-00113.safetensors",
10
+ "backbone.layers.73.mixer.q_proj.weight": "model-00074-of-00113.safetensors",
11
+ "backbone.layers.73.mixer.v_proj.weight": "model-00074-of-00113.safetensors",
12
+ "backbone.layers.73.norm.weight": "model-00074-of-00113.safetensors"
13
+ }
14
+ }
model-00076-of-00113.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 421762576
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.75.mixer.in_proj.input_scale": "model-00076-of-00113.safetensors",
7
+ "backbone.layers.75.mixer.in_proj.weight_scale": "model-00076-of-00113.safetensors",
8
+ "backbone.layers.75.mixer.out_proj.input_scale": "model-00076-of-00113.safetensors",
9
+ "backbone.layers.75.mixer.out_proj.weight_scale": "model-00076-of-00113.safetensors",
10
+ "backbone.layers.75.mixer.A_log": "model-00076-of-00113.safetensors",
11
+ "backbone.layers.75.mixer.D": "model-00076-of-00113.safetensors",
12
+ "backbone.layers.75.mixer.conv1d.bias": "model-00076-of-00113.safetensors",
13
+ "backbone.layers.75.mixer.conv1d.weight": "model-00076-of-00113.safetensors",
14
+ "backbone.layers.75.mixer.dt_bias": "model-00076-of-00113.safetensors",
15
+ "backbone.layers.75.mixer.norm.weight": "model-00076-of-00113.safetensors",
16
+ "backbone.layers.75.norm.weight": "model-00076-of-00113.safetensors",
17
+ "backbone.layers.75.mixer.in_proj.weight": "model-00076-of-00113.safetensors",
18
+ "backbone.layers.75.mixer.out_proj.weight": "model-00076-of-00113.safetensors"
19
+ }
20
+ }
model-00077-of-00113.json ADDED
The diff for this file is too large to render. See raw diff
 
model-00078-of-00113.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 421762576
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.77.mixer.in_proj.input_scale": "model-00078-of-00113.safetensors",
7
+ "backbone.layers.77.mixer.in_proj.weight_scale": "model-00078-of-00113.safetensors",
8
+ "backbone.layers.77.mixer.out_proj.input_scale": "model-00078-of-00113.safetensors",
9
+ "backbone.layers.77.mixer.out_proj.weight_scale": "model-00078-of-00113.safetensors",
10
+ "backbone.layers.77.mixer.A_log": "model-00078-of-00113.safetensors",
11
+ "backbone.layers.77.mixer.D": "model-00078-of-00113.safetensors",
12
+ "backbone.layers.77.mixer.conv1d.bias": "model-00078-of-00113.safetensors",
13
+ "backbone.layers.77.mixer.conv1d.weight": "model-00078-of-00113.safetensors",
14
+ "backbone.layers.77.mixer.dt_bias": "model-00078-of-00113.safetensors",
15
+ "backbone.layers.77.mixer.norm.weight": "model-00078-of-00113.safetensors",
16
+ "backbone.layers.77.norm.weight": "model-00078-of-00113.safetensors",
17
+ "backbone.layers.77.mixer.in_proj.weight": "model-00078-of-00113.safetensors",
18
+ "backbone.layers.77.mixer.out_proj.weight": "model-00078-of-00113.safetensors"
19
+ }
20
+ }
model-00081-of-00113.json ADDED
The diff for this file is too large to render. See raw diff
 
model-00082-of-00113.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 421762576
4
+ },
5
+ "weight_map": {
6
+ "backbone.layers.81.mixer.in_proj.input_scale": "model-00082-of-00113.safetensors",
7
+ "backbone.layers.81.mixer.in_proj.weight_scale": "model-00082-of-00113.safetensors",
8
+ "backbone.layers.81.mixer.out_proj.input_scale": "model-00082-of-00113.safetensors",
9
+ "backbone.layers.81.mixer.out_proj.weight_scale": "model-00082-of-00113.safetensors",
10
+ "backbone.layers.81.mixer.A_log": "model-00082-of-00113.safetensors",
11
+ "backbone.layers.81.mixer.D": "model-00082-of-00113.safetensors",
12
+ "backbone.layers.81.mixer.conv1d.bias": "model-00082-of-00113.safetensors",
13
+ "backbone.layers.81.mixer.conv1d.weight": "model-00082-of-00113.safetensors",
14
+ "backbone.layers.81.mixer.dt_bias": "model-00082-of-00113.safetensors",
15
+ "backbone.layers.81.mixer.norm.weight": "model-00082-of-00113.safetensors",
16
+ "backbone.layers.81.norm.weight": "model-00082-of-00113.safetensors",
17
+ "backbone.layers.81.mixer.in_proj.weight": "model-00082-of-00113.safetensors",
18
+ "backbone.layers.81.mixer.out_proj.weight": "model-00082-of-00113.safetensors"
19
+ }
20
+ }
model-00084-of-00113.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e9f0af97a0734cf76c3c0b0046f13129d0a63d910fec6dcaa2e86fe9be339d0
3
+ size 6291991440