Tacoin commited on
Commit
87ff076
·
verified ·
1 Parent(s): 3307275

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +460 -0
  2. README.md +57 -0
  3. assets/physical-intelligence/libero/norm_stats.json +556 -0
  4. fp16/model.onnx +3 -0
  5. fp16/model.onnx.data +3 -0
  6. fp32/model.onnx +3 -0
  7. fp32/model.onnx.data +3 -0
  8. int4/model.onnx +3 -0
  9. int4/model.onnx.data +3 -0
  10. int8/model.onnx +3 -0
  11. int8/model.onnx.data +3 -0
  12. model.action_in_proj.weight +3 -0
  13. model.action_out_proj.weight +3 -0
  14. model.paligemma_with_expert.gemma_expert.model.layers.0.input_layernorm.dense.bias +0 -0
  15. model.paligemma_with_expert.gemma_expert.model.layers.0.input_layernorm.dense.weight +3 -0
  16. model.paligemma_with_expert.gemma_expert.model.layers.0.mlp.down_proj.weight +3 -0
  17. model.paligemma_with_expert.gemma_expert.model.layers.0.mlp.gate_proj.weight +3 -0
  18. model.paligemma_with_expert.gemma_expert.model.layers.0.mlp.up_proj.weight +3 -0
  19. model.paligemma_with_expert.gemma_expert.model.layers.0.post_attention_layernorm.dense.weight +3 -0
  20. model.paligemma_with_expert.gemma_expert.model.layers.0.self_attn.k_proj.weight +3 -0
  21. model.paligemma_with_expert.gemma_expert.model.layers.0.self_attn.o_proj.weight +3 -0
  22. model.paligemma_with_expert.gemma_expert.model.layers.0.self_attn.q_proj.weight +3 -0
  23. model.paligemma_with_expert.gemma_expert.model.layers.0.self_attn.v_proj.weight +3 -0
  24. model.paligemma_with_expert.gemma_expert.model.layers.1.input_layernorm.dense.weight +3 -0
  25. model.paligemma_with_expert.gemma_expert.model.layers.1.mlp.down_proj.weight +3 -0
  26. model.paligemma_with_expert.gemma_expert.model.layers.1.mlp.gate_proj.weight +3 -0
  27. model.paligemma_with_expert.gemma_expert.model.layers.1.mlp.up_proj.weight +3 -0
  28. model.paligemma_with_expert.gemma_expert.model.layers.1.post_attention_layernorm.dense.weight +3 -0
  29. model.paligemma_with_expert.gemma_expert.model.layers.1.self_attn.k_proj.weight +3 -0
  30. model.paligemma_with_expert.gemma_expert.model.layers.1.self_attn.o_proj.weight +3 -0
  31. model.paligemma_with_expert.gemma_expert.model.layers.1.self_attn.q_proj.weight +3 -0
  32. model.paligemma_with_expert.gemma_expert.model.layers.1.self_attn.v_proj.weight +3 -0
  33. model.paligemma_with_expert.gemma_expert.model.layers.10.input_layernorm.dense.weight +3 -0
  34. model.paligemma_with_expert.gemma_expert.model.layers.10.mlp.down_proj.weight +3 -0
  35. model.paligemma_with_expert.gemma_expert.model.layers.10.mlp.gate_proj.weight +3 -0
  36. model.paligemma_with_expert.gemma_expert.model.layers.10.mlp.up_proj.weight +3 -0
  37. model.paligemma_with_expert.gemma_expert.model.layers.10.post_attention_layernorm.dense.weight +3 -0
  38. model.paligemma_with_expert.gemma_expert.model.layers.10.self_attn.k_proj.weight +3 -0
  39. model.paligemma_with_expert.gemma_expert.model.layers.10.self_attn.o_proj.weight +3 -0
  40. model.paligemma_with_expert.gemma_expert.model.layers.10.self_attn.q_proj.weight +3 -0
  41. model.paligemma_with_expert.gemma_expert.model.layers.10.self_attn.v_proj.weight +3 -0
  42. model.paligemma_with_expert.gemma_expert.model.layers.11.input_layernorm.dense.weight +3 -0
  43. model.paligemma_with_expert.gemma_expert.model.layers.11.mlp.down_proj.weight +3 -0
  44. model.paligemma_with_expert.gemma_expert.model.layers.11.mlp.gate_proj.weight +3 -0
  45. model.paligemma_with_expert.gemma_expert.model.layers.11.mlp.up_proj.weight +3 -0
  46. model.paligemma_with_expert.gemma_expert.model.layers.11.post_attention_layernorm.dense.weight +3 -0
  47. model.paligemma_with_expert.gemma_expert.model.layers.11.self_attn.k_proj.weight +3 -0
  48. model.paligemma_with_expert.gemma_expert.model.layers.11.self_attn.o_proj.weight +3 -0
  49. model.paligemma_with_expert.gemma_expert.model.layers.11.self_attn.q_proj.weight +3 -0
  50. model.paligemma_with_expert.gemma_expert.model.layers.11.self_attn.v_proj.weight +3 -0
.gitattributes CHANGED
@@ -33,3 +33,463 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ fp16/model.onnx.data filter=lfs diff=lfs merge=lfs -text
37
+ fp32/model.onnx.data filter=lfs diff=lfs merge=lfs -text
38
+ int4/model.onnx.data filter=lfs diff=lfs merge=lfs -text
39
+ int8/model.onnx.data filter=lfs diff=lfs merge=lfs -text
40
+ model.action_in_proj.weight filter=lfs diff=lfs merge=lfs -text
41
+ model.action_out_proj.weight filter=lfs diff=lfs merge=lfs -text
42
+ model.paligemma_with_expert.gemma_expert.model.layers.0.input_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
43
+ model.paligemma_with_expert.gemma_expert.model.layers.0.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
44
+ model.paligemma_with_expert.gemma_expert.model.layers.0.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
45
+ model.paligemma_with_expert.gemma_expert.model.layers.0.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
46
+ model.paligemma_with_expert.gemma_expert.model.layers.0.post_attention_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
47
+ model.paligemma_with_expert.gemma_expert.model.layers.0.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
48
+ model.paligemma_with_expert.gemma_expert.model.layers.0.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
49
+ model.paligemma_with_expert.gemma_expert.model.layers.0.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
50
+ model.paligemma_with_expert.gemma_expert.model.layers.0.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
51
+ model.paligemma_with_expert.gemma_expert.model.layers.1.input_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
52
+ model.paligemma_with_expert.gemma_expert.model.layers.1.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
53
+ model.paligemma_with_expert.gemma_expert.model.layers.1.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
54
+ model.paligemma_with_expert.gemma_expert.model.layers.1.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
55
+ model.paligemma_with_expert.gemma_expert.model.layers.1.post_attention_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
56
+ model.paligemma_with_expert.gemma_expert.model.layers.1.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
57
+ model.paligemma_with_expert.gemma_expert.model.layers.1.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
58
+ model.paligemma_with_expert.gemma_expert.model.layers.1.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
59
+ model.paligemma_with_expert.gemma_expert.model.layers.1.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
60
+ model.paligemma_with_expert.gemma_expert.model.layers.10.input_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
61
+ model.paligemma_with_expert.gemma_expert.model.layers.10.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
62
+ model.paligemma_with_expert.gemma_expert.model.layers.10.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
63
+ model.paligemma_with_expert.gemma_expert.model.layers.10.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
64
+ model.paligemma_with_expert.gemma_expert.model.layers.10.post_attention_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
65
+ model.paligemma_with_expert.gemma_expert.model.layers.10.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
66
+ model.paligemma_with_expert.gemma_expert.model.layers.10.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
67
+ model.paligemma_with_expert.gemma_expert.model.layers.10.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
68
+ model.paligemma_with_expert.gemma_expert.model.layers.10.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
69
+ model.paligemma_with_expert.gemma_expert.model.layers.11.input_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
70
+ model.paligemma_with_expert.gemma_expert.model.layers.11.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
71
+ model.paligemma_with_expert.gemma_expert.model.layers.11.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
72
+ model.paligemma_with_expert.gemma_expert.model.layers.11.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
73
+ model.paligemma_with_expert.gemma_expert.model.layers.11.post_attention_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
74
+ model.paligemma_with_expert.gemma_expert.model.layers.11.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
75
+ model.paligemma_with_expert.gemma_expert.model.layers.11.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
76
+ model.paligemma_with_expert.gemma_expert.model.layers.11.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
77
+ model.paligemma_with_expert.gemma_expert.model.layers.11.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
78
+ model.paligemma_with_expert.gemma_expert.model.layers.12.input_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
79
+ model.paligemma_with_expert.gemma_expert.model.layers.12.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
80
+ model.paligemma_with_expert.gemma_expert.model.layers.12.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
81
+ model.paligemma_with_expert.gemma_expert.model.layers.12.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
82
+ model.paligemma_with_expert.gemma_expert.model.layers.12.post_attention_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
83
+ model.paligemma_with_expert.gemma_expert.model.layers.12.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
84
+ model.paligemma_with_expert.gemma_expert.model.layers.12.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
85
+ model.paligemma_with_expert.gemma_expert.model.layers.12.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
86
+ model.paligemma_with_expert.gemma_expert.model.layers.12.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
87
+ model.paligemma_with_expert.gemma_expert.model.layers.13.input_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
88
+ model.paligemma_with_expert.gemma_expert.model.layers.13.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
89
+ model.paligemma_with_expert.gemma_expert.model.layers.13.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
90
+ model.paligemma_with_expert.gemma_expert.model.layers.13.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
91
+ model.paligemma_with_expert.gemma_expert.model.layers.13.post_attention_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
92
+ model.paligemma_with_expert.gemma_expert.model.layers.13.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
93
+ model.paligemma_with_expert.gemma_expert.model.layers.13.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
94
+ model.paligemma_with_expert.gemma_expert.model.layers.13.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
95
+ model.paligemma_with_expert.gemma_expert.model.layers.13.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
96
+ model.paligemma_with_expert.gemma_expert.model.layers.14.input_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
97
+ model.paligemma_with_expert.gemma_expert.model.layers.14.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
98
+ model.paligemma_with_expert.gemma_expert.model.layers.14.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
99
+ model.paligemma_with_expert.gemma_expert.model.layers.14.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
100
+ model.paligemma_with_expert.gemma_expert.model.layers.14.post_attention_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
101
+ model.paligemma_with_expert.gemma_expert.model.layers.14.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
102
+ model.paligemma_with_expert.gemma_expert.model.layers.14.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
103
+ model.paligemma_with_expert.gemma_expert.model.layers.14.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
104
+ model.paligemma_with_expert.gemma_expert.model.layers.14.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
105
+ model.paligemma_with_expert.gemma_expert.model.layers.15.input_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
106
+ model.paligemma_with_expert.gemma_expert.model.layers.15.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
107
+ model.paligemma_with_expert.gemma_expert.model.layers.15.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
108
+ model.paligemma_with_expert.gemma_expert.model.layers.15.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
109
+ model.paligemma_with_expert.gemma_expert.model.layers.15.post_attention_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
110
+ model.paligemma_with_expert.gemma_expert.model.layers.15.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
111
+ model.paligemma_with_expert.gemma_expert.model.layers.15.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
112
+ model.paligemma_with_expert.gemma_expert.model.layers.15.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
113
+ model.paligemma_with_expert.gemma_expert.model.layers.15.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
114
+ model.paligemma_with_expert.gemma_expert.model.layers.16.input_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
115
+ model.paligemma_with_expert.gemma_expert.model.layers.16.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
116
+ model.paligemma_with_expert.gemma_expert.model.layers.16.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
117
+ model.paligemma_with_expert.gemma_expert.model.layers.16.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
118
+ model.paligemma_with_expert.gemma_expert.model.layers.16.post_attention_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
119
+ model.paligemma_with_expert.gemma_expert.model.layers.16.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
120
+ model.paligemma_with_expert.gemma_expert.model.layers.16.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
121
+ model.paligemma_with_expert.gemma_expert.model.layers.16.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
122
+ model.paligemma_with_expert.gemma_expert.model.layers.16.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
123
+ model.paligemma_with_expert.gemma_expert.model.layers.17.input_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
124
+ model.paligemma_with_expert.gemma_expert.model.layers.17.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
125
+ model.paligemma_with_expert.gemma_expert.model.layers.17.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
126
+ model.paligemma_with_expert.gemma_expert.model.layers.17.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
127
+ model.paligemma_with_expert.gemma_expert.model.layers.17.post_attention_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
128
+ model.paligemma_with_expert.gemma_expert.model.layers.17.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
129
+ model.paligemma_with_expert.gemma_expert.model.layers.17.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
130
+ model.paligemma_with_expert.gemma_expert.model.layers.17.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
131
+ model.paligemma_with_expert.gemma_expert.model.layers.17.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
132
+ model.paligemma_with_expert.gemma_expert.model.layers.2.input_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
133
+ model.paligemma_with_expert.gemma_expert.model.layers.2.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
134
+ model.paligemma_with_expert.gemma_expert.model.layers.2.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
135
+ model.paligemma_with_expert.gemma_expert.model.layers.2.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
136
+ model.paligemma_with_expert.gemma_expert.model.layers.2.post_attention_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
137
+ model.paligemma_with_expert.gemma_expert.model.layers.2.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
138
+ model.paligemma_with_expert.gemma_expert.model.layers.2.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
139
+ model.paligemma_with_expert.gemma_expert.model.layers.2.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
140
+ model.paligemma_with_expert.gemma_expert.model.layers.2.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
141
+ model.paligemma_with_expert.gemma_expert.model.layers.3.input_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
142
+ model.paligemma_with_expert.gemma_expert.model.layers.3.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
143
+ model.paligemma_with_expert.gemma_expert.model.layers.3.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
144
+ model.paligemma_with_expert.gemma_expert.model.layers.3.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
145
+ model.paligemma_with_expert.gemma_expert.model.layers.3.post_attention_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
146
+ model.paligemma_with_expert.gemma_expert.model.layers.3.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
147
+ model.paligemma_with_expert.gemma_expert.model.layers.3.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
148
+ model.paligemma_with_expert.gemma_expert.model.layers.3.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
149
+ model.paligemma_with_expert.gemma_expert.model.layers.3.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
150
+ model.paligemma_with_expert.gemma_expert.model.layers.4.input_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
151
+ model.paligemma_with_expert.gemma_expert.model.layers.4.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
152
+ model.paligemma_with_expert.gemma_expert.model.layers.4.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
153
+ model.paligemma_with_expert.gemma_expert.model.layers.4.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
154
+ model.paligemma_with_expert.gemma_expert.model.layers.4.post_attention_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
155
+ model.paligemma_with_expert.gemma_expert.model.layers.4.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
156
+ model.paligemma_with_expert.gemma_expert.model.layers.4.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
157
+ model.paligemma_with_expert.gemma_expert.model.layers.4.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
158
+ model.paligemma_with_expert.gemma_expert.model.layers.4.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
159
+ model.paligemma_with_expert.gemma_expert.model.layers.5.input_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
160
+ model.paligemma_with_expert.gemma_expert.model.layers.5.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
161
+ model.paligemma_with_expert.gemma_expert.model.layers.5.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
162
+ model.paligemma_with_expert.gemma_expert.model.layers.5.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
163
+ model.paligemma_with_expert.gemma_expert.model.layers.5.post_attention_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
164
+ model.paligemma_with_expert.gemma_expert.model.layers.5.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
165
+ model.paligemma_with_expert.gemma_expert.model.layers.5.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
166
+ model.paligemma_with_expert.gemma_expert.model.layers.5.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
167
+ model.paligemma_with_expert.gemma_expert.model.layers.5.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
168
+ model.paligemma_with_expert.gemma_expert.model.layers.6.input_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
169
+ model.paligemma_with_expert.gemma_expert.model.layers.6.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
170
+ model.paligemma_with_expert.gemma_expert.model.layers.6.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
171
+ model.paligemma_with_expert.gemma_expert.model.layers.6.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
172
+ model.paligemma_with_expert.gemma_expert.model.layers.6.post_attention_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
173
+ model.paligemma_with_expert.gemma_expert.model.layers.6.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
174
+ model.paligemma_with_expert.gemma_expert.model.layers.6.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
175
+ model.paligemma_with_expert.gemma_expert.model.layers.6.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
176
+ model.paligemma_with_expert.gemma_expert.model.layers.6.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
177
+ model.paligemma_with_expert.gemma_expert.model.layers.7.input_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
178
+ model.paligemma_with_expert.gemma_expert.model.layers.7.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
179
+ model.paligemma_with_expert.gemma_expert.model.layers.7.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
180
+ model.paligemma_with_expert.gemma_expert.model.layers.7.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
181
+ model.paligemma_with_expert.gemma_expert.model.layers.7.post_attention_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
182
+ model.paligemma_with_expert.gemma_expert.model.layers.7.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
183
+ model.paligemma_with_expert.gemma_expert.model.layers.7.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
184
+ model.paligemma_with_expert.gemma_expert.model.layers.7.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
185
+ model.paligemma_with_expert.gemma_expert.model.layers.7.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
186
+ model.paligemma_with_expert.gemma_expert.model.layers.8.input_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
187
+ model.paligemma_with_expert.gemma_expert.model.layers.8.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
188
+ model.paligemma_with_expert.gemma_expert.model.layers.8.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
189
+ model.paligemma_with_expert.gemma_expert.model.layers.8.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
190
+ model.paligemma_with_expert.gemma_expert.model.layers.8.post_attention_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
191
+ model.paligemma_with_expert.gemma_expert.model.layers.8.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
192
+ model.paligemma_with_expert.gemma_expert.model.layers.8.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
193
+ model.paligemma_with_expert.gemma_expert.model.layers.8.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
194
+ model.paligemma_with_expert.gemma_expert.model.layers.8.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
195
+ model.paligemma_with_expert.gemma_expert.model.layers.9.input_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
196
+ model.paligemma_with_expert.gemma_expert.model.layers.9.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
197
+ model.paligemma_with_expert.gemma_expert.model.layers.9.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
198
+ model.paligemma_with_expert.gemma_expert.model.layers.9.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
199
+ model.paligemma_with_expert.gemma_expert.model.layers.9.post_attention_layernorm.dense.weight filter=lfs diff=lfs merge=lfs -text
200
+ model.paligemma_with_expert.gemma_expert.model.layers.9.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
201
+ model.paligemma_with_expert.gemma_expert.model.layers.9.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
202
+ model.paligemma_with_expert.gemma_expert.model.layers.9.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
203
+ model.paligemma_with_expert.gemma_expert.model.layers.9.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
204
+ model.paligemma_with_expert.gemma_expert.model.norm.dense.weight filter=lfs diff=lfs merge=lfs -text
205
+ model.paligemma_with_expert.paligemma.model.language_model.embed_tokens.weight filter=lfs diff=lfs merge=lfs -text
206
+ model.paligemma_with_expert.paligemma.model.language_model.layers.0.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
207
+ model.paligemma_with_expert.paligemma.model.language_model.layers.0.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
208
+ model.paligemma_with_expert.paligemma.model.language_model.layers.0.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
209
+ model.paligemma_with_expert.paligemma.model.language_model.layers.0.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
210
+ model.paligemma_with_expert.paligemma.model.language_model.layers.0.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
211
+ model.paligemma_with_expert.paligemma.model.language_model.layers.0.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
212
+ model.paligemma_with_expert.paligemma.model.language_model.layers.0.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
213
+ model.paligemma_with_expert.paligemma.model.language_model.layers.1.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
214
+ model.paligemma_with_expert.paligemma.model.language_model.layers.1.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
215
+ model.paligemma_with_expert.paligemma.model.language_model.layers.1.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
216
+ model.paligemma_with_expert.paligemma.model.language_model.layers.1.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
217
+ model.paligemma_with_expert.paligemma.model.language_model.layers.1.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
218
+ model.paligemma_with_expert.paligemma.model.language_model.layers.1.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
219
+ model.paligemma_with_expert.paligemma.model.language_model.layers.1.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
220
+ model.paligemma_with_expert.paligemma.model.language_model.layers.10.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
221
+ model.paligemma_with_expert.paligemma.model.language_model.layers.10.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
222
+ model.paligemma_with_expert.paligemma.model.language_model.layers.10.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
223
+ model.paligemma_with_expert.paligemma.model.language_model.layers.10.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
224
+ model.paligemma_with_expert.paligemma.model.language_model.layers.10.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
225
+ model.paligemma_with_expert.paligemma.model.language_model.layers.10.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
226
+ model.paligemma_with_expert.paligemma.model.language_model.layers.10.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
227
+ model.paligemma_with_expert.paligemma.model.language_model.layers.11.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
228
+ model.paligemma_with_expert.paligemma.model.language_model.layers.11.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
229
+ model.paligemma_with_expert.paligemma.model.language_model.layers.11.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
230
+ model.paligemma_with_expert.paligemma.model.language_model.layers.11.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
231
+ model.paligemma_with_expert.paligemma.model.language_model.layers.11.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
232
+ model.paligemma_with_expert.paligemma.model.language_model.layers.11.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
233
+ model.paligemma_with_expert.paligemma.model.language_model.layers.11.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
234
+ model.paligemma_with_expert.paligemma.model.language_model.layers.12.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
235
+ model.paligemma_with_expert.paligemma.model.language_model.layers.12.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
236
+ model.paligemma_with_expert.paligemma.model.language_model.layers.12.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
237
+ model.paligemma_with_expert.paligemma.model.language_model.layers.12.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
238
+ model.paligemma_with_expert.paligemma.model.language_model.layers.12.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
239
+ model.paligemma_with_expert.paligemma.model.language_model.layers.12.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
240
+ model.paligemma_with_expert.paligemma.model.language_model.layers.12.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
241
+ model.paligemma_with_expert.paligemma.model.language_model.layers.13.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
242
+ model.paligemma_with_expert.paligemma.model.language_model.layers.13.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
243
+ model.paligemma_with_expert.paligemma.model.language_model.layers.13.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
244
+ model.paligemma_with_expert.paligemma.model.language_model.layers.13.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
245
+ model.paligemma_with_expert.paligemma.model.language_model.layers.13.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
246
+ model.paligemma_with_expert.paligemma.model.language_model.layers.13.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
247
+ model.paligemma_with_expert.paligemma.model.language_model.layers.13.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
248
+ model.paligemma_with_expert.paligemma.model.language_model.layers.14.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
249
+ model.paligemma_with_expert.paligemma.model.language_model.layers.14.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
250
+ model.paligemma_with_expert.paligemma.model.language_model.layers.14.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
251
+ model.paligemma_with_expert.paligemma.model.language_model.layers.14.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
252
+ model.paligemma_with_expert.paligemma.model.language_model.layers.14.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
253
+ model.paligemma_with_expert.paligemma.model.language_model.layers.14.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
254
+ model.paligemma_with_expert.paligemma.model.language_model.layers.14.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
255
+ model.paligemma_with_expert.paligemma.model.language_model.layers.15.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
256
+ model.paligemma_with_expert.paligemma.model.language_model.layers.15.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
257
+ model.paligemma_with_expert.paligemma.model.language_model.layers.15.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
258
+ model.paligemma_with_expert.paligemma.model.language_model.layers.15.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
259
+ model.paligemma_with_expert.paligemma.model.language_model.layers.15.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
260
+ model.paligemma_with_expert.paligemma.model.language_model.layers.15.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
261
+ model.paligemma_with_expert.paligemma.model.language_model.layers.15.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
262
+ model.paligemma_with_expert.paligemma.model.language_model.layers.16.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
263
+ model.paligemma_with_expert.paligemma.model.language_model.layers.16.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
264
+ model.paligemma_with_expert.paligemma.model.language_model.layers.16.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
265
+ model.paligemma_with_expert.paligemma.model.language_model.layers.16.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
266
+ model.paligemma_with_expert.paligemma.model.language_model.layers.16.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
267
+ model.paligemma_with_expert.paligemma.model.language_model.layers.16.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
268
+ model.paligemma_with_expert.paligemma.model.language_model.layers.16.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
269
+ model.paligemma_with_expert.paligemma.model.language_model.layers.17.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
270
+ model.paligemma_with_expert.paligemma.model.language_model.layers.17.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
271
+ model.paligemma_with_expert.paligemma.model.language_model.layers.2.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
272
+ model.paligemma_with_expert.paligemma.model.language_model.layers.2.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
273
+ model.paligemma_with_expert.paligemma.model.language_model.layers.2.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
274
+ model.paligemma_with_expert.paligemma.model.language_model.layers.2.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
275
+ model.paligemma_with_expert.paligemma.model.language_model.layers.2.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
276
+ model.paligemma_with_expert.paligemma.model.language_model.layers.2.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
277
+ model.paligemma_with_expert.paligemma.model.language_model.layers.2.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
278
+ model.paligemma_with_expert.paligemma.model.language_model.layers.3.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
279
+ model.paligemma_with_expert.paligemma.model.language_model.layers.3.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
280
+ model.paligemma_with_expert.paligemma.model.language_model.layers.3.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
281
+ model.paligemma_with_expert.paligemma.model.language_model.layers.3.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
282
+ model.paligemma_with_expert.paligemma.model.language_model.layers.3.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
283
+ model.paligemma_with_expert.paligemma.model.language_model.layers.3.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
284
+ model.paligemma_with_expert.paligemma.model.language_model.layers.3.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
285
+ model.paligemma_with_expert.paligemma.model.language_model.layers.4.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
286
+ model.paligemma_with_expert.paligemma.model.language_model.layers.4.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
287
+ model.paligemma_with_expert.paligemma.model.language_model.layers.4.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
288
+ model.paligemma_with_expert.paligemma.model.language_model.layers.4.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
289
+ model.paligemma_with_expert.paligemma.model.language_model.layers.4.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
290
+ model.paligemma_with_expert.paligemma.model.language_model.layers.4.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
291
+ model.paligemma_with_expert.paligemma.model.language_model.layers.4.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
292
+ model.paligemma_with_expert.paligemma.model.language_model.layers.5.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
293
+ model.paligemma_with_expert.paligemma.model.language_model.layers.5.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
294
+ model.paligemma_with_expert.paligemma.model.language_model.layers.5.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
295
+ model.paligemma_with_expert.paligemma.model.language_model.layers.5.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
296
+ model.paligemma_with_expert.paligemma.model.language_model.layers.5.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
297
+ model.paligemma_with_expert.paligemma.model.language_model.layers.5.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
298
+ model.paligemma_with_expert.paligemma.model.language_model.layers.5.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
299
+ model.paligemma_with_expert.paligemma.model.language_model.layers.6.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
300
+ model.paligemma_with_expert.paligemma.model.language_model.layers.6.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
301
+ model.paligemma_with_expert.paligemma.model.language_model.layers.6.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
302
+ model.paligemma_with_expert.paligemma.model.language_model.layers.6.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
303
+ model.paligemma_with_expert.paligemma.model.language_model.layers.6.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
304
+ model.paligemma_with_expert.paligemma.model.language_model.layers.6.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
305
+ model.paligemma_with_expert.paligemma.model.language_model.layers.6.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
306
+ model.paligemma_with_expert.paligemma.model.language_model.layers.7.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
307
+ model.paligemma_with_expert.paligemma.model.language_model.layers.7.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
308
+ model.paligemma_with_expert.paligemma.model.language_model.layers.7.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
309
+ model.paligemma_with_expert.paligemma.model.language_model.layers.7.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
310
+ model.paligemma_with_expert.paligemma.model.language_model.layers.7.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
311
+ model.paligemma_with_expert.paligemma.model.language_model.layers.7.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
312
+ model.paligemma_with_expert.paligemma.model.language_model.layers.7.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
313
+ model.paligemma_with_expert.paligemma.model.language_model.layers.8.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
314
+ model.paligemma_with_expert.paligemma.model.language_model.layers.8.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
315
+ model.paligemma_with_expert.paligemma.model.language_model.layers.8.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
316
+ model.paligemma_with_expert.paligemma.model.language_model.layers.8.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
317
+ model.paligemma_with_expert.paligemma.model.language_model.layers.8.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
318
+ model.paligemma_with_expert.paligemma.model.language_model.layers.8.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
319
+ model.paligemma_with_expert.paligemma.model.language_model.layers.8.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
320
+ model.paligemma_with_expert.paligemma.model.language_model.layers.9.mlp.down_proj.weight filter=lfs diff=lfs merge=lfs -text
321
+ model.paligemma_with_expert.paligemma.model.language_model.layers.9.mlp.gate_proj.weight filter=lfs diff=lfs merge=lfs -text
322
+ model.paligemma_with_expert.paligemma.model.language_model.layers.9.mlp.up_proj.weight filter=lfs diff=lfs merge=lfs -text
323
+ model.paligemma_with_expert.paligemma.model.language_model.layers.9.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
324
+ model.paligemma_with_expert.paligemma.model.language_model.layers.9.self_attn.o_proj.weight filter=lfs diff=lfs merge=lfs -text
325
+ model.paligemma_with_expert.paligemma.model.language_model.layers.9.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
326
+ model.paligemma_with_expert.paligemma.model.language_model.layers.9.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
327
+ model.paligemma_with_expert.paligemma.model.multi_modal_projector.linear.weight filter=lfs diff=lfs merge=lfs -text
328
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.embeddings.patch_embedding.weight filter=lfs diff=lfs merge=lfs -text
329
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.embeddings.position_embedding.weight filter=lfs diff=lfs merge=lfs -text
330
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight filter=lfs diff=lfs merge=lfs -text
331
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight filter=lfs diff=lfs merge=lfs -text
332
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
333
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight filter=lfs diff=lfs merge=lfs -text
334
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
335
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
336
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight filter=lfs diff=lfs merge=lfs -text
337
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight filter=lfs diff=lfs merge=lfs -text
338
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
339
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight filter=lfs diff=lfs merge=lfs -text
340
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
341
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
342
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight filter=lfs diff=lfs merge=lfs -text
343
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight filter=lfs diff=lfs merge=lfs -text
344
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
345
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight filter=lfs diff=lfs merge=lfs -text
346
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
347
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
348
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight filter=lfs diff=lfs merge=lfs -text
349
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight filter=lfs diff=lfs merge=lfs -text
350
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
351
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight filter=lfs diff=lfs merge=lfs -text
352
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
353
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
354
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight filter=lfs diff=lfs merge=lfs -text
355
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight filter=lfs diff=lfs merge=lfs -text
356
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
357
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight filter=lfs diff=lfs merge=lfs -text
358
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
359
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
360
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight filter=lfs diff=lfs merge=lfs -text
361
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight filter=lfs diff=lfs merge=lfs -text
362
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
363
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight filter=lfs diff=lfs merge=lfs -text
364
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
365
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
366
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight filter=lfs diff=lfs merge=lfs -text
367
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight filter=lfs diff=lfs merge=lfs -text
368
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
369
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight filter=lfs diff=lfs merge=lfs -text
370
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
371
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
372
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight filter=lfs diff=lfs merge=lfs -text
373
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight filter=lfs diff=lfs merge=lfs -text
374
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
375
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight filter=lfs diff=lfs merge=lfs -text
376
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
377
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
378
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight filter=lfs diff=lfs merge=lfs -text
379
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight filter=lfs diff=lfs merge=lfs -text
380
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
381
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight filter=lfs diff=lfs merge=lfs -text
382
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
383
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
384
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight filter=lfs diff=lfs merge=lfs -text
385
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight filter=lfs diff=lfs merge=lfs -text
386
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
387
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight filter=lfs diff=lfs merge=lfs -text
388
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
389
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
390
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight filter=lfs diff=lfs merge=lfs -text
391
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight filter=lfs diff=lfs merge=lfs -text
392
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
393
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight filter=lfs diff=lfs merge=lfs -text
394
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
395
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
396
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight filter=lfs diff=lfs merge=lfs -text
397
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight filter=lfs diff=lfs merge=lfs -text
398
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
399
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight filter=lfs diff=lfs merge=lfs -text
400
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
401
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
402
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight filter=lfs diff=lfs merge=lfs -text
403
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight filter=lfs diff=lfs merge=lfs -text
404
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
405
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight filter=lfs diff=lfs merge=lfs -text
406
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
407
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
408
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight filter=lfs diff=lfs merge=lfs -text
409
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight filter=lfs diff=lfs merge=lfs -text
410
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
411
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight filter=lfs diff=lfs merge=lfs -text
412
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
413
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
414
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight filter=lfs diff=lfs merge=lfs -text
415
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight filter=lfs diff=lfs merge=lfs -text
416
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
417
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight filter=lfs diff=lfs merge=lfs -text
418
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
419
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
420
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight filter=lfs diff=lfs merge=lfs -text
421
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight filter=lfs diff=lfs merge=lfs -text
422
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
423
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight filter=lfs diff=lfs merge=lfs -text
424
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
425
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
426
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight filter=lfs diff=lfs merge=lfs -text
427
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight filter=lfs diff=lfs merge=lfs -text
428
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
429
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight filter=lfs diff=lfs merge=lfs -text
430
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
431
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
432
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight filter=lfs diff=lfs merge=lfs -text
433
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight filter=lfs diff=lfs merge=lfs -text
434
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
435
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight filter=lfs diff=lfs merge=lfs -text
436
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
437
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
438
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight filter=lfs diff=lfs merge=lfs -text
439
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight filter=lfs diff=lfs merge=lfs -text
440
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
441
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight filter=lfs diff=lfs merge=lfs -text
442
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
443
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
444
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight filter=lfs diff=lfs merge=lfs -text
445
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight filter=lfs diff=lfs merge=lfs -text
446
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
447
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight filter=lfs diff=lfs merge=lfs -text
448
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
449
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
450
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight filter=lfs diff=lfs merge=lfs -text
451
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight filter=lfs diff=lfs merge=lfs -text
452
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
453
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight filter=lfs diff=lfs merge=lfs -text
454
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
455
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
456
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight filter=lfs diff=lfs merge=lfs -text
457
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight filter=lfs diff=lfs merge=lfs -text
458
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
459
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight filter=lfs diff=lfs merge=lfs -text
460
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
461
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
462
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight filter=lfs diff=lfs merge=lfs -text
463
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight filter=lfs diff=lfs merge=lfs -text
464
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
465
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight filter=lfs diff=lfs merge=lfs -text
466
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
467
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
468
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight filter=lfs diff=lfs merge=lfs -text
469
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight filter=lfs diff=lfs merge=lfs -text
470
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
471
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight filter=lfs diff=lfs merge=lfs -text
472
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
473
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
474
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight filter=lfs diff=lfs merge=lfs -text
475
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight filter=lfs diff=lfs merge=lfs -text
476
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
477
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight filter=lfs diff=lfs merge=lfs -text
478
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
479
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
480
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight filter=lfs diff=lfs merge=lfs -text
481
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight filter=lfs diff=lfs merge=lfs -text
482
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
483
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight filter=lfs diff=lfs merge=lfs -text
484
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
485
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
486
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight filter=lfs diff=lfs merge=lfs -text
487
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight filter=lfs diff=lfs merge=lfs -text
488
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight filter=lfs diff=lfs merge=lfs -text
489
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight filter=lfs diff=lfs merge=lfs -text
490
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight filter=lfs diff=lfs merge=lfs -text
491
+ model.paligemma_with_expert.paligemma.model.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight filter=lfs diff=lfs merge=lfs -text
492
+ model.time_mlp_in.weight filter=lfs diff=lfs merge=lfs -text
493
+ model.time_mlp_out.weight filter=lfs diff=lfs merge=lfs -text
494
+ nvfp4/model.onnx.data filter=lfs diff=lfs merge=lfs -text
495
+ nvfp8/model.onnx.data filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - onnx
5
+ - robotics
6
+ - openpi
7
+ - jetson-thor
8
+ - quantization
9
+ ---
10
+
11
+ # OpenPi Pi0.5 Libero ONNX Exports for Jetson Thor
12
+
13
+ This repository contains ONNX exports of the OpenPi Pi0.5 Libero model, optimized for Nvidia Jetson Thor (Blackwell).
14
+
15
+ ## Models Included
16
+
17
+ All models are exported with their external data files consolidated.
18
+
19
+ | Format | Path | Size | Description |
20
+ | :--- | :--- | :--- | :--- |
21
+ | **FP32** | `fp32/` | ~13GB | Full precision FP32 export. |
22
+ | **FP16** | `fp16/` | ~6.5GB | True Float32 -> Float16 converted model. Recommended for general GPU use. |
23
+ | **NVFP8**| `nvfp8/`| ~13GB | **NVIDIA FP8** Quantized (FakeQuant). Optimized for Blackwell Transformer Engine. |
24
+ | **NVFP4**| `nvfp4/`| ~13GB | **NVIDIA FP4** Quantized (FakeQuant). Optimized for Blackwell Transformer Engine. |
25
+ | **INT8** | `int8/` | ~13GB | Standard INT8 Quantized (FakeQuant). |
26
+ | **INT4** | `int4/` | ~13GB | INT4 Blockwise Quantized (FakeQuant). |
27
+
28
+ **Note**: The quantized models (INT8/4, NVFP8/4) are exported using `modelopt` and currently contain FakeQuant nodes with Float32 tensors (hence the ~13GB size). They are intended to be loaded into TensorRT which will fuse these nodes into actual low-precision kernels on supported hardware (Jetson Thor).
29
+
30
+ ## Directory Structure
31
+
32
+ ```
33
+ .
34
+ ├── fp32/
35
+ │ ├── model.onnx
36
+ │ └── model.onnx.data
37
+ ├── fp16/
38
+ │ ├── model.onnx
39
+ │ └── model.onnx.data
40
+ ├── nvfp8/
41
+ │ ├── model.onnx
42
+ │ └── model.onnx.data
43
+ ├── nvfp4/
44
+ │ ├── model.onnx
45
+ │ └── model.onnx.data
46
+ ├── int8/
47
+ │ ├── model.onnx
48
+ │ └── model.onnx.data
49
+ └── int4/
50
+ ├── model.onnx
51
+ └── model.onnx.data
52
+ ```
53
+
54
+ ## Usage
55
+
56
+ These models are designed to be consumed by **TensorRT** or **ONNX Runtime** with TensorRT Execution Provider on Nvidia Jetson Thor.
57
+
assets/physical-intelligence/libero/norm_stats.json ADDED
@@ -0,0 +1,556 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "norm_stats": {
3
+ "actions": {
4
+ "mean": [
5
+ 0.0,
6
+ 0.0,
7
+ 0.0,
8
+ 0.0,
9
+ 0.0,
10
+ 0.0,
11
+ 0.0,
12
+ 0.0,
13
+ 0.0,
14
+ 0.0,
15
+ 0.0,
16
+ 0.0,
17
+ 0.0,
18
+ 0.0,
19
+ 0.0,
20
+ 0.0,
21
+ 0.0,
22
+ 0.0,
23
+ 0.0,
24
+ 0.0,
25
+ 0.0,
26
+ 0.0,
27
+ 0.0,
28
+ 0.0,
29
+ 0.0,
30
+ 0.0,
31
+ 0.0,
32
+ 0.0,
33
+ 0.0,
34
+ 0.0,
35
+ 0.0,
36
+ 0.0
37
+ ],
38
+ "std": [
39
+ 1.0,
40
+ 1.0,
41
+ 1.0,
42
+ 1.0,
43
+ 1.0,
44
+ 1.0,
45
+ 1.0,
46
+ 1.0,
47
+ 1.0,
48
+ 1.0,
49
+ 1.0,
50
+ 1.0,
51
+ 1.0,
52
+ 1.0,
53
+ 1.0,
54
+ 1.0,
55
+ 1.0,
56
+ 1.0,
57
+ 1.0,
58
+ 1.0,
59
+ 1.0,
60
+ 1.0,
61
+ 1.0,
62
+ 1.0,
63
+ 1.0,
64
+ 1.0,
65
+ 1.0,
66
+ 1.0,
67
+ 1.0,
68
+ 1.0,
69
+ 1.0,
70
+ 1.0
71
+ ],
72
+ "q01": [
73
+ -1.0,
74
+ -1.0,
75
+ -1.0,
76
+ -1.0,
77
+ -1.0,
78
+ -1.0,
79
+ -1.0,
80
+ -1.0,
81
+ -1.0,
82
+ -1.0,
83
+ -1.0,
84
+ -1.0,
85
+ -1.0,
86
+ -1.0,
87
+ -1.0,
88
+ -1.0,
89
+ -1.0,
90
+ -1.0,
91
+ -1.0,
92
+ -1.0,
93
+ -1.0,
94
+ -1.0,
95
+ -1.0,
96
+ -1.0,
97
+ -1.0,
98
+ -1.0,
99
+ -1.0,
100
+ -1.0,
101
+ -1.0,
102
+ -1.0,
103
+ -1.0,
104
+ -1.0
105
+ ],
106
+ "q99": [
107
+ 2.0,
108
+ 2.0,
109
+ 2.0,
110
+ 2.0,
111
+ 2.0,
112
+ 2.0,
113
+ 2.0,
114
+ 2.0,
115
+ 2.0,
116
+ 2.0,
117
+ 2.0,
118
+ 2.0,
119
+ 2.0,
120
+ 2.0,
121
+ 2.0,
122
+ 2.0,
123
+ 2.0,
124
+ 2.0,
125
+ 2.0,
126
+ 2.0,
127
+ 2.0,
128
+ 2.0,
129
+ 2.0,
130
+ 2.0,
131
+ 2.0,
132
+ 2.0,
133
+ 2.0,
134
+ 2.0,
135
+ 2.0,
136
+ 2.0,
137
+ 2.0,
138
+ 2.0
139
+ ]
140
+ },
141
+ "state": {
142
+ "mean": [
143
+ 0.0,
144
+ 0.0,
145
+ 0.0,
146
+ 0.0,
147
+ 0.0,
148
+ 0.0,
149
+ 0.0,
150
+ 0.0,
151
+ 0.0,
152
+ 0.0,
153
+ 0.0,
154
+ 0.0,
155
+ 0.0,
156
+ 0.0,
157
+ 0.0,
158
+ 0.0,
159
+ 0.0,
160
+ 0.0,
161
+ 0.0,
162
+ 0.0,
163
+ 0.0,
164
+ 0.0,
165
+ 0.0,
166
+ 0.0,
167
+ 0.0,
168
+ 0.0,
169
+ 0.0,
170
+ 0.0,
171
+ 0.0,
172
+ 0.0,
173
+ 0.0,
174
+ 0.0
175
+ ],
176
+ "std": [
177
+ 1.0,
178
+ 1.0,
179
+ 1.0,
180
+ 1.0,
181
+ 1.0,
182
+ 1.0,
183
+ 1.0,
184
+ 1.0,
185
+ 1.0,
186
+ 1.0,
187
+ 1.0,
188
+ 1.0,
189
+ 1.0,
190
+ 1.0,
191
+ 1.0,
192
+ 1.0,
193
+ 1.0,
194
+ 1.0,
195
+ 1.0,
196
+ 1.0,
197
+ 1.0,
198
+ 1.0,
199
+ 1.0,
200
+ 1.0,
201
+ 1.0,
202
+ 1.0,
203
+ 1.0,
204
+ 1.0,
205
+ 1.0,
206
+ 1.0,
207
+ 1.0,
208
+ 1.0
209
+ ],
210
+ "q01": [
211
+ -1.0,
212
+ -1.0,
213
+ -1.0,
214
+ -1.0,
215
+ -1.0,
216
+ -1.0,
217
+ -1.0,
218
+ -1.0,
219
+ -1.0,
220
+ -1.0,
221
+ -1.0,
222
+ -1.0,
223
+ -1.0,
224
+ -1.0,
225
+ -1.0,
226
+ -1.0,
227
+ -1.0,
228
+ -1.0,
229
+ -1.0,
230
+ -1.0,
231
+ -1.0,
232
+ -1.0,
233
+ -1.0,
234
+ -1.0,
235
+ -1.0,
236
+ -1.0,
237
+ -1.0,
238
+ -1.0,
239
+ -1.0,
240
+ -1.0,
241
+ -1.0,
242
+ -1.0
243
+ ],
244
+ "q99": [
245
+ 2.0,
246
+ 2.0,
247
+ 2.0,
248
+ 2.0,
249
+ 2.0,
250
+ 2.0,
251
+ 2.0,
252
+ 2.0,
253
+ 2.0,
254
+ 2.0,
255
+ 2.0,
256
+ 2.0,
257
+ 2.0,
258
+ 2.0,
259
+ 2.0,
260
+ 2.0,
261
+ 2.0,
262
+ 2.0,
263
+ 2.0,
264
+ 2.0,
265
+ 2.0,
266
+ 2.0,
267
+ 2.0,
268
+ 2.0,
269
+ 2.0,
270
+ 2.0,
271
+ 2.0,
272
+ 2.0,
273
+ 2.0,
274
+ 2.0,
275
+ 2.0,
276
+ 2.0
277
+ ]
278
+ },
279
+ "joint_position": {
280
+ "mean": [
281
+ 0.0,
282
+ 0.0,
283
+ 0.0,
284
+ 0.0,
285
+ 0.0,
286
+ 0.0,
287
+ 0.0,
288
+ 0.0,
289
+ 0.0,
290
+ 0.0,
291
+ 0.0,
292
+ 0.0,
293
+ 0.0,
294
+ 0.0,
295
+ 0.0,
296
+ 0.0,
297
+ 0.0,
298
+ 0.0,
299
+ 0.0,
300
+ 0.0,
301
+ 0.0,
302
+ 0.0,
303
+ 0.0,
304
+ 0.0,
305
+ 0.0,
306
+ 0.0,
307
+ 0.0,
308
+ 0.0,
309
+ 0.0,
310
+ 0.0,
311
+ 0.0,
312
+ 0.0
313
+ ],
314
+ "std": [
315
+ 1.0,
316
+ 1.0,
317
+ 1.0,
318
+ 1.0,
319
+ 1.0,
320
+ 1.0,
321
+ 1.0,
322
+ 1.0,
323
+ 1.0,
324
+ 1.0,
325
+ 1.0,
326
+ 1.0,
327
+ 1.0,
328
+ 1.0,
329
+ 1.0,
330
+ 1.0,
331
+ 1.0,
332
+ 1.0,
333
+ 1.0,
334
+ 1.0,
335
+ 1.0,
336
+ 1.0,
337
+ 1.0,
338
+ 1.0,
339
+ 1.0,
340
+ 1.0,
341
+ 1.0,
342
+ 1.0,
343
+ 1.0,
344
+ 1.0,
345
+ 1.0,
346
+ 1.0
347
+ ],
348
+ "q01": [
349
+ -1.0,
350
+ -1.0,
351
+ -1.0,
352
+ -1.0,
353
+ -1.0,
354
+ -1.0,
355
+ -1.0,
356
+ -1.0,
357
+ -1.0,
358
+ -1.0,
359
+ -1.0,
360
+ -1.0,
361
+ -1.0,
362
+ -1.0,
363
+ -1.0,
364
+ -1.0,
365
+ -1.0,
366
+ -1.0,
367
+ -1.0,
368
+ -1.0,
369
+ -1.0,
370
+ -1.0,
371
+ -1.0,
372
+ -1.0,
373
+ -1.0,
374
+ -1.0,
375
+ -1.0,
376
+ -1.0,
377
+ -1.0,
378
+ -1.0,
379
+ -1.0,
380
+ -1.0
381
+ ],
382
+ "q99": [
383
+ 2.0,
384
+ 2.0,
385
+ 2.0,
386
+ 2.0,
387
+ 2.0,
388
+ 2.0,
389
+ 2.0,
390
+ 2.0,
391
+ 2.0,
392
+ 2.0,
393
+ 2.0,
394
+ 2.0,
395
+ 2.0,
396
+ 2.0,
397
+ 2.0,
398
+ 2.0,
399
+ 2.0,
400
+ 2.0,
401
+ 2.0,
402
+ 2.0,
403
+ 2.0,
404
+ 2.0,
405
+ 2.0,
406
+ 2.0,
407
+ 2.0,
408
+ 2.0,
409
+ 2.0,
410
+ 2.0,
411
+ 2.0,
412
+ 2.0,
413
+ 2.0,
414
+ 2.0
415
+ ]
416
+ },
417
+ "gripper_position": {
418
+ "mean": [
419
+ 0.0,
420
+ 0.0,
421
+ 0.0,
422
+ 0.0,
423
+ 0.0,
424
+ 0.0,
425
+ 0.0,
426
+ 0.0,
427
+ 0.0,
428
+ 0.0,
429
+ 0.0,
430
+ 0.0,
431
+ 0.0,
432
+ 0.0,
433
+ 0.0,
434
+ 0.0,
435
+ 0.0,
436
+ 0.0,
437
+ 0.0,
438
+ 0.0,
439
+ 0.0,
440
+ 0.0,
441
+ 0.0,
442
+ 0.0,
443
+ 0.0,
444
+ 0.0,
445
+ 0.0,
446
+ 0.0,
447
+ 0.0,
448
+ 0.0,
449
+ 0.0,
450
+ 0.0
451
+ ],
452
+ "std": [
453
+ 1.0,
454
+ 1.0,
455
+ 1.0,
456
+ 1.0,
457
+ 1.0,
458
+ 1.0,
459
+ 1.0,
460
+ 1.0,
461
+ 1.0,
462
+ 1.0,
463
+ 1.0,
464
+ 1.0,
465
+ 1.0,
466
+ 1.0,
467
+ 1.0,
468
+ 1.0,
469
+ 1.0,
470
+ 1.0,
471
+ 1.0,
472
+ 1.0,
473
+ 1.0,
474
+ 1.0,
475
+ 1.0,
476
+ 1.0,
477
+ 1.0,
478
+ 1.0,
479
+ 1.0,
480
+ 1.0,
481
+ 1.0,
482
+ 1.0,
483
+ 1.0,
484
+ 1.0
485
+ ],
486
+ "q01": [
487
+ -1.0,
488
+ -1.0,
489
+ -1.0,
490
+ -1.0,
491
+ -1.0,
492
+ -1.0,
493
+ -1.0,
494
+ -1.0,
495
+ -1.0,
496
+ -1.0,
497
+ -1.0,
498
+ -1.0,
499
+ -1.0,
500
+ -1.0,
501
+ -1.0,
502
+ -1.0,
503
+ -1.0,
504
+ -1.0,
505
+ -1.0,
506
+ -1.0,
507
+ -1.0,
508
+ -1.0,
509
+ -1.0,
510
+ -1.0,
511
+ -1.0,
512
+ -1.0,
513
+ -1.0,
514
+ -1.0,
515
+ -1.0,
516
+ -1.0,
517
+ -1.0,
518
+ -1.0
519
+ ],
520
+ "q99": [
521
+ 2.0,
522
+ 2.0,
523
+ 2.0,
524
+ 2.0,
525
+ 2.0,
526
+ 2.0,
527
+ 2.0,
528
+ 2.0,
529
+ 2.0,
530
+ 2.0,
531
+ 2.0,
532
+ 2.0,
533
+ 2.0,
534
+ 2.0,
535
+ 2.0,
536
+ 2.0,
537
+ 2.0,
538
+ 2.0,
539
+ 2.0,
540
+ 2.0,
541
+ 2.0,
542
+ 2.0,
543
+ 2.0,
544
+ 2.0,
545
+ 2.0,
546
+ 2.0,
547
+ 2.0,
548
+ 2.0,
549
+ 2.0,
550
+ 2.0,
551
+ 2.0,
552
+ 2.0
553
+ ]
554
+ }
555
+ }
556
+ }
fp16/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9d307da4658ae0d1000d5dc26867424b394d9e13bfa09854fc06d32048e2402
3
+ size 19494076
fp16/model.onnx.data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46787d2fa5c1b20c1f82a256ec6b688cb707ee29eff894e9af96ac542b434fb2
3
+ size 6488672480
fp32/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3ae488c8cb2a2b9a2708fa5144b3321a85b71e12b57123904de94a0c8dc143b
3
+ size 12460408
fp32/model.onnx.data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdb0a65ae85dd0af5d6e76b1f1e35fc91041cf07be2a4a968361af2d2a83e113
3
+ size 12975790528
int4/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6969a79571a6a5e1e23084af6e5a9b1eb55be70db3c3ac35cbfee3ca324ecf8c
3
+ size 211026524
int4/model.onnx.data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c650d406fe459550326d12af9ad989d331dcef05b9dd18b543d6469d5cad2fc3
3
+ size 12975790528
int8/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9b3816e2aa8bae2dd82eebb0424b9f6df0892004d61534e357bc164791e4d8a
3
+ size 37230927
int8/model.onnx.data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f0747ae8c7a814db7015db07ac6f75cdfa49f4e31e718c28c987a7083b59431
3
+ size 12975790528
model.action_in_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98b42ef28d85469d61445992e3bdf163274749946b36ec06aedeb40bb03e1b19
3
+ size 131072
model.action_out_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5194d9cbb7f742c0201786985948f4a1a184126d15b79deb36f78f94bbf8ae0
3
+ size 131072
model.paligemma_with_expert.gemma_expert.model.layers.0.input_layernorm.dense.bias ADDED
Binary file (12.3 kB). View file
 
model.paligemma_with_expert.gemma_expert.model.layers.0.input_layernorm.dense.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27545db05466fe61b2cd92910c8d04985151c847fc9e528977a5cfdb19a5f626
3
+ size 12582912
model.paligemma_with_expert.gemma_expert.model.layers.0.mlp.down_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cec64d8c346bd59192f1c2143e6bbb9b7c8aa7d0a4ac6e60a62f543a787d284a
3
+ size 16777216
model.paligemma_with_expert.gemma_expert.model.layers.0.mlp.gate_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8169de1b17b965644b459f55cb1edacfe0809b2838569f76e9751e2566d5dbfe
3
+ size 16777216
model.paligemma_with_expert.gemma_expert.model.layers.0.mlp.up_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a1f73ab1498549c1730b1bf81524728323f78d09f08608f9b8c171395f7a1e0
3
+ size 16777216
model.paligemma_with_expert.gemma_expert.model.layers.0.post_attention_layernorm.dense.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5436534b6140a1a9ef39bd8ad11ee122161fdffcee336d7b5bd79b1d80ebb59
3
+ size 12582912
model.paligemma_with_expert.gemma_expert.model.layers.0.self_attn.k_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93b3df11387123361154db38287d95d22b489a1a1cb7a3ec9f4cabe16e5d77d0
3
+ size 1048576
model.paligemma_with_expert.gemma_expert.model.layers.0.self_attn.o_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f069f89a15236275a0ce8200463307c8995288b2e5726cd186a616c1d370641
3
+ size 8388608
model.paligemma_with_expert.gemma_expert.model.layers.0.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91f7164879bd9565e6435e2ebcb6b0edf4315292a1ea22b556b5e3f4323bf054
3
+ size 8388608
model.paligemma_with_expert.gemma_expert.model.layers.0.self_attn.v_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf8322964064996d1ee2e683f52a936a40d4d5018adf22660f177ad380f1c4d8
3
+ size 1048576
model.paligemma_with_expert.gemma_expert.model.layers.1.input_layernorm.dense.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4d2ca089d408fe186df334e0873f67c7cc728c571de149f71d9ea53b5052f98
3
+ size 12582912
model.paligemma_with_expert.gemma_expert.model.layers.1.mlp.down_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8266898d1b6873a3bf7319c532d259aa12112f9943febbb46f67625fd57b71f
3
+ size 16777216
model.paligemma_with_expert.gemma_expert.model.layers.1.mlp.gate_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbfb6b4c7b5cde907bffa747579372f1228a5146c2f73c7c5f085c81f2280594
3
+ size 16777216
model.paligemma_with_expert.gemma_expert.model.layers.1.mlp.up_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37685f709f13b768242103338ae98e138d9653534c15704c1f69e3d45d925f03
3
+ size 16777216
model.paligemma_with_expert.gemma_expert.model.layers.1.post_attention_layernorm.dense.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:173ac5175bd9d3dc11cb818d63965e8a59de0407b0ef6b6132c4345a349603c7
3
+ size 12582912
model.paligemma_with_expert.gemma_expert.model.layers.1.self_attn.k_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a919f2dbc0e4b501c7ee68ee032b5b29abf9a465b16777e5911e3687ad63a3ff
3
+ size 1048576
model.paligemma_with_expert.gemma_expert.model.layers.1.self_attn.o_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79e3c0fa50fab36a3032160400180422125660aba85aa9c41838287aa9e03051
3
+ size 8388608
model.paligemma_with_expert.gemma_expert.model.layers.1.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69b092e53d99cb498b10e6e387325f8cfbc678c8d05d6ad7ae05663179a4c820
3
+ size 8388608
model.paligemma_with_expert.gemma_expert.model.layers.1.self_attn.v_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae56ca548f82f83273a25205f521d03be8f21b941b24f8d57423601f29b18049
3
+ size 1048576
model.paligemma_with_expert.gemma_expert.model.layers.10.input_layernorm.dense.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edebd7adbb30d8beb0e7f55b48febcfc311ca793d554ece290c45a9900be653a
3
+ size 12582912
model.paligemma_with_expert.gemma_expert.model.layers.10.mlp.down_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20d80955a132fb3ba3d1545e4708bd21bffde21a7275e674ac867175a836ad25
3
+ size 16777216
model.paligemma_with_expert.gemma_expert.model.layers.10.mlp.gate_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dce6e97a9fd7e01f355d6afc006ed03a8057c7fe5f9c60593f8766581a24a7d
3
+ size 16777216
model.paligemma_with_expert.gemma_expert.model.layers.10.mlp.up_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:739c8c10af59304aa92e195c9496c00df10dfba52ff6448c45f538edd4697941
3
+ size 16777216
model.paligemma_with_expert.gemma_expert.model.layers.10.post_attention_layernorm.dense.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe24159dcadda45a6a8a03c91a6071381e200701e1acb398ec0d8ef19c8cb988
3
+ size 12582912
model.paligemma_with_expert.gemma_expert.model.layers.10.self_attn.k_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ece46492d96746e5fc6b7e060290960dc7f81cf9e306cd00de1303b226568be
3
+ size 1048576
model.paligemma_with_expert.gemma_expert.model.layers.10.self_attn.o_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c850649b4821399c73dffe771e31bb73620833b91a1f1ff3818e379d54c68bc
3
+ size 8388608
model.paligemma_with_expert.gemma_expert.model.layers.10.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ff223bd88b6b55e5e66570833a5021c180b4d8660347a57dfca9a936710bf83
3
+ size 8388608
model.paligemma_with_expert.gemma_expert.model.layers.10.self_attn.v_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:841e214f8cc0ccb824be6311c0fc6518d85fa888faa883ba4e5db9d8db4fab62
3
+ size 1048576
model.paligemma_with_expert.gemma_expert.model.layers.11.input_layernorm.dense.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebfa8033c616be8202539201501989d752e2844dae74cd9d56da66cbae90779d
3
+ size 12582912
model.paligemma_with_expert.gemma_expert.model.layers.11.mlp.down_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1780de412bc30be7a7edd79ed907068857562423e1be63eac16ed95335937cdf
3
+ size 16777216
model.paligemma_with_expert.gemma_expert.model.layers.11.mlp.gate_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78217aea4a35a729f09bff2db6f640c1fa7b07dde6d2810c76cda8f1fab565b8
3
+ size 16777216
model.paligemma_with_expert.gemma_expert.model.layers.11.mlp.up_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7db5e8026d2a1916490c1f1c05f35f707784887b598d5c4163244f45cd654b6
3
+ size 16777216
model.paligemma_with_expert.gemma_expert.model.layers.11.post_attention_layernorm.dense.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f85edb6d1cd8a79a5482093f58a0752beab3b3896af295374edad4a4e6a6cd42
3
+ size 12582912
model.paligemma_with_expert.gemma_expert.model.layers.11.self_attn.k_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b156b317360655bff9d7ddb58a72adeaeadcdfd8e9fccb967e4ad642d5f220f5
3
+ size 1048576
model.paligemma_with_expert.gemma_expert.model.layers.11.self_attn.o_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22461101e4c53e4d54418a5fbc9699d65716e348b7e449ce2384f646a0933258
3
+ size 8388608
model.paligemma_with_expert.gemma_expert.model.layers.11.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93cbbb0323c6b4109481c14c30d3de9e3eef04ebc5e245da2a5199b7bdfcd791
3
+ size 8388608
model.paligemma_with_expert.gemma_expert.model.layers.11.self_attn.v_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16e04dc4ff36d7de689c6702eb87d44dc66a6771272b3f64a9272304c2c4c09a
3
+ size 1048576