pranavajay
commited on
Upload log.txt with huggingface_hub
Browse files
log.txt
ADDED
@@ -0,0 +1,488 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Tensor 'context_embedder.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
2 |
+
Tensor 'context_embedder.weight' has different shapes: Model 1: torch.Size([2150, 4096]), Model 2: torch.Size([3072, 4096])
|
3 |
+
Tensor 'time_text_embed.guidance_embedder.linear_1.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
4 |
+
Tensor 'time_text_embed.guidance_embedder.linear_1.weight' has different shapes: Model 1: torch.Size([2150, 256]), Model 2: torch.Size([3072, 256])
|
5 |
+
Tensor 'time_text_embed.guidance_embedder.linear_2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
6 |
+
Tensor 'time_text_embed.guidance_embedder.linear_2.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
7 |
+
Tensor 'time_text_embed.text_embedder.linear_1.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
8 |
+
Tensor 'time_text_embed.text_embedder.linear_1.weight' has different shapes: Model 1: torch.Size([2150, 768]), Model 2: torch.Size([3072, 768])
|
9 |
+
Tensor 'time_text_embed.text_embedder.linear_2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
10 |
+
Tensor 'time_text_embed.text_embedder.linear_2.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
11 |
+
Tensor 'time_text_embed.timestep_embedder.linear_1.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
12 |
+
Tensor 'time_text_embed.timestep_embedder.linear_1.weight' has different shapes: Model 1: torch.Size([2150, 256]), Model 2: torch.Size([3072, 256])
|
13 |
+
Tensor 'time_text_embed.timestep_embedder.linear_2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
14 |
+
Tensor 'time_text_embed.timestep_embedder.linear_2.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
15 |
+
Tensor 'transformer_blocks.0.attn.add_k_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
16 |
+
Tensor 'transformer_blocks.0.attn.add_k_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
17 |
+
Tensor 'transformer_blocks.0.attn.add_q_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
18 |
+
Tensor 'transformer_blocks.0.attn.add_q_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
19 |
+
Tensor 'transformer_blocks.0.attn.add_v_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
20 |
+
Tensor 'transformer_blocks.0.attn.add_v_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
21 |
+
Tensor 'transformer_blocks.0.attn.norm_added_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
22 |
+
Tensor 'transformer_blocks.0.attn.norm_added_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
23 |
+
Tensor 'transformer_blocks.0.attn.norm_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
24 |
+
Tensor 'transformer_blocks.0.attn.norm_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
25 |
+
Tensor 'transformer_blocks.0.attn.to_add_out.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
26 |
+
Tensor 'transformer_blocks.0.attn.to_add_out.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
27 |
+
Tensor 'transformer_blocks.0.attn.to_k.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
28 |
+
Tensor 'transformer_blocks.0.attn.to_k.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
29 |
+
Tensor 'transformer_blocks.0.attn.to_out.0.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
30 |
+
Tensor 'transformer_blocks.0.attn.to_out.0.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
31 |
+
Tensor 'transformer_blocks.0.attn.to_q.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
32 |
+
Tensor 'transformer_blocks.0.attn.to_q.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
33 |
+
Tensor 'transformer_blocks.0.attn.to_v.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
34 |
+
Tensor 'transformer_blocks.0.attn.to_v.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
35 |
+
Tensor 'transformer_blocks.0.ff.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
36 |
+
Tensor 'transformer_blocks.0.ff.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
37 |
+
Tensor 'transformer_blocks.0.ff.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
38 |
+
Tensor 'transformer_blocks.0.ff.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
39 |
+
Tensor 'transformer_blocks.0.ff_context.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
40 |
+
Tensor 'transformer_blocks.0.ff_context.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
41 |
+
Tensor 'transformer_blocks.0.ff_context.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
42 |
+
Tensor 'transformer_blocks.0.ff_context.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
43 |
+
Tensor 'transformer_blocks.0.norm1.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
44 |
+
Tensor 'transformer_blocks.0.norm1.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
45 |
+
Tensor 'transformer_blocks.0.norm1_context.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
46 |
+
Tensor 'transformer_blocks.0.norm1_context.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
47 |
+
Tensor 'transformer_blocks.1.attn.add_k_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
48 |
+
Tensor 'transformer_blocks.1.attn.add_k_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
49 |
+
Tensor 'transformer_blocks.1.attn.add_q_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
50 |
+
Tensor 'transformer_blocks.1.attn.add_q_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
51 |
+
Tensor 'transformer_blocks.1.attn.add_v_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
52 |
+
Tensor 'transformer_blocks.1.attn.add_v_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
53 |
+
Tensor 'transformer_blocks.1.attn.norm_added_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
54 |
+
Tensor 'transformer_blocks.1.attn.norm_added_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
55 |
+
Tensor 'transformer_blocks.1.attn.norm_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
56 |
+
Tensor 'transformer_blocks.1.attn.norm_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
57 |
+
Tensor 'transformer_blocks.1.attn.to_add_out.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
58 |
+
Tensor 'transformer_blocks.1.attn.to_add_out.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
59 |
+
Tensor 'transformer_blocks.1.attn.to_k.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
60 |
+
Tensor 'transformer_blocks.1.attn.to_k.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
61 |
+
Tensor 'transformer_blocks.1.attn.to_out.0.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
62 |
+
Tensor 'transformer_blocks.1.attn.to_out.0.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
63 |
+
Tensor 'transformer_blocks.1.attn.to_q.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
64 |
+
Tensor 'transformer_blocks.1.attn.to_q.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
65 |
+
Tensor 'transformer_blocks.1.attn.to_v.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
66 |
+
Tensor 'transformer_blocks.1.attn.to_v.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
67 |
+
Tensor 'transformer_blocks.1.ff.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
68 |
+
Tensor 'transformer_blocks.1.ff.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
69 |
+
Tensor 'transformer_blocks.1.ff.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
70 |
+
Tensor 'transformer_blocks.1.ff.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
71 |
+
Tensor 'transformer_blocks.1.ff_context.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
72 |
+
Tensor 'transformer_blocks.1.ff_context.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
73 |
+
Tensor 'transformer_blocks.1.ff_context.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
74 |
+
Tensor 'transformer_blocks.1.ff_context.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
75 |
+
Tensor 'transformer_blocks.1.norm1.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
76 |
+
Tensor 'transformer_blocks.1.norm1.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
77 |
+
Tensor 'transformer_blocks.1.norm1_context.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
78 |
+
Tensor 'transformer_blocks.1.norm1_context.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
79 |
+
Tensor 'transformer_blocks.10.attn.add_k_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
80 |
+
Tensor 'transformer_blocks.10.attn.add_k_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
81 |
+
Tensor 'transformer_blocks.10.attn.add_q_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
82 |
+
Tensor 'transformer_blocks.10.attn.add_q_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
83 |
+
Tensor 'transformer_blocks.10.attn.add_v_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
84 |
+
Tensor 'transformer_blocks.10.attn.add_v_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
85 |
+
Tensor 'transformer_blocks.10.attn.norm_added_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
86 |
+
Tensor 'transformer_blocks.10.attn.norm_added_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
87 |
+
Tensor 'transformer_blocks.10.attn.norm_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
88 |
+
Tensor 'transformer_blocks.10.attn.norm_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
89 |
+
Tensor 'transformer_blocks.10.attn.to_add_out.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
90 |
+
Tensor 'transformer_blocks.10.attn.to_add_out.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
91 |
+
Tensor 'transformer_blocks.10.attn.to_k.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
92 |
+
Tensor 'transformer_blocks.10.attn.to_k.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
93 |
+
Tensor 'transformer_blocks.10.attn.to_out.0.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
94 |
+
Tensor 'transformer_blocks.10.attn.to_out.0.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
95 |
+
Tensor 'transformer_blocks.10.attn.to_q.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
96 |
+
Tensor 'transformer_blocks.10.attn.to_q.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
97 |
+
Tensor 'transformer_blocks.10.attn.to_v.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
98 |
+
Tensor 'transformer_blocks.10.attn.to_v.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
99 |
+
Tensor 'transformer_blocks.10.ff.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
100 |
+
Tensor 'transformer_blocks.10.ff.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
101 |
+
Tensor 'transformer_blocks.10.ff.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
102 |
+
Tensor 'transformer_blocks.10.ff.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
103 |
+
Tensor 'transformer_blocks.10.ff_context.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
104 |
+
Tensor 'transformer_blocks.10.ff_context.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
105 |
+
Tensor 'transformer_blocks.10.ff_context.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
106 |
+
Tensor 'transformer_blocks.10.ff_context.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
107 |
+
Tensor 'transformer_blocks.10.norm1.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
108 |
+
Tensor 'transformer_blocks.10.norm1.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
109 |
+
Tensor 'transformer_blocks.10.norm1_context.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
110 |
+
Tensor 'transformer_blocks.10.norm1_context.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
111 |
+
Tensor 'transformer_blocks.11.attn.add_k_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
112 |
+
Tensor 'transformer_blocks.11.attn.add_k_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
113 |
+
Tensor 'transformer_blocks.11.attn.add_q_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
114 |
+
Tensor 'transformer_blocks.11.attn.add_q_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
115 |
+
Tensor 'transformer_blocks.11.attn.add_v_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
116 |
+
Tensor 'transformer_blocks.11.attn.add_v_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
117 |
+
Tensor 'transformer_blocks.11.attn.norm_added_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
118 |
+
Tensor 'transformer_blocks.11.attn.norm_added_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
119 |
+
Tensor 'transformer_blocks.11.attn.norm_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
120 |
+
Tensor 'transformer_blocks.11.attn.norm_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
121 |
+
Tensor 'transformer_blocks.11.attn.to_add_out.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
122 |
+
Tensor 'transformer_blocks.11.attn.to_add_out.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
123 |
+
Tensor 'transformer_blocks.11.attn.to_k.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
124 |
+
Tensor 'transformer_blocks.11.attn.to_k.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
125 |
+
Tensor 'transformer_blocks.11.attn.to_out.0.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
126 |
+
Tensor 'transformer_blocks.11.attn.to_out.0.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
127 |
+
Tensor 'transformer_blocks.11.attn.to_q.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
128 |
+
Tensor 'transformer_blocks.11.attn.to_q.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
129 |
+
Tensor 'transformer_blocks.11.attn.to_v.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
130 |
+
Tensor 'transformer_blocks.11.attn.to_v.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
131 |
+
Tensor 'transformer_blocks.11.ff.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
132 |
+
Tensor 'transformer_blocks.11.ff.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
133 |
+
Tensor 'transformer_blocks.11.ff.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
134 |
+
Tensor 'transformer_blocks.11.ff.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
135 |
+
Tensor 'transformer_blocks.11.ff_context.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
136 |
+
Tensor 'transformer_blocks.11.ff_context.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
137 |
+
Tensor 'transformer_blocks.11.ff_context.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
138 |
+
Tensor 'transformer_blocks.11.ff_context.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
139 |
+
Tensor 'transformer_blocks.11.norm1.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
140 |
+
Tensor 'transformer_blocks.11.norm1.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
141 |
+
Tensor 'transformer_blocks.11.norm1_context.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
142 |
+
Tensor 'transformer_blocks.11.norm1_context.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
143 |
+
Tensor 'transformer_blocks.12.attn.add_k_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
144 |
+
Tensor 'transformer_blocks.12.attn.add_k_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
145 |
+
Tensor 'transformer_blocks.12.attn.add_q_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
146 |
+
Tensor 'transformer_blocks.12.attn.add_q_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
147 |
+
Tensor 'transformer_blocks.12.attn.add_v_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
148 |
+
Tensor 'transformer_blocks.12.attn.add_v_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
149 |
+
Tensor 'transformer_blocks.12.attn.norm_added_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
150 |
+
Tensor 'transformer_blocks.12.attn.norm_added_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
151 |
+
Tensor 'transformer_blocks.12.attn.norm_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
152 |
+
Tensor 'transformer_blocks.12.attn.norm_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
153 |
+
Tensor 'transformer_blocks.12.attn.to_add_out.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
154 |
+
Tensor 'transformer_blocks.12.attn.to_add_out.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
155 |
+
Tensor 'transformer_blocks.12.attn.to_k.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
156 |
+
Tensor 'transformer_blocks.12.attn.to_k.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
157 |
+
Tensor 'transformer_blocks.12.attn.to_out.0.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
158 |
+
Tensor 'transformer_blocks.12.attn.to_out.0.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
159 |
+
Tensor 'transformer_blocks.12.attn.to_q.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
160 |
+
Tensor 'transformer_blocks.12.attn.to_q.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
161 |
+
Tensor 'transformer_blocks.12.attn.to_v.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
162 |
+
Tensor 'transformer_blocks.12.attn.to_v.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
163 |
+
Tensor 'transformer_blocks.12.ff.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
164 |
+
Tensor 'transformer_blocks.12.ff.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
165 |
+
Tensor 'transformer_blocks.12.ff.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
166 |
+
Tensor 'transformer_blocks.12.ff.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
167 |
+
Tensor 'transformer_blocks.12.ff_context.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
168 |
+
Tensor 'transformer_blocks.12.ff_context.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
169 |
+
Tensor 'transformer_blocks.12.ff_context.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
170 |
+
Tensor 'transformer_blocks.12.ff_context.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
171 |
+
Tensor 'transformer_blocks.12.norm1.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
172 |
+
Tensor 'transformer_blocks.12.norm1.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
173 |
+
Tensor 'transformer_blocks.12.norm1_context.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
174 |
+
Tensor 'transformer_blocks.12.norm1_context.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
175 |
+
Tensor 'transformer_blocks.13.attn.add_k_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
176 |
+
Tensor 'transformer_blocks.13.attn.add_k_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
177 |
+
Tensor 'transformer_blocks.13.attn.add_q_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
178 |
+
Tensor 'transformer_blocks.13.attn.add_q_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
179 |
+
Tensor 'transformer_blocks.13.attn.add_v_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
180 |
+
Tensor 'transformer_blocks.13.attn.add_v_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
181 |
+
Tensor 'transformer_blocks.13.attn.norm_added_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
182 |
+
Tensor 'transformer_blocks.13.attn.norm_added_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
183 |
+
Tensor 'transformer_blocks.13.attn.norm_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
184 |
+
Tensor 'transformer_blocks.13.attn.norm_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
185 |
+
Tensor 'transformer_blocks.13.attn.to_add_out.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
186 |
+
Tensor 'transformer_blocks.13.attn.to_add_out.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
187 |
+
Tensor 'transformer_blocks.13.attn.to_k.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
188 |
+
Tensor 'transformer_blocks.13.attn.to_k.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
189 |
+
Tensor 'transformer_blocks.13.attn.to_out.0.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
190 |
+
Tensor 'transformer_blocks.13.attn.to_out.0.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
191 |
+
Tensor 'transformer_blocks.13.attn.to_q.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
192 |
+
Tensor 'transformer_blocks.13.attn.to_q.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
193 |
+
Tensor 'transformer_blocks.13.attn.to_v.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
194 |
+
Tensor 'transformer_blocks.13.attn.to_v.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
195 |
+
Tensor 'transformer_blocks.13.ff.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
196 |
+
Tensor 'transformer_blocks.13.ff.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
197 |
+
Tensor 'transformer_blocks.13.ff.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
198 |
+
Tensor 'transformer_blocks.13.ff.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
199 |
+
Tensor 'transformer_blocks.13.ff_context.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
200 |
+
Tensor 'transformer_blocks.13.ff_context.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
201 |
+
Tensor 'transformer_blocks.13.ff_context.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
202 |
+
Tensor 'transformer_blocks.13.ff_context.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
203 |
+
Tensor 'transformer_blocks.13.norm1.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
204 |
+
Tensor 'transformer_blocks.13.norm1.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
205 |
+
Tensor 'transformer_blocks.13.norm1_context.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
206 |
+
Tensor 'transformer_blocks.13.norm1_context.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
207 |
+
Tensor 'transformer_blocks.14.attn.add_k_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
208 |
+
Tensor 'transformer_blocks.14.attn.add_k_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
209 |
+
Tensor 'transformer_blocks.14.attn.add_q_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
210 |
+
Tensor 'transformer_blocks.14.attn.add_q_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
211 |
+
Tensor 'transformer_blocks.14.attn.add_v_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
212 |
+
Tensor 'transformer_blocks.14.attn.add_v_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
213 |
+
Tensor 'transformer_blocks.14.attn.norm_added_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
214 |
+
Tensor 'transformer_blocks.14.attn.norm_added_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
215 |
+
Tensor 'transformer_blocks.14.attn.norm_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
216 |
+
Tensor 'transformer_blocks.14.attn.norm_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
217 |
+
Tensor 'transformer_blocks.14.attn.to_add_out.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
218 |
+
Tensor 'transformer_blocks.14.attn.to_add_out.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
219 |
+
Tensor 'transformer_blocks.14.attn.to_k.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
220 |
+
Tensor 'transformer_blocks.14.attn.to_k.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
221 |
+
Tensor 'transformer_blocks.14.attn.to_out.0.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
222 |
+
Tensor 'transformer_blocks.14.attn.to_out.0.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
223 |
+
Tensor 'transformer_blocks.14.attn.to_q.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
224 |
+
Tensor 'transformer_blocks.14.attn.to_q.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
225 |
+
Tensor 'transformer_blocks.14.attn.to_v.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
226 |
+
Tensor 'transformer_blocks.14.attn.to_v.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
227 |
+
Tensor 'transformer_blocks.14.norm1.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
228 |
+
Tensor 'transformer_blocks.14.norm1.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
229 |
+
Tensor 'transformer_blocks.14.norm1_context.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
230 |
+
Tensor 'transformer_blocks.14.norm1_context.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
231 |
+
Tensor 'transformer_blocks.2.attn.add_k_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
232 |
+
Tensor 'transformer_blocks.2.attn.add_k_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
233 |
+
Tensor 'transformer_blocks.2.attn.add_q_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
234 |
+
Tensor 'transformer_blocks.2.attn.add_q_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
235 |
+
Tensor 'transformer_blocks.2.attn.add_v_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
236 |
+
Tensor 'transformer_blocks.2.attn.add_v_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
237 |
+
Tensor 'transformer_blocks.2.attn.norm_added_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
238 |
+
Tensor 'transformer_blocks.2.attn.norm_added_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
239 |
+
Tensor 'transformer_blocks.2.attn.norm_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
240 |
+
Tensor 'transformer_blocks.2.attn.norm_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
241 |
+
Tensor 'transformer_blocks.2.attn.to_add_out.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
242 |
+
Tensor 'transformer_blocks.2.attn.to_add_out.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
243 |
+
Tensor 'transformer_blocks.2.attn.to_k.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
244 |
+
Tensor 'transformer_blocks.2.attn.to_k.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
245 |
+
Tensor 'transformer_blocks.2.attn.to_out.0.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
246 |
+
Tensor 'transformer_blocks.2.attn.to_out.0.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
247 |
+
Tensor 'transformer_blocks.2.attn.to_q.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
248 |
+
Tensor 'transformer_blocks.2.attn.to_q.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
249 |
+
Tensor 'transformer_blocks.2.attn.to_v.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
250 |
+
Tensor 'transformer_blocks.2.attn.to_v.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
251 |
+
Tensor 'transformer_blocks.2.ff.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
252 |
+
Tensor 'transformer_blocks.2.ff.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
253 |
+
Tensor 'transformer_blocks.2.ff.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
254 |
+
Tensor 'transformer_blocks.2.ff.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
255 |
+
Tensor 'transformer_blocks.2.ff_context.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
256 |
+
Tensor 'transformer_blocks.2.ff_context.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
257 |
+
Tensor 'transformer_blocks.2.ff_context.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
258 |
+
Tensor 'transformer_blocks.2.ff_context.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
259 |
+
Tensor 'transformer_blocks.2.norm1.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
260 |
+
Tensor 'transformer_blocks.2.norm1.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
261 |
+
Tensor 'transformer_blocks.2.norm1_context.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
262 |
+
Tensor 'transformer_blocks.2.norm1_context.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
263 |
+
Tensor 'transformer_blocks.3.attn.add_k_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
264 |
+
Tensor 'transformer_blocks.3.attn.add_k_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
265 |
+
Tensor 'transformer_blocks.3.attn.add_q_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
266 |
+
Tensor 'transformer_blocks.3.attn.add_q_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
267 |
+
Tensor 'transformer_blocks.3.attn.add_v_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
268 |
+
Tensor 'transformer_blocks.3.attn.add_v_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
269 |
+
Tensor 'transformer_blocks.3.attn.norm_added_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
270 |
+
Tensor 'transformer_blocks.3.attn.norm_added_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
271 |
+
Tensor 'transformer_blocks.3.attn.norm_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
272 |
+
Tensor 'transformer_blocks.3.attn.norm_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
273 |
+
Tensor 'transformer_blocks.3.attn.to_add_out.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
274 |
+
Tensor 'transformer_blocks.3.attn.to_add_out.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
275 |
+
Tensor 'transformer_blocks.3.attn.to_k.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
276 |
+
Tensor 'transformer_blocks.3.attn.to_k.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
277 |
+
Tensor 'transformer_blocks.3.attn.to_out.0.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
278 |
+
Tensor 'transformer_blocks.3.attn.to_out.0.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
279 |
+
Tensor 'transformer_blocks.3.attn.to_q.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
280 |
+
Tensor 'transformer_blocks.3.attn.to_q.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
281 |
+
Tensor 'transformer_blocks.3.attn.to_v.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
282 |
+
Tensor 'transformer_blocks.3.attn.to_v.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
283 |
+
Tensor 'transformer_blocks.3.ff.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
284 |
+
Tensor 'transformer_blocks.3.ff.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
285 |
+
Tensor 'transformer_blocks.3.ff.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
286 |
+
Tensor 'transformer_blocks.3.ff.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
287 |
+
Tensor 'transformer_blocks.3.ff_context.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
288 |
+
Tensor 'transformer_blocks.3.ff_context.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
289 |
+
Tensor 'transformer_blocks.3.ff_context.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
290 |
+
Tensor 'transformer_blocks.3.ff_context.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
291 |
+
Tensor 'transformer_blocks.3.norm1.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
292 |
+
Tensor 'transformer_blocks.3.norm1.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
293 |
+
Tensor 'transformer_blocks.3.norm1_context.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
294 |
+
Tensor 'transformer_blocks.3.norm1_context.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
295 |
+
Tensor 'transformer_blocks.4.attn.add_k_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
296 |
+
Tensor 'transformer_blocks.4.attn.add_k_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
297 |
+
Tensor 'transformer_blocks.4.attn.add_q_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
298 |
+
Tensor 'transformer_blocks.4.attn.add_q_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
299 |
+
Tensor 'transformer_blocks.4.attn.add_v_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
300 |
+
Tensor 'transformer_blocks.4.attn.add_v_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
301 |
+
Tensor 'transformer_blocks.4.attn.norm_added_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
302 |
+
Tensor 'transformer_blocks.4.attn.norm_added_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
303 |
+
Tensor 'transformer_blocks.4.attn.norm_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
304 |
+
Tensor 'transformer_blocks.4.attn.norm_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
305 |
+
Tensor 'transformer_blocks.4.attn.to_add_out.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
306 |
+
Tensor 'transformer_blocks.4.attn.to_add_out.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
307 |
+
Tensor 'transformer_blocks.4.attn.to_k.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
308 |
+
Tensor 'transformer_blocks.4.attn.to_k.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
309 |
+
Tensor 'transformer_blocks.4.attn.to_out.0.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
310 |
+
Tensor 'transformer_blocks.4.attn.to_out.0.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
311 |
+
Tensor 'transformer_blocks.4.attn.to_q.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
312 |
+
Tensor 'transformer_blocks.4.attn.to_q.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
313 |
+
Tensor 'transformer_blocks.4.attn.to_v.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
314 |
+
Tensor 'transformer_blocks.4.attn.to_v.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
315 |
+
Tensor 'transformer_blocks.4.ff.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
316 |
+
Tensor 'transformer_blocks.4.ff.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
317 |
+
Tensor 'transformer_blocks.4.ff.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
318 |
+
Tensor 'transformer_blocks.4.ff.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
319 |
+
Tensor 'transformer_blocks.4.ff_context.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
320 |
+
Tensor 'transformer_blocks.4.ff_context.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
321 |
+
Tensor 'transformer_blocks.4.ff_context.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
322 |
+
Tensor 'transformer_blocks.4.ff_context.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
323 |
+
Tensor 'transformer_blocks.4.norm1.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
324 |
+
Tensor 'transformer_blocks.4.norm1.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
325 |
+
Tensor 'transformer_blocks.4.norm1_context.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
326 |
+
Tensor 'transformer_blocks.4.norm1_context.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
327 |
+
Tensor 'transformer_blocks.5.attn.add_k_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
328 |
+
Tensor 'transformer_blocks.5.attn.add_k_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
329 |
+
Tensor 'transformer_blocks.5.attn.add_q_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
330 |
+
Tensor 'transformer_blocks.5.attn.add_q_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
331 |
+
Tensor 'transformer_blocks.5.attn.add_v_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
332 |
+
Tensor 'transformer_blocks.5.attn.add_v_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
333 |
+
Tensor 'transformer_blocks.5.attn.norm_added_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
334 |
+
Tensor 'transformer_blocks.5.attn.norm_added_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
335 |
+
Tensor 'transformer_blocks.5.attn.norm_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
336 |
+
Tensor 'transformer_blocks.5.attn.norm_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
337 |
+
Tensor 'transformer_blocks.5.attn.to_add_out.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
338 |
+
Tensor 'transformer_blocks.5.attn.to_add_out.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
339 |
+
Tensor 'transformer_blocks.5.attn.to_k.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
340 |
+
Tensor 'transformer_blocks.5.attn.to_k.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
341 |
+
Tensor 'transformer_blocks.5.attn.to_out.0.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
342 |
+
Tensor 'transformer_blocks.5.attn.to_out.0.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
343 |
+
Tensor 'transformer_blocks.5.attn.to_q.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
344 |
+
Tensor 'transformer_blocks.5.attn.to_q.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
345 |
+
Tensor 'transformer_blocks.5.attn.to_v.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
346 |
+
Tensor 'transformer_blocks.5.attn.to_v.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
347 |
+
Tensor 'transformer_blocks.5.ff.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
348 |
+
Tensor 'transformer_blocks.5.ff.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
349 |
+
Tensor 'transformer_blocks.5.ff.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
350 |
+
Tensor 'transformer_blocks.5.ff.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
351 |
+
Tensor 'transformer_blocks.5.ff_context.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
352 |
+
Tensor 'transformer_blocks.5.ff_context.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
353 |
+
Tensor 'transformer_blocks.5.ff_context.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
354 |
+
Tensor 'transformer_blocks.5.ff_context.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
355 |
+
Tensor 'transformer_blocks.5.norm1.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
356 |
+
Tensor 'transformer_blocks.5.norm1.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
357 |
+
Tensor 'transformer_blocks.5.norm1_context.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
358 |
+
Tensor 'transformer_blocks.5.norm1_context.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
359 |
+
Tensor 'transformer_blocks.6.attn.add_k_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
360 |
+
Tensor 'transformer_blocks.6.attn.add_k_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
361 |
+
Tensor 'transformer_blocks.6.attn.add_q_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
362 |
+
Tensor 'transformer_blocks.6.attn.add_q_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
363 |
+
Tensor 'transformer_blocks.6.attn.add_v_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
364 |
+
Tensor 'transformer_blocks.6.attn.add_v_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
365 |
+
Tensor 'transformer_blocks.6.attn.norm_added_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
366 |
+
Tensor 'transformer_blocks.6.attn.norm_added_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
367 |
+
Tensor 'transformer_blocks.6.attn.norm_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
368 |
+
Tensor 'transformer_blocks.6.attn.norm_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
369 |
+
Tensor 'transformer_blocks.6.attn.to_add_out.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
370 |
+
Tensor 'transformer_blocks.6.attn.to_add_out.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
371 |
+
Tensor 'transformer_blocks.6.attn.to_k.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
372 |
+
Tensor 'transformer_blocks.6.attn.to_k.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
373 |
+
Tensor 'transformer_blocks.6.attn.to_out.0.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
374 |
+
Tensor 'transformer_blocks.6.attn.to_out.0.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
375 |
+
Tensor 'transformer_blocks.6.attn.to_q.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
376 |
+
Tensor 'transformer_blocks.6.attn.to_q.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
377 |
+
Tensor 'transformer_blocks.6.attn.to_v.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
378 |
+
Tensor 'transformer_blocks.6.attn.to_v.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
379 |
+
Tensor 'transformer_blocks.6.ff.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
380 |
+
Tensor 'transformer_blocks.6.ff.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
381 |
+
Tensor 'transformer_blocks.6.ff.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
382 |
+
Tensor 'transformer_blocks.6.ff.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
383 |
+
Tensor 'transformer_blocks.6.ff_context.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
384 |
+
Tensor 'transformer_blocks.6.ff_context.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
385 |
+
Tensor 'transformer_blocks.6.ff_context.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
386 |
+
Tensor 'transformer_blocks.6.ff_context.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
387 |
+
Tensor 'transformer_blocks.6.norm1.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
388 |
+
Tensor 'transformer_blocks.6.norm1.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
389 |
+
Tensor 'transformer_blocks.6.norm1_context.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
390 |
+
Tensor 'transformer_blocks.6.norm1_context.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
391 |
+
Tensor 'transformer_blocks.7.attn.add_k_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
392 |
+
Tensor 'transformer_blocks.7.attn.add_k_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
393 |
+
Tensor 'transformer_blocks.7.attn.add_q_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
394 |
+
Tensor 'transformer_blocks.7.attn.add_q_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
395 |
+
Tensor 'transformer_blocks.7.attn.add_v_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
396 |
+
Tensor 'transformer_blocks.7.attn.add_v_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
397 |
+
Tensor 'transformer_blocks.7.attn.norm_added_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
398 |
+
Tensor 'transformer_blocks.7.attn.norm_added_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
399 |
+
Tensor 'transformer_blocks.7.attn.norm_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
400 |
+
Tensor 'transformer_blocks.7.attn.norm_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
401 |
+
Tensor 'transformer_blocks.7.attn.to_add_out.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
402 |
+
Tensor 'transformer_blocks.7.attn.to_add_out.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
403 |
+
Tensor 'transformer_blocks.7.attn.to_k.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
404 |
+
Tensor 'transformer_blocks.7.attn.to_k.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
405 |
+
Tensor 'transformer_blocks.7.attn.to_out.0.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
406 |
+
Tensor 'transformer_blocks.7.attn.to_out.0.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
407 |
+
Tensor 'transformer_blocks.7.attn.to_q.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
408 |
+
Tensor 'transformer_blocks.7.attn.to_q.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
409 |
+
Tensor 'transformer_blocks.7.attn.to_v.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
410 |
+
Tensor 'transformer_blocks.7.attn.to_v.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
411 |
+
Tensor 'transformer_blocks.7.ff.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
412 |
+
Tensor 'transformer_blocks.7.ff.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
413 |
+
Tensor 'transformer_blocks.7.ff.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
414 |
+
Tensor 'transformer_blocks.7.ff.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
415 |
+
Tensor 'transformer_blocks.7.ff_context.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
416 |
+
Tensor 'transformer_blocks.7.ff_context.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
417 |
+
Tensor 'transformer_blocks.7.ff_context.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
418 |
+
Tensor 'transformer_blocks.7.ff_context.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
419 |
+
Tensor 'transformer_blocks.7.norm1.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
420 |
+
Tensor 'transformer_blocks.7.norm1.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
421 |
+
Tensor 'transformer_blocks.7.norm1_context.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
422 |
+
Tensor 'transformer_blocks.7.norm1_context.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
423 |
+
Tensor 'transformer_blocks.8.attn.add_k_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
424 |
+
Tensor 'transformer_blocks.8.attn.add_k_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
425 |
+
Tensor 'transformer_blocks.8.attn.add_q_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
426 |
+
Tensor 'transformer_blocks.8.attn.add_q_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
427 |
+
Tensor 'transformer_blocks.8.attn.add_v_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
428 |
+
Tensor 'transformer_blocks.8.attn.add_v_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
429 |
+
Tensor 'transformer_blocks.8.attn.norm_added_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
430 |
+
Tensor 'transformer_blocks.8.attn.norm_added_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
431 |
+
Tensor 'transformer_blocks.8.attn.norm_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
432 |
+
Tensor 'transformer_blocks.8.attn.norm_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
433 |
+
Tensor 'transformer_blocks.8.attn.to_add_out.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
434 |
+
Tensor 'transformer_blocks.8.attn.to_add_out.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
435 |
+
Tensor 'transformer_blocks.8.attn.to_k.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
436 |
+
Tensor 'transformer_blocks.8.attn.to_k.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
437 |
+
Tensor 'transformer_blocks.8.attn.to_out.0.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
438 |
+
Tensor 'transformer_blocks.8.attn.to_out.0.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
439 |
+
Tensor 'transformer_blocks.8.attn.to_q.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
440 |
+
Tensor 'transformer_blocks.8.attn.to_q.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
441 |
+
Tensor 'transformer_blocks.8.attn.to_v.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
442 |
+
Tensor 'transformer_blocks.8.attn.to_v.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
443 |
+
Tensor 'transformer_blocks.8.ff.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
444 |
+
Tensor 'transformer_blocks.8.ff.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
445 |
+
Tensor 'transformer_blocks.8.ff.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
446 |
+
Tensor 'transformer_blocks.8.ff.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
447 |
+
Tensor 'transformer_blocks.8.ff_context.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
448 |
+
Tensor 'transformer_blocks.8.ff_context.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
449 |
+
Tensor 'transformer_blocks.8.ff_context.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
450 |
+
Tensor 'transformer_blocks.8.ff_context.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
451 |
+
Tensor 'transformer_blocks.8.norm1.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
452 |
+
Tensor 'transformer_blocks.8.norm1.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
453 |
+
Tensor 'transformer_blocks.8.norm1_context.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
454 |
+
Tensor 'transformer_blocks.8.norm1_context.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
455 |
+
Tensor 'transformer_blocks.9.attn.add_k_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
456 |
+
Tensor 'transformer_blocks.9.attn.add_k_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
457 |
+
Tensor 'transformer_blocks.9.attn.add_q_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
458 |
+
Tensor 'transformer_blocks.9.attn.add_q_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
459 |
+
Tensor 'transformer_blocks.9.attn.add_v_proj.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
460 |
+
Tensor 'transformer_blocks.9.attn.add_v_proj.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
461 |
+
Tensor 'transformer_blocks.9.attn.norm_added_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
462 |
+
Tensor 'transformer_blocks.9.attn.norm_added_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
463 |
+
Tensor 'transformer_blocks.9.attn.norm_k.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
464 |
+
Tensor 'transformer_blocks.9.attn.norm_q.weight' has different shapes: Model 1: torch.Size([89]), Model 2: torch.Size([128])
|
465 |
+
Tensor 'transformer_blocks.9.attn.to_add_out.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
466 |
+
Tensor 'transformer_blocks.9.attn.to_add_out.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
467 |
+
Tensor 'transformer_blocks.9.attn.to_k.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
468 |
+
Tensor 'transformer_blocks.9.attn.to_k.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
469 |
+
Tensor 'transformer_blocks.9.attn.to_out.0.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
470 |
+
Tensor 'transformer_blocks.9.attn.to_out.0.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
471 |
+
Tensor 'transformer_blocks.9.attn.to_q.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
472 |
+
Tensor 'transformer_blocks.9.attn.to_q.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
473 |
+
Tensor 'transformer_blocks.9.attn.to_v.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
474 |
+
Tensor 'transformer_blocks.9.attn.to_v.weight' has different shapes: Model 1: torch.Size([2150, 3072]), Model 2: torch.Size([3072, 3072])
|
475 |
+
Tensor 'transformer_blocks.9.ff.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
476 |
+
Tensor 'transformer_blocks.9.ff.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
477 |
+
Tensor 'transformer_blocks.9.ff.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
478 |
+
Tensor 'transformer_blocks.9.ff.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
479 |
+
Tensor 'transformer_blocks.9.ff_context.net.0.proj.bias' has different shapes: Model 1: torch.Size([8601]), Model 2: torch.Size([12288])
|
480 |
+
Tensor 'transformer_blocks.9.ff_context.net.0.proj.weight' has different shapes: Model 1: torch.Size([8601, 3072]), Model 2: torch.Size([12288, 3072])
|
481 |
+
Tensor 'transformer_blocks.9.ff_context.net.2.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
482 |
+
Tensor 'transformer_blocks.9.ff_context.net.2.weight' has different shapes: Model 1: torch.Size([2150, 12288]), Model 2: torch.Size([3072, 12288])
|
483 |
+
Tensor 'transformer_blocks.9.norm1.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
484 |
+
Tensor 'transformer_blocks.9.norm1.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
485 |
+
Tensor 'transformer_blocks.9.norm1_context.linear.bias' has different shapes: Model 1: torch.Size([12902]), Model 2: torch.Size([18432])
|
486 |
+
Tensor 'transformer_blocks.9.norm1_context.linear.weight' has different shapes: Model 1: torch.Size([12902, 3072]), Model 2: torch.Size([18432, 3072])
|
487 |
+
Tensor 'x_embedder.bias' has different shapes: Model 1: torch.Size([2150]), Model 2: torch.Size([3072])
|
488 |
+
Tensor 'x_embedder.weight' has different shapes: Model 1: torch.Size([2150, 64]), Model 2: torch.Size([3072, 64])
|