Upload folder using huggingface_hub
Browse files- generation_config.json +1 -1
- model.safetensors.index.json +39 -312
generation_config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"bos_token_id": 2,
|
| 3 |
-
"cache_implementation": "
|
| 4 |
"do_sample": true,
|
| 5 |
"eos_token_id": [
|
| 6 |
1,
|
|
|
|
| 1 |
{
|
| 2 |
"bos_token_id": 2,
|
| 3 |
+
"cache_implementation": "dynamic",
|
| 4 |
"do_sample": true,
|
| 5 |
"eos_token_id": [
|
| 6 |
1,
|
model.safetensors.index.json
CHANGED
|
@@ -1,282 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_parameters":
|
| 4 |
-
"total_size":
|
| 5 |
},
|
| 6 |
"weight_map": {
|
| 7 |
-
"model.audio_tower.conformer.0.attention.attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 8 |
-
"model.audio_tower.conformer.0.attention.attn.per_dim_scale": "model-00002-of-00002.safetensors",
|
| 9 |
-
"model.audio_tower.conformer.0.attention.attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 10 |
-
"model.audio_tower.conformer.0.attention.attn.relative_position_embedding.pos_proj.weight": "model-00002-of-00002.safetensors",
|
| 11 |
-
"model.audio_tower.conformer.0.attention.attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 12 |
-
"model.audio_tower.conformer.0.attention.post.weight": "model-00002-of-00002.safetensors",
|
| 13 |
-
"model.audio_tower.conformer.0.attention.post_norm.weight": "model-00002-of-00002.safetensors",
|
| 14 |
-
"model.audio_tower.conformer.0.attention.pre_attn_norm.weight": "model-00002-of-00002.safetensors",
|
| 15 |
-
"model.audio_tower.conformer.0.ffw_layer_end.ffw_layer_1.weight": "model-00002-of-00002.safetensors",
|
| 16 |
-
"model.audio_tower.conformer.0.ffw_layer_end.ffw_layer_2.weight": "model-00002-of-00002.safetensors",
|
| 17 |
-
"model.audio_tower.conformer.0.ffw_layer_end.post_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 18 |
-
"model.audio_tower.conformer.0.ffw_layer_end.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 19 |
-
"model.audio_tower.conformer.0.ffw_layer_start.ffw_layer_1.weight": "model-00002-of-00002.safetensors",
|
| 20 |
-
"model.audio_tower.conformer.0.ffw_layer_start.ffw_layer_2.weight": "model-00002-of-00002.safetensors",
|
| 21 |
-
"model.audio_tower.conformer.0.ffw_layer_start.post_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 22 |
-
"model.audio_tower.conformer.0.ffw_layer_start.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 23 |
-
"model.audio_tower.conformer.0.lconv1d.conv_norm.weight": "model-00002-of-00002.safetensors",
|
| 24 |
-
"model.audio_tower.conformer.0.lconv1d.depthwise_conv1d.weight": "model-00002-of-00002.safetensors",
|
| 25 |
-
"model.audio_tower.conformer.0.lconv1d.linear_end.weight": "model-00002-of-00002.safetensors",
|
| 26 |
-
"model.audio_tower.conformer.0.lconv1d.linear_start.weight": "model-00002-of-00002.safetensors",
|
| 27 |
-
"model.audio_tower.conformer.0.lconv1d.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 28 |
-
"model.audio_tower.conformer.0.norm.weight": "model-00002-of-00002.safetensors",
|
| 29 |
-
"model.audio_tower.conformer.1.attention.attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 30 |
-
"model.audio_tower.conformer.1.attention.attn.per_dim_scale": "model-00002-of-00002.safetensors",
|
| 31 |
-
"model.audio_tower.conformer.1.attention.attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 32 |
-
"model.audio_tower.conformer.1.attention.attn.relative_position_embedding.pos_proj.weight": "model-00002-of-00002.safetensors",
|
| 33 |
-
"model.audio_tower.conformer.1.attention.attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 34 |
-
"model.audio_tower.conformer.1.attention.post.weight": "model-00002-of-00002.safetensors",
|
| 35 |
-
"model.audio_tower.conformer.1.attention.post_norm.weight": "model-00002-of-00002.safetensors",
|
| 36 |
-
"model.audio_tower.conformer.1.attention.pre_attn_norm.weight": "model-00002-of-00002.safetensors",
|
| 37 |
-
"model.audio_tower.conformer.1.ffw_layer_end.ffw_layer_1.weight": "model-00002-of-00002.safetensors",
|
| 38 |
-
"model.audio_tower.conformer.1.ffw_layer_end.ffw_layer_2.weight": "model-00002-of-00002.safetensors",
|
| 39 |
-
"model.audio_tower.conformer.1.ffw_layer_end.post_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 40 |
-
"model.audio_tower.conformer.1.ffw_layer_end.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 41 |
-
"model.audio_tower.conformer.1.ffw_layer_start.ffw_layer_1.weight": "model-00002-of-00002.safetensors",
|
| 42 |
-
"model.audio_tower.conformer.1.ffw_layer_start.ffw_layer_2.weight": "model-00002-of-00002.safetensors",
|
| 43 |
-
"model.audio_tower.conformer.1.ffw_layer_start.post_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 44 |
-
"model.audio_tower.conformer.1.ffw_layer_start.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 45 |
-
"model.audio_tower.conformer.1.lconv1d.conv_norm.weight": "model-00002-of-00002.safetensors",
|
| 46 |
-
"model.audio_tower.conformer.1.lconv1d.depthwise_conv1d.weight": "model-00002-of-00002.safetensors",
|
| 47 |
-
"model.audio_tower.conformer.1.lconv1d.linear_end.weight": "model-00002-of-00002.safetensors",
|
| 48 |
-
"model.audio_tower.conformer.1.lconv1d.linear_start.weight": "model-00002-of-00002.safetensors",
|
| 49 |
-
"model.audio_tower.conformer.1.lconv1d.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 50 |
-
"model.audio_tower.conformer.1.norm.weight": "model-00002-of-00002.safetensors",
|
| 51 |
-
"model.audio_tower.conformer.10.attention.attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 52 |
-
"model.audio_tower.conformer.10.attention.attn.per_dim_scale": "model-00002-of-00002.safetensors",
|
| 53 |
-
"model.audio_tower.conformer.10.attention.attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 54 |
-
"model.audio_tower.conformer.10.attention.attn.relative_position_embedding.pos_proj.weight": "model-00002-of-00002.safetensors",
|
| 55 |
-
"model.audio_tower.conformer.10.attention.attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 56 |
-
"model.audio_tower.conformer.10.attention.post.weight": "model-00002-of-00002.safetensors",
|
| 57 |
-
"model.audio_tower.conformer.10.attention.post_norm.weight": "model-00002-of-00002.safetensors",
|
| 58 |
-
"model.audio_tower.conformer.10.attention.pre_attn_norm.weight": "model-00002-of-00002.safetensors",
|
| 59 |
-
"model.audio_tower.conformer.10.ffw_layer_end.ffw_layer_1.weight": "model-00002-of-00002.safetensors",
|
| 60 |
-
"model.audio_tower.conformer.10.ffw_layer_end.ffw_layer_2.weight": "model-00002-of-00002.safetensors",
|
| 61 |
-
"model.audio_tower.conformer.10.ffw_layer_end.post_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 62 |
-
"model.audio_tower.conformer.10.ffw_layer_end.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 63 |
-
"model.audio_tower.conformer.10.ffw_layer_start.ffw_layer_1.weight": "model-00002-of-00002.safetensors",
|
| 64 |
-
"model.audio_tower.conformer.10.ffw_layer_start.ffw_layer_2.weight": "model-00002-of-00002.safetensors",
|
| 65 |
-
"model.audio_tower.conformer.10.ffw_layer_start.post_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 66 |
-
"model.audio_tower.conformer.10.ffw_layer_start.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 67 |
-
"model.audio_tower.conformer.10.lconv1d.conv_norm.weight": "model-00002-of-00002.safetensors",
|
| 68 |
-
"model.audio_tower.conformer.10.lconv1d.depthwise_conv1d.weight": "model-00002-of-00002.safetensors",
|
| 69 |
-
"model.audio_tower.conformer.10.lconv1d.linear_end.weight": "model-00002-of-00002.safetensors",
|
| 70 |
-
"model.audio_tower.conformer.10.lconv1d.linear_start.weight": "model-00002-of-00002.safetensors",
|
| 71 |
-
"model.audio_tower.conformer.10.lconv1d.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 72 |
-
"model.audio_tower.conformer.10.norm.weight": "model-00002-of-00002.safetensors",
|
| 73 |
-
"model.audio_tower.conformer.11.attention.attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 74 |
-
"model.audio_tower.conformer.11.attention.attn.per_dim_scale": "model-00002-of-00002.safetensors",
|
| 75 |
-
"model.audio_tower.conformer.11.attention.attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 76 |
-
"model.audio_tower.conformer.11.attention.attn.relative_position_embedding.pos_proj.weight": "model-00002-of-00002.safetensors",
|
| 77 |
-
"model.audio_tower.conformer.11.attention.attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 78 |
-
"model.audio_tower.conformer.11.attention.post.weight": "model-00002-of-00002.safetensors",
|
| 79 |
-
"model.audio_tower.conformer.11.attention.post_norm.weight": "model-00002-of-00002.safetensors",
|
| 80 |
-
"model.audio_tower.conformer.11.attention.pre_attn_norm.weight": "model-00002-of-00002.safetensors",
|
| 81 |
-
"model.audio_tower.conformer.11.ffw_layer_end.ffw_layer_1.weight": "model-00002-of-00002.safetensors",
|
| 82 |
-
"model.audio_tower.conformer.11.ffw_layer_end.ffw_layer_2.weight": "model-00002-of-00002.safetensors",
|
| 83 |
-
"model.audio_tower.conformer.11.ffw_layer_end.post_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 84 |
-
"model.audio_tower.conformer.11.ffw_layer_end.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 85 |
-
"model.audio_tower.conformer.11.ffw_layer_start.ffw_layer_1.weight": "model-00002-of-00002.safetensors",
|
| 86 |
-
"model.audio_tower.conformer.11.ffw_layer_start.ffw_layer_2.weight": "model-00002-of-00002.safetensors",
|
| 87 |
-
"model.audio_tower.conformer.11.ffw_layer_start.post_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 88 |
-
"model.audio_tower.conformer.11.ffw_layer_start.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 89 |
-
"model.audio_tower.conformer.11.lconv1d.conv_norm.weight": "model-00002-of-00002.safetensors",
|
| 90 |
-
"model.audio_tower.conformer.11.lconv1d.depthwise_conv1d.weight": "model-00002-of-00002.safetensors",
|
| 91 |
-
"model.audio_tower.conformer.11.lconv1d.linear_end.weight": "model-00002-of-00002.safetensors",
|
| 92 |
-
"model.audio_tower.conformer.11.lconv1d.linear_start.weight": "model-00002-of-00002.safetensors",
|
| 93 |
-
"model.audio_tower.conformer.11.lconv1d.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 94 |
-
"model.audio_tower.conformer.11.norm.weight": "model-00002-of-00002.safetensors",
|
| 95 |
-
"model.audio_tower.conformer.2.attention.attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 96 |
-
"model.audio_tower.conformer.2.attention.attn.per_dim_scale": "model-00002-of-00002.safetensors",
|
| 97 |
-
"model.audio_tower.conformer.2.attention.attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 98 |
-
"model.audio_tower.conformer.2.attention.attn.relative_position_embedding.pos_proj.weight": "model-00002-of-00002.safetensors",
|
| 99 |
-
"model.audio_tower.conformer.2.attention.attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 100 |
-
"model.audio_tower.conformer.2.attention.post.weight": "model-00002-of-00002.safetensors",
|
| 101 |
-
"model.audio_tower.conformer.2.attention.post_norm.weight": "model-00002-of-00002.safetensors",
|
| 102 |
-
"model.audio_tower.conformer.2.attention.pre_attn_norm.weight": "model-00002-of-00002.safetensors",
|
| 103 |
-
"model.audio_tower.conformer.2.ffw_layer_end.ffw_layer_1.weight": "model-00002-of-00002.safetensors",
|
| 104 |
-
"model.audio_tower.conformer.2.ffw_layer_end.ffw_layer_2.weight": "model-00002-of-00002.safetensors",
|
| 105 |
-
"model.audio_tower.conformer.2.ffw_layer_end.post_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 106 |
-
"model.audio_tower.conformer.2.ffw_layer_end.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 107 |
-
"model.audio_tower.conformer.2.ffw_layer_start.ffw_layer_1.weight": "model-00002-of-00002.safetensors",
|
| 108 |
-
"model.audio_tower.conformer.2.ffw_layer_start.ffw_layer_2.weight": "model-00002-of-00002.safetensors",
|
| 109 |
-
"model.audio_tower.conformer.2.ffw_layer_start.post_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 110 |
-
"model.audio_tower.conformer.2.ffw_layer_start.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 111 |
-
"model.audio_tower.conformer.2.lconv1d.conv_norm.weight": "model-00002-of-00002.safetensors",
|
| 112 |
-
"model.audio_tower.conformer.2.lconv1d.depthwise_conv1d.weight": "model-00002-of-00002.safetensors",
|
| 113 |
-
"model.audio_tower.conformer.2.lconv1d.linear_end.weight": "model-00002-of-00002.safetensors",
|
| 114 |
-
"model.audio_tower.conformer.2.lconv1d.linear_start.weight": "model-00002-of-00002.safetensors",
|
| 115 |
-
"model.audio_tower.conformer.2.lconv1d.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 116 |
-
"model.audio_tower.conformer.2.norm.weight": "model-00002-of-00002.safetensors",
|
| 117 |
-
"model.audio_tower.conformer.3.attention.attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 118 |
-
"model.audio_tower.conformer.3.attention.attn.per_dim_scale": "model-00002-of-00002.safetensors",
|
| 119 |
-
"model.audio_tower.conformer.3.attention.attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 120 |
-
"model.audio_tower.conformer.3.attention.attn.relative_position_embedding.pos_proj.weight": "model-00002-of-00002.safetensors",
|
| 121 |
-
"model.audio_tower.conformer.3.attention.attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 122 |
-
"model.audio_tower.conformer.3.attention.post.weight": "model-00002-of-00002.safetensors",
|
| 123 |
-
"model.audio_tower.conformer.3.attention.post_norm.weight": "model-00002-of-00002.safetensors",
|
| 124 |
-
"model.audio_tower.conformer.3.attention.pre_attn_norm.weight": "model-00002-of-00002.safetensors",
|
| 125 |
-
"model.audio_tower.conformer.3.ffw_layer_end.ffw_layer_1.weight": "model-00002-of-00002.safetensors",
|
| 126 |
-
"model.audio_tower.conformer.3.ffw_layer_end.ffw_layer_2.weight": "model-00002-of-00002.safetensors",
|
| 127 |
-
"model.audio_tower.conformer.3.ffw_layer_end.post_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 128 |
-
"model.audio_tower.conformer.3.ffw_layer_end.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 129 |
-
"model.audio_tower.conformer.3.ffw_layer_start.ffw_layer_1.weight": "model-00002-of-00002.safetensors",
|
| 130 |
-
"model.audio_tower.conformer.3.ffw_layer_start.ffw_layer_2.weight": "model-00002-of-00002.safetensors",
|
| 131 |
-
"model.audio_tower.conformer.3.ffw_layer_start.post_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 132 |
-
"model.audio_tower.conformer.3.ffw_layer_start.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 133 |
-
"model.audio_tower.conformer.3.lconv1d.conv_norm.weight": "model-00002-of-00002.safetensors",
|
| 134 |
-
"model.audio_tower.conformer.3.lconv1d.depthwise_conv1d.weight": "model-00002-of-00002.safetensors",
|
| 135 |
-
"model.audio_tower.conformer.3.lconv1d.linear_end.weight": "model-00002-of-00002.safetensors",
|
| 136 |
-
"model.audio_tower.conformer.3.lconv1d.linear_start.weight": "model-00002-of-00002.safetensors",
|
| 137 |
-
"model.audio_tower.conformer.3.lconv1d.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 138 |
-
"model.audio_tower.conformer.3.norm.weight": "model-00002-of-00002.safetensors",
|
| 139 |
-
"model.audio_tower.conformer.4.attention.attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 140 |
-
"model.audio_tower.conformer.4.attention.attn.per_dim_scale": "model-00002-of-00002.safetensors",
|
| 141 |
-
"model.audio_tower.conformer.4.attention.attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 142 |
-
"model.audio_tower.conformer.4.attention.attn.relative_position_embedding.pos_proj.weight": "model-00002-of-00002.safetensors",
|
| 143 |
-
"model.audio_tower.conformer.4.attention.attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 144 |
-
"model.audio_tower.conformer.4.attention.post.weight": "model-00002-of-00002.safetensors",
|
| 145 |
-
"model.audio_tower.conformer.4.attention.post_norm.weight": "model-00002-of-00002.safetensors",
|
| 146 |
-
"model.audio_tower.conformer.4.attention.pre_attn_norm.weight": "model-00002-of-00002.safetensors",
|
| 147 |
-
"model.audio_tower.conformer.4.ffw_layer_end.ffw_layer_1.weight": "model-00002-of-00002.safetensors",
|
| 148 |
-
"model.audio_tower.conformer.4.ffw_layer_end.ffw_layer_2.weight": "model-00002-of-00002.safetensors",
|
| 149 |
-
"model.audio_tower.conformer.4.ffw_layer_end.post_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 150 |
-
"model.audio_tower.conformer.4.ffw_layer_end.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 151 |
-
"model.audio_tower.conformer.4.ffw_layer_start.ffw_layer_1.weight": "model-00002-of-00002.safetensors",
|
| 152 |
-
"model.audio_tower.conformer.4.ffw_layer_start.ffw_layer_2.weight": "model-00002-of-00002.safetensors",
|
| 153 |
-
"model.audio_tower.conformer.4.ffw_layer_start.post_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 154 |
-
"model.audio_tower.conformer.4.ffw_layer_start.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 155 |
-
"model.audio_tower.conformer.4.lconv1d.conv_norm.weight": "model-00002-of-00002.safetensors",
|
| 156 |
-
"model.audio_tower.conformer.4.lconv1d.depthwise_conv1d.weight": "model-00002-of-00002.safetensors",
|
| 157 |
-
"model.audio_tower.conformer.4.lconv1d.linear_end.weight": "model-00002-of-00002.safetensors",
|
| 158 |
-
"model.audio_tower.conformer.4.lconv1d.linear_start.weight": "model-00002-of-00002.safetensors",
|
| 159 |
-
"model.audio_tower.conformer.4.lconv1d.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 160 |
-
"model.audio_tower.conformer.4.norm.weight": "model-00002-of-00002.safetensors",
|
| 161 |
-
"model.audio_tower.conformer.5.attention.attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 162 |
-
"model.audio_tower.conformer.5.attention.attn.per_dim_scale": "model-00002-of-00002.safetensors",
|
| 163 |
-
"model.audio_tower.conformer.5.attention.attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 164 |
-
"model.audio_tower.conformer.5.attention.attn.relative_position_embedding.pos_proj.weight": "model-00002-of-00002.safetensors",
|
| 165 |
-
"model.audio_tower.conformer.5.attention.attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 166 |
-
"model.audio_tower.conformer.5.attention.post.weight": "model-00002-of-00002.safetensors",
|
| 167 |
-
"model.audio_tower.conformer.5.attention.post_norm.weight": "model-00002-of-00002.safetensors",
|
| 168 |
-
"model.audio_tower.conformer.5.attention.pre_attn_norm.weight": "model-00002-of-00002.safetensors",
|
| 169 |
-
"model.audio_tower.conformer.5.ffw_layer_end.ffw_layer_1.weight": "model-00002-of-00002.safetensors",
|
| 170 |
-
"model.audio_tower.conformer.5.ffw_layer_end.ffw_layer_2.weight": "model-00002-of-00002.safetensors",
|
| 171 |
-
"model.audio_tower.conformer.5.ffw_layer_end.post_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 172 |
-
"model.audio_tower.conformer.5.ffw_layer_end.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 173 |
-
"model.audio_tower.conformer.5.ffw_layer_start.ffw_layer_1.weight": "model-00002-of-00002.safetensors",
|
| 174 |
-
"model.audio_tower.conformer.5.ffw_layer_start.ffw_layer_2.weight": "model-00002-of-00002.safetensors",
|
| 175 |
-
"model.audio_tower.conformer.5.ffw_layer_start.post_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 176 |
-
"model.audio_tower.conformer.5.ffw_layer_start.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 177 |
-
"model.audio_tower.conformer.5.lconv1d.conv_norm.weight": "model-00002-of-00002.safetensors",
|
| 178 |
-
"model.audio_tower.conformer.5.lconv1d.depthwise_conv1d.weight": "model-00002-of-00002.safetensors",
|
| 179 |
-
"model.audio_tower.conformer.5.lconv1d.linear_end.weight": "model-00002-of-00002.safetensors",
|
| 180 |
-
"model.audio_tower.conformer.5.lconv1d.linear_start.weight": "model-00002-of-00002.safetensors",
|
| 181 |
-
"model.audio_tower.conformer.5.lconv1d.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 182 |
-
"model.audio_tower.conformer.5.norm.weight": "model-00002-of-00002.safetensors",
|
| 183 |
-
"model.audio_tower.conformer.6.attention.attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 184 |
-
"model.audio_tower.conformer.6.attention.attn.per_dim_scale": "model-00002-of-00002.safetensors",
|
| 185 |
-
"model.audio_tower.conformer.6.attention.attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 186 |
-
"model.audio_tower.conformer.6.attention.attn.relative_position_embedding.pos_proj.weight": "model-00002-of-00002.safetensors",
|
| 187 |
-
"model.audio_tower.conformer.6.attention.attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
-
"model.audio_tower.conformer.6.attention.post.weight": "model-00002-of-00002.safetensors",
|
| 189 |
-
"model.audio_tower.conformer.6.attention.post_norm.weight": "model-00002-of-00002.safetensors",
|
| 190 |
-
"model.audio_tower.conformer.6.attention.pre_attn_norm.weight": "model-00002-of-00002.safetensors",
|
| 191 |
-
"model.audio_tower.conformer.6.ffw_layer_end.ffw_layer_1.weight": "model-00002-of-00002.safetensors",
|
| 192 |
-
"model.audio_tower.conformer.6.ffw_layer_end.ffw_layer_2.weight": "model-00002-of-00002.safetensors",
|
| 193 |
-
"model.audio_tower.conformer.6.ffw_layer_end.post_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 194 |
-
"model.audio_tower.conformer.6.ffw_layer_end.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 195 |
-
"model.audio_tower.conformer.6.ffw_layer_start.ffw_layer_1.weight": "model-00002-of-00002.safetensors",
|
| 196 |
-
"model.audio_tower.conformer.6.ffw_layer_start.ffw_layer_2.weight": "model-00002-of-00002.safetensors",
|
| 197 |
-
"model.audio_tower.conformer.6.ffw_layer_start.post_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 198 |
-
"model.audio_tower.conformer.6.ffw_layer_start.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 199 |
-
"model.audio_tower.conformer.6.lconv1d.conv_norm.weight": "model-00002-of-00002.safetensors",
|
| 200 |
-
"model.audio_tower.conformer.6.lconv1d.depthwise_conv1d.weight": "model-00002-of-00002.safetensors",
|
| 201 |
-
"model.audio_tower.conformer.6.lconv1d.linear_end.weight": "model-00002-of-00002.safetensors",
|
| 202 |
-
"model.audio_tower.conformer.6.lconv1d.linear_start.weight": "model-00002-of-00002.safetensors",
|
| 203 |
-
"model.audio_tower.conformer.6.lconv1d.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 204 |
-
"model.audio_tower.conformer.6.norm.weight": "model-00002-of-00002.safetensors",
|
| 205 |
-
"model.audio_tower.conformer.7.attention.attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 206 |
-
"model.audio_tower.conformer.7.attention.attn.per_dim_scale": "model-00002-of-00002.safetensors",
|
| 207 |
-
"model.audio_tower.conformer.7.attention.attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
-
"model.audio_tower.conformer.7.attention.attn.relative_position_embedding.pos_proj.weight": "model-00002-of-00002.safetensors",
|
| 209 |
-
"model.audio_tower.conformer.7.attention.attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 210 |
-
"model.audio_tower.conformer.7.attention.post.weight": "model-00002-of-00002.safetensors",
|
| 211 |
-
"model.audio_tower.conformer.7.attention.post_norm.weight": "model-00002-of-00002.safetensors",
|
| 212 |
-
"model.audio_tower.conformer.7.attention.pre_attn_norm.weight": "model-00002-of-00002.safetensors",
|
| 213 |
-
"model.audio_tower.conformer.7.ffw_layer_end.ffw_layer_1.weight": "model-00002-of-00002.safetensors",
|
| 214 |
-
"model.audio_tower.conformer.7.ffw_layer_end.ffw_layer_2.weight": "model-00002-of-00002.safetensors",
|
| 215 |
-
"model.audio_tower.conformer.7.ffw_layer_end.post_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 216 |
-
"model.audio_tower.conformer.7.ffw_layer_end.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 217 |
-
"model.audio_tower.conformer.7.ffw_layer_start.ffw_layer_1.weight": "model-00002-of-00002.safetensors",
|
| 218 |
-
"model.audio_tower.conformer.7.ffw_layer_start.ffw_layer_2.weight": "model-00002-of-00002.safetensors",
|
| 219 |
-
"model.audio_tower.conformer.7.ffw_layer_start.post_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 220 |
-
"model.audio_tower.conformer.7.ffw_layer_start.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 221 |
-
"model.audio_tower.conformer.7.lconv1d.conv_norm.weight": "model-00002-of-00002.safetensors",
|
| 222 |
-
"model.audio_tower.conformer.7.lconv1d.depthwise_conv1d.weight": "model-00002-of-00002.safetensors",
|
| 223 |
-
"model.audio_tower.conformer.7.lconv1d.linear_end.weight": "model-00002-of-00002.safetensors",
|
| 224 |
-
"model.audio_tower.conformer.7.lconv1d.linear_start.weight": "model-00002-of-00002.safetensors",
|
| 225 |
-
"model.audio_tower.conformer.7.lconv1d.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 226 |
-
"model.audio_tower.conformer.7.norm.weight": "model-00002-of-00002.safetensors",
|
| 227 |
-
"model.audio_tower.conformer.8.attention.attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 228 |
-
"model.audio_tower.conformer.8.attention.attn.per_dim_scale": "model-00002-of-00002.safetensors",
|
| 229 |
-
"model.audio_tower.conformer.8.attention.attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
-
"model.audio_tower.conformer.8.attention.attn.relative_position_embedding.pos_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
-
"model.audio_tower.conformer.8.attention.attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 232 |
-
"model.audio_tower.conformer.8.attention.post.weight": "model-00002-of-00002.safetensors",
|
| 233 |
-
"model.audio_tower.conformer.8.attention.post_norm.weight": "model-00002-of-00002.safetensors",
|
| 234 |
-
"model.audio_tower.conformer.8.attention.pre_attn_norm.weight": "model-00002-of-00002.safetensors",
|
| 235 |
-
"model.audio_tower.conformer.8.ffw_layer_end.ffw_layer_1.weight": "model-00002-of-00002.safetensors",
|
| 236 |
-
"model.audio_tower.conformer.8.ffw_layer_end.ffw_layer_2.weight": "model-00002-of-00002.safetensors",
|
| 237 |
-
"model.audio_tower.conformer.8.ffw_layer_end.post_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 238 |
-
"model.audio_tower.conformer.8.ffw_layer_end.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 239 |
-
"model.audio_tower.conformer.8.ffw_layer_start.ffw_layer_1.weight": "model-00002-of-00002.safetensors",
|
| 240 |
-
"model.audio_tower.conformer.8.ffw_layer_start.ffw_layer_2.weight": "model-00002-of-00002.safetensors",
|
| 241 |
-
"model.audio_tower.conformer.8.ffw_layer_start.post_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 242 |
-
"model.audio_tower.conformer.8.ffw_layer_start.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 243 |
-
"model.audio_tower.conformer.8.lconv1d.conv_norm.weight": "model-00002-of-00002.safetensors",
|
| 244 |
-
"model.audio_tower.conformer.8.lconv1d.depthwise_conv1d.weight": "model-00002-of-00002.safetensors",
|
| 245 |
-
"model.audio_tower.conformer.8.lconv1d.linear_end.weight": "model-00002-of-00002.safetensors",
|
| 246 |
-
"model.audio_tower.conformer.8.lconv1d.linear_start.weight": "model-00002-of-00002.safetensors",
|
| 247 |
-
"model.audio_tower.conformer.8.lconv1d.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 248 |
-
"model.audio_tower.conformer.8.norm.weight": "model-00002-of-00002.safetensors",
|
| 249 |
-
"model.audio_tower.conformer.9.attention.attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 250 |
-
"model.audio_tower.conformer.9.attention.attn.per_dim_scale": "model-00002-of-00002.safetensors",
|
| 251 |
-
"model.audio_tower.conformer.9.attention.attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 252 |
-
"model.audio_tower.conformer.9.attention.attn.relative_position_embedding.pos_proj.weight": "model-00002-of-00002.safetensors",
|
| 253 |
-
"model.audio_tower.conformer.9.attention.attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 254 |
-
"model.audio_tower.conformer.9.attention.post.weight": "model-00002-of-00002.safetensors",
|
| 255 |
-
"model.audio_tower.conformer.9.attention.post_norm.weight": "model-00002-of-00002.safetensors",
|
| 256 |
-
"model.audio_tower.conformer.9.attention.pre_attn_norm.weight": "model-00002-of-00002.safetensors",
|
| 257 |
-
"model.audio_tower.conformer.9.ffw_layer_end.ffw_layer_1.weight": "model-00002-of-00002.safetensors",
|
| 258 |
-
"model.audio_tower.conformer.9.ffw_layer_end.ffw_layer_2.weight": "model-00002-of-00002.safetensors",
|
| 259 |
-
"model.audio_tower.conformer.9.ffw_layer_end.post_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 260 |
-
"model.audio_tower.conformer.9.ffw_layer_end.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 261 |
-
"model.audio_tower.conformer.9.ffw_layer_start.ffw_layer_1.weight": "model-00002-of-00002.safetensors",
|
| 262 |
-
"model.audio_tower.conformer.9.ffw_layer_start.ffw_layer_2.weight": "model-00002-of-00002.safetensors",
|
| 263 |
-
"model.audio_tower.conformer.9.ffw_layer_start.post_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 264 |
-
"model.audio_tower.conformer.9.ffw_layer_start.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 265 |
-
"model.audio_tower.conformer.9.lconv1d.conv_norm.weight": "model-00002-of-00002.safetensors",
|
| 266 |
-
"model.audio_tower.conformer.9.lconv1d.depthwise_conv1d.weight": "model-00002-of-00002.safetensors",
|
| 267 |
-
"model.audio_tower.conformer.9.lconv1d.linear_end.weight": "model-00002-of-00002.safetensors",
|
| 268 |
-
"model.audio_tower.conformer.9.lconv1d.linear_start.weight": "model-00002-of-00002.safetensors",
|
| 269 |
-
"model.audio_tower.conformer.9.lconv1d.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 270 |
-
"model.audio_tower.conformer.9.norm.weight": "model-00002-of-00002.safetensors",
|
| 271 |
-
"model.audio_tower.subsample_conv_projection.conv_0.conv.weight": "model-00002-of-00002.safetensors",
|
| 272 |
-
"model.audio_tower.subsample_conv_projection.conv_0.norm.weight": "model-00002-of-00002.safetensors",
|
| 273 |
-
"model.audio_tower.subsample_conv_projection.conv_1.conv.weight": "model-00002-of-00002.safetensors",
|
| 274 |
-
"model.audio_tower.subsample_conv_projection.conv_1.norm.weight": "model-00002-of-00002.safetensors",
|
| 275 |
-
"model.audio_tower.subsample_conv_projection.input_proj_linear.weight": "model-00002-of-00002.safetensors",
|
| 276 |
-
"model.embed_audio.embedding.weight": "model-00002-of-00002.safetensors",
|
| 277 |
-
"model.embed_audio.embedding_projection.weight": "model-00002-of-00002.safetensors",
|
| 278 |
-
"model.embed_audio.hard_embedding_norm.weight": "model-00002-of-00002.safetensors",
|
| 279 |
-
"model.embed_audio.soft_embedding_norm.weight": "model-00002-of-00002.safetensors",
|
| 280 |
"model.embed_vision.embedding.weight": "model-00002-of-00002.safetensors",
|
| 281 |
"model.embed_vision.embedding_projection.weight": "model-00002-of-00002.safetensors",
|
| 282 |
"model.embed_vision.hard_embedding_norm.weight": "model-00002-of-00002.safetensors",
|
|
@@ -299,36 +26,36 @@
|
|
| 299 |
"model.language_model.layers.1.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 300 |
"model.language_model.layers.1.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 301 |
"model.language_model.layers.1.operator_norm.weight": "model-00001-of-00002.safetensors",
|
| 302 |
-
"model.language_model.layers.10.feed_forward.w1.weight": "model-
|
| 303 |
-
"model.language_model.layers.10.feed_forward.w2.weight": "model-
|
| 304 |
-
"model.language_model.layers.10.feed_forward.w3.weight": "model-
|
| 305 |
-
"model.language_model.layers.10.ffn_norm.weight": "model-
|
| 306 |
-
"model.language_model.layers.10.operator_norm.weight": "model-
|
| 307 |
-
"model.language_model.layers.10.self_attn.k_layernorm.weight": "model-
|
| 308 |
-
"model.language_model.layers.10.self_attn.k_proj.weight": "model-
|
| 309 |
-
"model.language_model.layers.10.self_attn.out_proj.weight": "model-
|
| 310 |
-
"model.language_model.layers.10.self_attn.q_layernorm.weight": "model-
|
| 311 |
-
"model.language_model.layers.10.self_attn.q_proj.weight": "model-
|
| 312 |
-
"model.language_model.layers.10.self_attn.v_proj.weight": "model-
|
| 313 |
-
"model.language_model.layers.11.conv.conv.weight": "model-
|
| 314 |
-
"model.language_model.layers.11.conv.in_proj.weight": "model-
|
| 315 |
-
"model.language_model.layers.11.conv.out_proj.weight": "model-
|
| 316 |
-
"model.language_model.layers.11.feed_forward.w1.weight": "model-
|
| 317 |
-
"model.language_model.layers.11.feed_forward.w2.weight": "model-
|
| 318 |
-
"model.language_model.layers.11.feed_forward.w3.weight": "model-
|
| 319 |
-
"model.language_model.layers.11.ffn_norm.weight": "model-
|
| 320 |
-
"model.language_model.layers.11.operator_norm.weight": "model-
|
| 321 |
-
"model.language_model.layers.12.feed_forward.w1.weight": "model-
|
| 322 |
"model.language_model.layers.12.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 323 |
"model.language_model.layers.12.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 324 |
"model.language_model.layers.12.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 325 |
"model.language_model.layers.12.operator_norm.weight": "model-00002-of-00002.safetensors",
|
| 326 |
-
"model.language_model.layers.12.self_attn.k_layernorm.weight": "model-
|
| 327 |
-
"model.language_model.layers.12.self_attn.k_proj.weight": "model-
|
| 328 |
-
"model.language_model.layers.12.self_attn.out_proj.weight": "model-
|
| 329 |
-
"model.language_model.layers.12.self_attn.q_layernorm.weight": "model-
|
| 330 |
-
"model.language_model.layers.12.self_attn.q_proj.weight": "model-
|
| 331 |
-
"model.language_model.layers.12.self_attn.v_proj.weight": "model-
|
| 332 |
"model.language_model.layers.13.conv.conv.weight": "model-00002-of-00002.safetensors",
|
| 333 |
"model.language_model.layers.13.conv.in_proj.weight": "model-00002-of-00002.safetensors",
|
| 334 |
"model.language_model.layers.13.conv.out_proj.weight": "model-00002-of-00002.safetensors",
|
|
@@ -411,24 +138,24 @@
|
|
| 411 |
"model.language_model.layers.7.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 412 |
"model.language_model.layers.7.operator_norm.weight": "model-00001-of-00002.safetensors",
|
| 413 |
"model.language_model.layers.8.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 414 |
-
"model.language_model.layers.8.feed_forward.w2.weight": "model-
|
| 415 |
"model.language_model.layers.8.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 416 |
-
"model.language_model.layers.8.ffn_norm.weight": "model-
|
| 417 |
-
"model.language_model.layers.8.operator_norm.weight": "model-
|
| 418 |
"model.language_model.layers.8.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 419 |
"model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 420 |
"model.language_model.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 421 |
"model.language_model.layers.8.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 422 |
"model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 423 |
"model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 424 |
-
"model.language_model.layers.9.conv.conv.weight": "model-
|
| 425 |
-
"model.language_model.layers.9.conv.in_proj.weight": "model-
|
| 426 |
-
"model.language_model.layers.9.conv.out_proj.weight": "model-
|
| 427 |
-
"model.language_model.layers.9.feed_forward.w1.weight": "model-
|
| 428 |
-
"model.language_model.layers.9.feed_forward.w2.weight": "model-
|
| 429 |
-
"model.language_model.layers.9.feed_forward.w3.weight": "model-
|
| 430 |
-
"model.language_model.layers.9.ffn_norm.weight": "model-
|
| 431 |
-
"model.language_model.layers.9.operator_norm.weight": "model-
|
| 432 |
"model.vision_tower.timm_model.blocks.0.0.bn1.weight": "model-00001-of-00002.safetensors",
|
| 433 |
"model.vision_tower.timm_model.blocks.0.0.bn2.weight": "model-00001-of-00002.safetensors",
|
| 434 |
"model.vision_tower.timm_model.blocks.0.0.conv_exp.weight": "model-00001-of-00002.safetensors",
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_parameters": 1466607680,
|
| 4 |
+
"total_size": 2933215360
|
| 5 |
},
|
| 6 |
"weight_map": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
"model.embed_vision.embedding.weight": "model-00002-of-00002.safetensors",
|
| 8 |
"model.embed_vision.embedding_projection.weight": "model-00002-of-00002.safetensors",
|
| 9 |
"model.embed_vision.hard_embedding_norm.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 26 |
"model.language_model.layers.1.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 27 |
"model.language_model.layers.1.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 28 |
"model.language_model.layers.1.operator_norm.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.language_model.layers.10.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 30 |
+
"model.language_model.layers.10.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 31 |
+
"model.language_model.layers.10.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 32 |
+
"model.language_model.layers.10.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 33 |
+
"model.language_model.layers.10.operator_norm.weight": "model-00002-of-00002.safetensors",
|
| 34 |
+
"model.language_model.layers.10.self_attn.k_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 35 |
+
"model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 36 |
+
"model.language_model.layers.10.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 37 |
+
"model.language_model.layers.10.self_attn.q_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 38 |
+
"model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 39 |
+
"model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 40 |
+
"model.language_model.layers.11.conv.conv.weight": "model-00002-of-00002.safetensors",
|
| 41 |
+
"model.language_model.layers.11.conv.in_proj.weight": "model-00002-of-00002.safetensors",
|
| 42 |
+
"model.language_model.layers.11.conv.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 43 |
+
"model.language_model.layers.11.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 44 |
+
"model.language_model.layers.11.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 45 |
+
"model.language_model.layers.11.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 46 |
+
"model.language_model.layers.11.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 47 |
+
"model.language_model.layers.11.operator_norm.weight": "model-00002-of-00002.safetensors",
|
| 48 |
+
"model.language_model.layers.12.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 49 |
"model.language_model.layers.12.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 50 |
"model.language_model.layers.12.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 51 |
"model.language_model.layers.12.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 52 |
"model.language_model.layers.12.operator_norm.weight": "model-00002-of-00002.safetensors",
|
| 53 |
+
"model.language_model.layers.12.self_attn.k_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 54 |
+
"model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 55 |
+
"model.language_model.layers.12.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 56 |
+
"model.language_model.layers.12.self_attn.q_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 57 |
+
"model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 58 |
+
"model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 59 |
"model.language_model.layers.13.conv.conv.weight": "model-00002-of-00002.safetensors",
|
| 60 |
"model.language_model.layers.13.conv.in_proj.weight": "model-00002-of-00002.safetensors",
|
| 61 |
"model.language_model.layers.13.conv.out_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 138 |
"model.language_model.layers.7.ffn_norm.weight": "model-00001-of-00002.safetensors",
|
| 139 |
"model.language_model.layers.7.operator_norm.weight": "model-00001-of-00002.safetensors",
|
| 140 |
"model.language_model.layers.8.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.language_model.layers.8.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 142 |
"model.language_model.layers.8.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.language_model.layers.8.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 144 |
+
"model.language_model.layers.8.operator_norm.weight": "model-00002-of-00002.safetensors",
|
| 145 |
"model.language_model.layers.8.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 146 |
"model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
"model.language_model.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
"model.language_model.layers.8.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 149 |
"model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
"model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.language_model.layers.9.conv.conv.weight": "model-00002-of-00002.safetensors",
|
| 152 |
+
"model.language_model.layers.9.conv.in_proj.weight": "model-00002-of-00002.safetensors",
|
| 153 |
+
"model.language_model.layers.9.conv.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"model.language_model.layers.9.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
|
| 155 |
+
"model.language_model.layers.9.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"model.language_model.layers.9.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
|
| 157 |
+
"model.language_model.layers.9.ffn_norm.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"model.language_model.layers.9.operator_norm.weight": "model-00002-of-00002.safetensors",
|
| 159 |
"model.vision_tower.timm_model.blocks.0.0.bn1.weight": "model-00001-of-00002.safetensors",
|
| 160 |
"model.vision_tower.timm_model.blocks.0.0.bn2.weight": "model-00001-of-00002.safetensors",
|
| 161 |
"model.vision_tower.timm_model.blocks.0.0.conv_exp.weight": "model-00001-of-00002.safetensors",
|