Upload GemmaForCausalLM
Browse files- config.json +2 -2
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +165 -165
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "hannam-2b/checkpoint-
|
| 3 |
"architectures": [
|
| 4 |
"GemmaForCausalLM"
|
| 5 |
],
|
|
@@ -21,7 +21,7 @@
|
|
| 21 |
"rms_norm_eps": 1e-06,
|
| 22 |
"rope_scaling": null,
|
| 23 |
"rope_theta": 10000.0,
|
| 24 |
-
"torch_dtype": "
|
| 25 |
"transformers_version": "4.38.1",
|
| 26 |
"use_cache": true,
|
| 27 |
"vocab_size": 256000
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "hannam-2b/checkpoint-30000",
|
| 3 |
"architectures": [
|
| 4 |
"GemmaForCausalLM"
|
| 5 |
],
|
|
|
|
| 21 |
"rms_norm_eps": 1e-06,
|
| 22 |
"rope_scaling": null,
|
| 23 |
"rope_theta": 10000.0,
|
| 24 |
+
"torch_dtype": "bfloat16",
|
| 25 |
"transformers_version": "4.38.1",
|
| 26 |
"use_cache": true,
|
| 27 |
"vocab_size": 256000
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:686e837442062780a33e430a1988d85074d05636f381b40a825581a8a1c3924b
|
| 3 |
+
size 4945242264
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ca672a78a61c219acb035dff8aa3e7416dbccc5ac6053c3774e9fe3a62047d3
|
| 3 |
+
size 67121608
|
model.safetensors.index.json
CHANGED
|
@@ -1,171 +1,171 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
-
"model.embed_tokens.weight": "model-00001-of-
|
| 7 |
-
"model.layers.0.input_layernorm.weight": "model-00001-of-
|
| 8 |
-
"model.layers.0.mlp.down_proj.weight": "model-00001-of-
|
| 9 |
-
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-
|
| 10 |
-
"model.layers.0.mlp.up_proj.weight": "model-00001-of-
|
| 11 |
-
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-
|
| 12 |
-
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-
|
| 13 |
-
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-
|
| 14 |
-
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-
|
| 15 |
-
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-
|
| 16 |
-
"model.layers.1.input_layernorm.weight": "model-00001-of-
|
| 17 |
-
"model.layers.1.mlp.down_proj.weight": "model-00001-of-
|
| 18 |
-
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-
|
| 19 |
-
"model.layers.1.mlp.up_proj.weight": "model-00001-of-
|
| 20 |
-
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-
|
| 21 |
-
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-
|
| 22 |
-
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-
|
| 23 |
-
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-
|
| 24 |
-
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-
|
| 25 |
-
"model.layers.10.input_layernorm.weight": "model-
|
| 26 |
-
"model.layers.10.mlp.down_proj.weight": "model-
|
| 27 |
-
"model.layers.10.mlp.gate_proj.weight": "model-
|
| 28 |
-
"model.layers.10.mlp.up_proj.weight": "model-
|
| 29 |
-
"model.layers.10.post_attention_layernorm.weight": "model-
|
| 30 |
-
"model.layers.10.self_attn.k_proj.weight": "model-
|
| 31 |
-
"model.layers.10.self_attn.o_proj.weight": "model-
|
| 32 |
-
"model.layers.10.self_attn.q_proj.weight": "model-
|
| 33 |
-
"model.layers.10.self_attn.v_proj.weight": "model-
|
| 34 |
-
"model.layers.11.input_layernorm.weight": "model-
|
| 35 |
-
"model.layers.11.mlp.down_proj.weight": "model-
|
| 36 |
-
"model.layers.11.mlp.gate_proj.weight": "model-
|
| 37 |
-
"model.layers.11.mlp.up_proj.weight": "model-
|
| 38 |
-
"model.layers.11.post_attention_layernorm.weight": "model-
|
| 39 |
-
"model.layers.11.self_attn.k_proj.weight": "model-
|
| 40 |
-
"model.layers.11.self_attn.o_proj.weight": "model-
|
| 41 |
-
"model.layers.11.self_attn.q_proj.weight": "model-
|
| 42 |
-
"model.layers.11.self_attn.v_proj.weight": "model-
|
| 43 |
-
"model.layers.12.input_layernorm.weight": "model-
|
| 44 |
-
"model.layers.12.mlp.down_proj.weight": "model-
|
| 45 |
-
"model.layers.12.mlp.gate_proj.weight": "model-
|
| 46 |
-
"model.layers.12.mlp.up_proj.weight": "model-
|
| 47 |
-
"model.layers.12.post_attention_layernorm.weight": "model-
|
| 48 |
-
"model.layers.12.self_attn.k_proj.weight": "model-
|
| 49 |
-
"model.layers.12.self_attn.o_proj.weight": "model-
|
| 50 |
-
"model.layers.12.self_attn.q_proj.weight": "model-
|
| 51 |
-
"model.layers.12.self_attn.v_proj.weight": "model-
|
| 52 |
-
"model.layers.13.input_layernorm.weight": "model-
|
| 53 |
-
"model.layers.13.mlp.down_proj.weight": "model-
|
| 54 |
-
"model.layers.13.mlp.gate_proj.weight": "model-
|
| 55 |
-
"model.layers.13.mlp.up_proj.weight": "model-
|
| 56 |
-
"model.layers.13.post_attention_layernorm.weight": "model-
|
| 57 |
-
"model.layers.13.self_attn.k_proj.weight": "model-
|
| 58 |
-
"model.layers.13.self_attn.o_proj.weight": "model-
|
| 59 |
-
"model.layers.13.self_attn.q_proj.weight": "model-
|
| 60 |
-
"model.layers.13.self_attn.v_proj.weight": "model-
|
| 61 |
-
"model.layers.14.input_layernorm.weight": "model-
|
| 62 |
-
"model.layers.14.mlp.down_proj.weight": "model-
|
| 63 |
-
"model.layers.14.mlp.gate_proj.weight": "model-
|
| 64 |
-
"model.layers.14.mlp.up_proj.weight": "model-
|
| 65 |
-
"model.layers.14.post_attention_layernorm.weight": "model-
|
| 66 |
-
"model.layers.14.self_attn.k_proj.weight": "model-
|
| 67 |
-
"model.layers.14.self_attn.o_proj.weight": "model-
|
| 68 |
-
"model.layers.14.self_attn.q_proj.weight": "model-
|
| 69 |
-
"model.layers.14.self_attn.v_proj.weight": "model-
|
| 70 |
-
"model.layers.15.input_layernorm.weight": "model-
|
| 71 |
-
"model.layers.15.mlp.down_proj.weight": "model-
|
| 72 |
-
"model.layers.15.mlp.gate_proj.weight": "model-
|
| 73 |
-
"model.layers.15.mlp.up_proj.weight": "model-
|
| 74 |
-
"model.layers.15.post_attention_layernorm.weight": "model-
|
| 75 |
-
"model.layers.15.self_attn.k_proj.weight": "model-
|
| 76 |
-
"model.layers.15.self_attn.o_proj.weight": "model-
|
| 77 |
-
"model.layers.15.self_attn.q_proj.weight": "model-
|
| 78 |
-
"model.layers.15.self_attn.v_proj.weight": "model-
|
| 79 |
-
"model.layers.16.input_layernorm.weight": "model-
|
| 80 |
-
"model.layers.16.mlp.down_proj.weight": "model-
|
| 81 |
-
"model.layers.16.mlp.gate_proj.weight": "model-
|
| 82 |
-
"model.layers.16.mlp.up_proj.weight": "model-
|
| 83 |
-
"model.layers.16.post_attention_layernorm.weight": "model-
|
| 84 |
-
"model.layers.16.self_attn.k_proj.weight": "model-
|
| 85 |
-
"model.layers.16.self_attn.o_proj.weight": "model-
|
| 86 |
-
"model.layers.16.self_attn.q_proj.weight": "model-
|
| 87 |
-
"model.layers.16.self_attn.v_proj.weight": "model-
|
| 88 |
-
"model.layers.17.input_layernorm.weight": "model-
|
| 89 |
-
"model.layers.17.mlp.down_proj.weight": "model-
|
| 90 |
-
"model.layers.17.mlp.gate_proj.weight": "model-
|
| 91 |
-
"model.layers.17.mlp.up_proj.weight": "model-
|
| 92 |
-
"model.layers.17.post_attention_layernorm.weight": "model-
|
| 93 |
-
"model.layers.17.self_attn.k_proj.weight": "model-
|
| 94 |
-
"model.layers.17.self_attn.o_proj.weight": "model-
|
| 95 |
-
"model.layers.17.self_attn.q_proj.weight": "model-
|
| 96 |
-
"model.layers.17.self_attn.v_proj.weight": "model-
|
| 97 |
-
"model.layers.2.input_layernorm.weight": "model-00001-of-
|
| 98 |
-
"model.layers.2.mlp.down_proj.weight": "model-00001-of-
|
| 99 |
-
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-
|
| 100 |
-
"model.layers.2.mlp.up_proj.weight": "model-00001-of-
|
| 101 |
-
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-
|
| 102 |
-
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-
|
| 103 |
-
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-
|
| 104 |
-
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-
|
| 105 |
-
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-
|
| 106 |
-
"model.layers.3.input_layernorm.weight": "model-00001-of-
|
| 107 |
-
"model.layers.3.mlp.down_proj.weight": "model-00001-of-
|
| 108 |
-
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-
|
| 109 |
-
"model.layers.3.mlp.up_proj.weight": "model-00001-of-
|
| 110 |
-
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-
|
| 111 |
-
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-
|
| 112 |
-
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-
|
| 113 |
-
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-
|
| 114 |
-
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-
|
| 115 |
-
"model.layers.4.input_layernorm.weight": "model-00001-of-
|
| 116 |
-
"model.layers.4.mlp.down_proj.weight": "model-00001-of-
|
| 117 |
-
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-
|
| 118 |
-
"model.layers.4.mlp.up_proj.weight": "model-00001-of-
|
| 119 |
-
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-
|
| 120 |
-
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-
|
| 121 |
-
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-
|
| 122 |
-
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-
|
| 123 |
-
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-
|
| 124 |
-
"model.layers.5.input_layernorm.weight": "model-00001-of-
|
| 125 |
-
"model.layers.5.mlp.down_proj.weight": "model-00001-of-
|
| 126 |
-
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-
|
| 127 |
-
"model.layers.5.mlp.up_proj.weight": "model-00001-of-
|
| 128 |
-
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-
|
| 129 |
-
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-
|
| 130 |
-
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-
|
| 131 |
-
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-
|
| 132 |
-
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-
|
| 133 |
-
"model.layers.6.input_layernorm.weight": "model-
|
| 134 |
-
"model.layers.6.mlp.down_proj.weight": "model-
|
| 135 |
-
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-
|
| 136 |
-
"model.layers.6.mlp.up_proj.weight": "model-
|
| 137 |
-
"model.layers.6.post_attention_layernorm.weight": "model-
|
| 138 |
-
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-
|
| 139 |
-
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-
|
| 140 |
-
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-
|
| 141 |
-
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-
|
| 142 |
-
"model.layers.7.input_layernorm.weight": "model-
|
| 143 |
-
"model.layers.7.mlp.down_proj.weight": "model-
|
| 144 |
-
"model.layers.7.mlp.gate_proj.weight": "model-
|
| 145 |
-
"model.layers.7.mlp.up_proj.weight": "model-
|
| 146 |
-
"model.layers.7.post_attention_layernorm.weight": "model-
|
| 147 |
-
"model.layers.7.self_attn.k_proj.weight": "model-
|
| 148 |
-
"model.layers.7.self_attn.o_proj.weight": "model-
|
| 149 |
-
"model.layers.7.self_attn.q_proj.weight": "model-
|
| 150 |
-
"model.layers.7.self_attn.v_proj.weight": "model-
|
| 151 |
-
"model.layers.8.input_layernorm.weight": "model-
|
| 152 |
-
"model.layers.8.mlp.down_proj.weight": "model-
|
| 153 |
-
"model.layers.8.mlp.gate_proj.weight": "model-
|
| 154 |
-
"model.layers.8.mlp.up_proj.weight": "model-
|
| 155 |
-
"model.layers.8.post_attention_layernorm.weight": "model-
|
| 156 |
-
"model.layers.8.self_attn.k_proj.weight": "model-
|
| 157 |
-
"model.layers.8.self_attn.o_proj.weight": "model-
|
| 158 |
-
"model.layers.8.self_attn.q_proj.weight": "model-
|
| 159 |
-
"model.layers.8.self_attn.v_proj.weight": "model-
|
| 160 |
-
"model.layers.9.input_layernorm.weight": "model-
|
| 161 |
-
"model.layers.9.mlp.down_proj.weight": "model-
|
| 162 |
-
"model.layers.9.mlp.gate_proj.weight": "model-
|
| 163 |
-
"model.layers.9.mlp.up_proj.weight": "model-
|
| 164 |
-
"model.layers.9.post_attention_layernorm.weight": "model-
|
| 165 |
-
"model.layers.9.self_attn.k_proj.weight": "model-
|
| 166 |
-
"model.layers.9.self_attn.o_proj.weight": "model-
|
| 167 |
-
"model.layers.9.self_attn.q_proj.weight": "model-
|
| 168 |
-
"model.layers.9.self_attn.v_proj.weight": "model-
|
| 169 |
-
"model.norm.weight": "model-
|
| 170 |
}
|
| 171 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 5012344832
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 7 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 89 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 90 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 93 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 170 |
}
|
| 171 |
}
|