Commit
•
a75a720
1
Parent(s):
bb957e5
Upload LlamaForCausalLM
Browse files- config.json +4 -7
- generation_config.json +0 -1
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +274 -256
config.json
CHANGED
|
@@ -1,25 +1,22 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "model-
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
| 6 |
"attention_bias": false,
|
| 7 |
"attention_dropout": 0.0,
|
| 8 |
-
"attn_config": {
|
| 9 |
-
"attn_impl": "flash_v2"
|
| 10 |
-
},
|
| 11 |
"bos_token_id": 100257,
|
| 12 |
"eos_token_id": 100257,
|
| 13 |
"head_dim": 128,
|
| 14 |
"hidden_act": "silu",
|
| 15 |
"hidden_size": 4096,
|
| 16 |
"initializer_range": 0.02,
|
| 17 |
-
"intermediate_size":
|
| 18 |
"max_position_embeddings": 4096,
|
| 19 |
"mlp_bias": false,
|
| 20 |
"model_type": "llama",
|
| 21 |
"num_attention_heads": 32,
|
| 22 |
-
"num_hidden_layers":
|
| 23 |
"num_key_value_heads": 8,
|
| 24 |
"pretraining_tp": 1,
|
| 25 |
"rms_norm_eps": 1e-05,
|
|
@@ -28,6 +25,6 @@
|
|
| 28 |
"tie_word_embeddings": false,
|
| 29 |
"torch_dtype": "bfloat16",
|
| 30 |
"transformers_version": "4.44.0",
|
| 31 |
-
"use_cache":
|
| 32 |
"vocab_size": 100288
|
| 33 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "model-pretrained",
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
| 6 |
"attention_bias": false,
|
| 7 |
"attention_dropout": 0.0,
|
|
|
|
|
|
|
|
|
|
| 8 |
"bos_token_id": 100257,
|
| 9 |
"eos_token_id": 100257,
|
| 10 |
"head_dim": 128,
|
| 11 |
"hidden_act": "silu",
|
| 12 |
"hidden_size": 4096,
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 18752,
|
| 15 |
"max_position_embeddings": 4096,
|
| 16 |
"mlp_bias": false,
|
| 17 |
"model_type": "llama",
|
| 18 |
"num_attention_heads": 32,
|
| 19 |
+
"num_hidden_layers": 30,
|
| 20 |
"num_key_value_heads": 8,
|
| 21 |
"pretraining_tp": 1,
|
| 22 |
"rms_norm_eps": 1e-05,
|
|
|
|
| 25 |
"tie_word_embeddings": false,
|
| 26 |
"torch_dtype": "bfloat16",
|
| 27 |
"transformers_version": "4.44.0",
|
| 28 |
+
"use_cache": true,
|
| 29 |
"vocab_size": 100288
|
| 30 |
}
|
generation_config.json
CHANGED
|
@@ -1,7 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 100257,
|
| 4 |
-
"do_sample": true,
|
| 5 |
"eos_token_id": 100257,
|
| 6 |
"transformers_version": "4.44.0"
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 100257,
|
|
|
|
| 4 |
"eos_token_id": 100257,
|
| 5 |
"transformers_version": "4.44.0"
|
| 6 |
}
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ddd99ff260f6c3ebf43a5c9e840afb694a71908f2098a7654c9d54fb4efbb327
|
| 3 |
+
size 4872331080
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b32a4a88027a152168c9d1732e9f7dbc00b42470660e3f121e76823a56101d65
|
| 3 |
+
size 4902773984
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19c0be09f2f0be3dfb03da99c85457525ef5150ad1831ccababc6fba3aecb949
|
| 3 |
+
size 4902774000
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4a7dea895a466a07d06e9f30ccbcea1784edd2d5b93597fe877b412d0cafaf4
|
| 3 |
+
size 3307827984
|
model.safetensors.index.json
CHANGED
|
@@ -1,262 +1,280 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
-
"lm_head.weight": "model-
|
| 7 |
-
"model.embed_tokens.weight": "model-00001-of-
|
| 8 |
-
"model.layers.0.input_layernorm.weight": "model-00001-of-
|
| 9 |
-
"model.layers.0.mlp.down_proj.weight": "model-00001-of-
|
| 10 |
-
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-
|
| 11 |
-
"model.layers.0.mlp.up_proj.weight": "model-00001-of-
|
| 12 |
-
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-
|
| 13 |
-
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-
|
| 14 |
-
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-
|
| 15 |
-
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-
|
| 16 |
-
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-
|
| 17 |
-
"model.layers.1.input_layernorm.weight": "model-00001-of-
|
| 18 |
-
"model.layers.1.mlp.down_proj.weight": "model-00001-of-
|
| 19 |
-
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-
|
| 20 |
-
"model.layers.1.mlp.up_proj.weight": "model-00001-of-
|
| 21 |
-
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-
|
| 22 |
-
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-
|
| 23 |
-
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-
|
| 24 |
-
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-
|
| 25 |
-
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-
|
| 26 |
-
"model.layers.10.input_layernorm.weight": "model-00002-of-
|
| 27 |
-
"model.layers.10.mlp.down_proj.weight": "model-00002-of-
|
| 28 |
-
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-
|
| 29 |
-
"model.layers.10.mlp.up_proj.weight": "model-00002-of-
|
| 30 |
-
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-
|
| 31 |
-
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-
|
| 32 |
-
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-
|
| 33 |
-
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-
|
| 34 |
-
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-
|
| 35 |
-
"model.layers.11.input_layernorm.weight": "model-00002-of-
|
| 36 |
-
"model.layers.11.mlp.down_proj.weight": "model-00002-of-
|
| 37 |
-
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-
|
| 38 |
-
"model.layers.11.mlp.up_proj.weight": "model-00002-of-
|
| 39 |
-
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-
|
| 40 |
-
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-
|
| 41 |
-
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-
|
| 42 |
-
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-
|
| 43 |
-
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-
|
| 44 |
-
"model.layers.12.input_layernorm.weight": "model-00002-of-
|
| 45 |
-
"model.layers.12.mlp.down_proj.weight": "model-00002-of-
|
| 46 |
-
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-
|
| 47 |
-
"model.layers.12.mlp.up_proj.weight": "model-00002-of-
|
| 48 |
-
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-
|
| 49 |
-
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-
|
| 50 |
-
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-
|
| 51 |
-
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-
|
| 52 |
-
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-
|
| 53 |
-
"model.layers.13.input_layernorm.weight": "model-00002-of-
|
| 54 |
-
"model.layers.13.mlp.down_proj.weight": "model-00002-of-
|
| 55 |
-
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-
|
| 56 |
-
"model.layers.13.mlp.up_proj.weight": "model-00002-of-
|
| 57 |
-
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-
|
| 58 |
-
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-
|
| 59 |
-
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-
|
| 60 |
-
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-
|
| 61 |
-
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-
|
| 62 |
-
"model.layers.14.input_layernorm.weight": "model-00002-of-
|
| 63 |
-
"model.layers.14.mlp.down_proj.weight": "model-00002-of-
|
| 64 |
-
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-
|
| 65 |
-
"model.layers.14.mlp.up_proj.weight": "model-00002-of-
|
| 66 |
-
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-
|
| 67 |
-
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-
|
| 68 |
-
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-
|
| 69 |
-
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-
|
| 70 |
-
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-
|
| 71 |
-
"model.layers.15.input_layernorm.weight": "model-00002-of-
|
| 72 |
-
"model.layers.15.mlp.down_proj.weight": "model-00002-of-
|
| 73 |
-
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-
|
| 74 |
-
"model.layers.15.mlp.up_proj.weight": "model-00002-of-
|
| 75 |
-
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-
|
| 76 |
-
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-
|
| 77 |
-
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-
|
| 78 |
-
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-
|
| 79 |
-
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-
|
| 80 |
-
"model.layers.16.input_layernorm.weight": "model-
|
| 81 |
-
"model.layers.16.mlp.down_proj.weight": "model-
|
| 82 |
-
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-
|
| 83 |
-
"model.layers.16.mlp.up_proj.weight": "model-
|
| 84 |
-
"model.layers.16.post_attention_layernorm.weight": "model-
|
| 85 |
-
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-
|
| 86 |
-
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-
|
| 87 |
-
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-
|
| 88 |
-
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-
|
| 89 |
-
"model.layers.17.input_layernorm.weight": "model-
|
| 90 |
-
"model.layers.17.mlp.down_proj.weight": "model-
|
| 91 |
-
"model.layers.17.mlp.gate_proj.weight": "model-
|
| 92 |
-
"model.layers.17.mlp.up_proj.weight": "model-
|
| 93 |
-
"model.layers.17.post_attention_layernorm.weight": "model-
|
| 94 |
-
"model.layers.17.self_attn.k_proj.weight": "model-
|
| 95 |
-
"model.layers.17.self_attn.o_proj.weight": "model-
|
| 96 |
-
"model.layers.17.self_attn.q_proj.weight": "model-
|
| 97 |
-
"model.layers.17.self_attn.v_proj.weight": "model-
|
| 98 |
-
"model.layers.18.input_layernorm.weight": "model-
|
| 99 |
-
"model.layers.18.mlp.down_proj.weight": "model-
|
| 100 |
-
"model.layers.18.mlp.gate_proj.weight": "model-
|
| 101 |
-
"model.layers.18.mlp.up_proj.weight": "model-
|
| 102 |
-
"model.layers.18.post_attention_layernorm.weight": "model-
|
| 103 |
-
"model.layers.18.self_attn.k_proj.weight": "model-
|
| 104 |
-
"model.layers.18.self_attn.o_proj.weight": "model-
|
| 105 |
-
"model.layers.18.self_attn.q_proj.weight": "model-
|
| 106 |
-
"model.layers.18.self_attn.v_proj.weight": "model-
|
| 107 |
-
"model.layers.19.input_layernorm.weight": "model-
|
| 108 |
-
"model.layers.19.mlp.down_proj.weight": "model-
|
| 109 |
-
"model.layers.19.mlp.gate_proj.weight": "model-
|
| 110 |
-
"model.layers.19.mlp.up_proj.weight": "model-
|
| 111 |
-
"model.layers.19.post_attention_layernorm.weight": "model-
|
| 112 |
-
"model.layers.19.self_attn.k_proj.weight": "model-
|
| 113 |
-
"model.layers.19.self_attn.o_proj.weight": "model-
|
| 114 |
-
"model.layers.19.self_attn.q_proj.weight": "model-
|
| 115 |
-
"model.layers.19.self_attn.v_proj.weight": "model-
|
| 116 |
-
"model.layers.2.input_layernorm.weight": "model-00001-of-
|
| 117 |
-
"model.layers.2.mlp.down_proj.weight": "model-00001-of-
|
| 118 |
-
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-
|
| 119 |
-
"model.layers.2.mlp.up_proj.weight": "model-00001-of-
|
| 120 |
-
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-
|
| 121 |
-
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-
|
| 122 |
-
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-
|
| 123 |
-
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-
|
| 124 |
-
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-
|
| 125 |
-
"model.layers.20.input_layernorm.weight": "model-
|
| 126 |
-
"model.layers.20.mlp.down_proj.weight": "model-
|
| 127 |
-
"model.layers.20.mlp.gate_proj.weight": "model-
|
| 128 |
-
"model.layers.20.mlp.up_proj.weight": "model-
|
| 129 |
-
"model.layers.20.post_attention_layernorm.weight": "model-
|
| 130 |
-
"model.layers.20.self_attn.k_proj.weight": "model-
|
| 131 |
-
"model.layers.20.self_attn.o_proj.weight": "model-
|
| 132 |
-
"model.layers.20.self_attn.q_proj.weight": "model-
|
| 133 |
-
"model.layers.20.self_attn.v_proj.weight": "model-
|
| 134 |
-
"model.layers.21.input_layernorm.weight": "model-00003-of-
|
| 135 |
-
"model.layers.21.mlp.down_proj.weight": "model-00003-of-
|
| 136 |
-
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-
|
| 137 |
-
"model.layers.21.mlp.up_proj.weight": "model-00003-of-
|
| 138 |
-
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-
|
| 139 |
-
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-
|
| 140 |
-
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-
|
| 141 |
-
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-
|
| 142 |
-
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-
|
| 143 |
-
"model.layers.22.input_layernorm.weight": "model-00003-of-
|
| 144 |
-
"model.layers.22.mlp.down_proj.weight": "model-00003-of-
|
| 145 |
-
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-
|
| 146 |
-
"model.layers.22.mlp.up_proj.weight": "model-00003-of-
|
| 147 |
-
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-
|
| 148 |
-
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-
|
| 149 |
-
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-
|
| 150 |
-
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-
|
| 151 |
-
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-
|
| 152 |
-
"model.layers.23.input_layernorm.weight": "model-00003-of-
|
| 153 |
-
"model.layers.23.mlp.down_proj.weight": "model-00003-of-
|
| 154 |
-
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-
|
| 155 |
-
"model.layers.23.mlp.up_proj.weight": "model-00003-of-
|
| 156 |
-
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-
|
| 157 |
-
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-
|
| 158 |
-
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-
|
| 159 |
-
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-
|
| 160 |
-
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-
|
| 161 |
-
"model.layers.24.input_layernorm.weight": "model-00003-of-
|
| 162 |
-
"model.layers.24.mlp.down_proj.weight": "model-00003-of-
|
| 163 |
-
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-
|
| 164 |
-
"model.layers.24.mlp.up_proj.weight": "model-00003-of-
|
| 165 |
-
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-
|
| 166 |
-
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-
|
| 167 |
-
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-
|
| 168 |
-
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-
|
| 169 |
-
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-
|
| 170 |
-
"model.layers.25.input_layernorm.weight": "model-
|
| 171 |
-
"model.layers.25.mlp.down_proj.weight": "model-
|
| 172 |
-
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-
|
| 173 |
-
"model.layers.25.mlp.up_proj.weight": "model-
|
| 174 |
-
"model.layers.25.post_attention_layernorm.weight": "model-
|
| 175 |
-
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-
|
| 176 |
-
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-
|
| 177 |
-
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-
|
| 178 |
-
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-
|
| 179 |
-
"model.layers.26.input_layernorm.weight": "model-
|
| 180 |
-
"model.layers.26.mlp.down_proj.weight": "model-
|
| 181 |
-
"model.layers.26.mlp.gate_proj.weight": "model-
|
| 182 |
-
"model.layers.26.mlp.up_proj.weight": "model-
|
| 183 |
-
"model.layers.26.post_attention_layernorm.weight": "model-
|
| 184 |
-
"model.layers.26.self_attn.k_proj.weight": "model-
|
| 185 |
-
"model.layers.26.self_attn.o_proj.weight": "model-
|
| 186 |
-
"model.layers.26.self_attn.q_proj.weight": "model-
|
| 187 |
-
"model.layers.26.self_attn.v_proj.weight": "model-
|
| 188 |
-
"model.layers.27.input_layernorm.weight": "model-
|
| 189 |
-
"model.layers.27.mlp.down_proj.weight": "model-
|
| 190 |
-
"model.layers.27.mlp.gate_proj.weight": "model-
|
| 191 |
-
"model.layers.27.mlp.up_proj.weight": "model-
|
| 192 |
-
"model.layers.27.post_attention_layernorm.weight": "model-
|
| 193 |
-
"model.layers.27.self_attn.k_proj.weight": "model-
|
| 194 |
-
"model.layers.27.self_attn.o_proj.weight": "model-
|
| 195 |
-
"model.layers.27.self_attn.q_proj.weight": "model-
|
| 196 |
-
"model.layers.27.self_attn.v_proj.weight": "model-
|
| 197 |
-
"model.layers.
|
| 198 |
-
"model.layers.
|
| 199 |
-
"model.layers.
|
| 200 |
-
"model.layers.
|
| 201 |
-
"model.layers.
|
| 202 |
-
"model.layers.
|
| 203 |
-
"model.layers.
|
| 204 |
-
"model.layers.
|
| 205 |
-
"model.layers.
|
| 206 |
-
"model.layers.
|
| 207 |
-
"model.layers.
|
| 208 |
-
"model.layers.
|
| 209 |
-
"model.layers.
|
| 210 |
-
"model.layers.
|
| 211 |
-
"model.layers.
|
| 212 |
-
"model.layers.
|
| 213 |
-
"model.layers.
|
| 214 |
-
"model.layers.
|
| 215 |
-
"model.layers.
|
| 216 |
-
"model.layers.
|
| 217 |
-
"model.layers.
|
| 218 |
-
"model.layers.
|
| 219 |
-
"model.layers.
|
| 220 |
-
"model.layers.
|
| 221 |
-
"model.layers.
|
| 222 |
-
"model.layers.
|
| 223 |
-
"model.layers.
|
| 224 |
-
"model.layers.
|
| 225 |
-
"model.layers.
|
| 226 |
-
"model.layers.
|
| 227 |
-
"model.layers.
|
| 228 |
-
"model.layers.
|
| 229 |
-
"model.layers.
|
| 230 |
-
"model.layers.
|
| 231 |
-
"model.layers.
|
| 232 |
-
"model.layers.
|
| 233 |
-
"model.layers.
|
| 234 |
-
"model.layers.
|
| 235 |
-
"model.layers.
|
| 236 |
-
"model.layers.
|
| 237 |
-
"model.layers.
|
| 238 |
-
"model.layers.
|
| 239 |
-
"model.layers.
|
| 240 |
-
"model.layers.
|
| 241 |
-
"model.layers.
|
| 242 |
-
"model.layers.
|
| 243 |
-
"model.layers.
|
| 244 |
-
"model.layers.
|
| 245 |
-
"model.layers.
|
| 246 |
-
"model.layers.
|
| 247 |
-
"model.layers.
|
| 248 |
-
"model.layers.
|
| 249 |
-
"model.layers.
|
| 250 |
-
"model.layers.
|
| 251 |
-
"model.layers.
|
| 252 |
-
"model.layers.
|
| 253 |
-
"model.layers.
|
| 254 |
-
"model.layers.
|
| 255 |
-
"model.layers.
|
| 256 |
-
"model.layers.
|
| 257 |
-
"model.layers.
|
| 258 |
-
"model.layers.
|
| 259 |
-
"model.layers.
|
| 260 |
-
"model.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 261 |
}
|
| 262 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 17985675264
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 98 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 107 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 125 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 134 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 143 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 152 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 161 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 170 |
+
"model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 188 |
+
"model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 197 |
+
"model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 206 |
+
"model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 215 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 224 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 225 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 226 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 227 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 228 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 229 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 230 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 231 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 232 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 233 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 234 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 235 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 236 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 237 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 238 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 239 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 240 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 241 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 242 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 243 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 244 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 245 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 246 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 247 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 248 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 249 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 250 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 251 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 252 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 253 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 254 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 255 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 256 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 257 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 258 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 259 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 260 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 261 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 262 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 263 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 264 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 265 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 266 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 267 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 268 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 269 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 270 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 271 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 272 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 273 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 274 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 275 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 276 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 277 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 278 |
+
"model.norm.weight": "model-00004-of-00004.safetensors"
|
| 279 |
}
|
| 280 |
}
|