Commit
·
0432a65
1
Parent(s):
e9fa413
Fix quantized weights
Browse files- config.json +2 -3
- model-00001-of-00002.safetensors +2 -2
- model-00002-of-00002.safetensors +1 -1
- model.safetensors.index.json +359 -359
config.json
CHANGED
|
@@ -27,8 +27,7 @@
|
|
| 27 |
"bits": 4,
|
| 28 |
"group_size": 128,
|
| 29 |
"modules_to_not_convert": [
|
| 30 |
-
"lm_head"
|
| 31 |
-
"gate"
|
| 32 |
],
|
| 33 |
"quant_method": "awq",
|
| 34 |
"version": "gemm",
|
|
@@ -43,7 +42,7 @@
|
|
| 43 |
},
|
| 44 |
"rope_theta": 1000000.0,
|
| 45 |
"tie_word_embeddings": false,
|
| 46 |
-
"torch_dtype": "
|
| 47 |
"transformers_version": "4.43.1",
|
| 48 |
"use_cache": false,
|
| 49 |
"vocab_size": 102400
|
|
|
|
| 27 |
"bits": 4,
|
| 28 |
"group_size": 128,
|
| 29 |
"modules_to_not_convert": [
|
| 30 |
+
"lm_head"
|
|
|
|
| 31 |
],
|
| 32 |
"quant_method": "awq",
|
| 33 |
"version": "gemm",
|
|
|
|
| 42 |
},
|
| 43 |
"rope_theta": 1000000.0,
|
| 44 |
"tie_word_embeddings": false,
|
| 45 |
+
"torch_dtype": "float16",
|
| 46 |
"transformers_version": "4.43.1",
|
| 47 |
"use_cache": false,
|
| 48 |
"vocab_size": 102400
|
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ad74f00a48ea4e67b60a26347c21b28344719ab0e7cbc98cafaa9558109e254
|
| 3 |
+
size 4465454112
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 838860928
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5a595e8e4eeb32fb568aebcfd80b02dd2e098d060947aed79bb46e09a31172f
|
| 3 |
size 838860928
|
model.safetensors.index.json
CHANGED
|
@@ -3,20 +3,20 @@
|
|
| 3 |
"total_size": 5304229888
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
-
"
|
| 7 |
-
"transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 8 |
"transformer.h.0.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 9 |
"transformer.h.0.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 10 |
"transformer.h.0.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 11 |
-
"transformer.h.0.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 12 |
-
"transformer.h.0.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 13 |
-
"transformer.h.0.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 14 |
-
"transformer.h.0.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 15 |
-
"transformer.h.0.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 16 |
-
"transformer.h.0.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 17 |
"transformer.h.0.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 18 |
"transformer.h.0.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 19 |
"transformer.h.0.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
"transformer.h.0.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 21 |
"transformer.h.0.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 22 |
"transformer.h.0.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
@@ -27,19 +27,19 @@
|
|
| 27 |
"transformer.h.0.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 28 |
"transformer.h.0.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 29 |
"transformer.h.0.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 30 |
-
"transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 31 |
"transformer.h.1.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 32 |
"transformer.h.1.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 33 |
"transformer.h.1.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 34 |
-
"transformer.h.1.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 35 |
-
"transformer.h.1.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 36 |
-
"transformer.h.1.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 37 |
-
"transformer.h.1.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 38 |
-
"transformer.h.1.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 39 |
-
"transformer.h.1.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 40 |
"transformer.h.1.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 41 |
"transformer.h.1.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 42 |
"transformer.h.1.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
"transformer.h.1.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 44 |
"transformer.h.1.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 45 |
"transformer.h.1.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
@@ -50,203 +50,19 @@
|
|
| 50 |
"transformer.h.1.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 51 |
"transformer.h.1.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 52 |
"transformer.h.1.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 53 |
-
"transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 54 |
-
"transformer.h.2.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 55 |
-
"transformer.h.2.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 56 |
-
"transformer.h.2.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 57 |
-
"transformer.h.2.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 58 |
-
"transformer.h.2.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 59 |
-
"transformer.h.2.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 60 |
-
"transformer.h.2.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 61 |
-
"transformer.h.2.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 62 |
-
"transformer.h.2.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 63 |
-
"transformer.h.2.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 64 |
-
"transformer.h.2.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 65 |
-
"transformer.h.2.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 66 |
-
"transformer.h.2.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 67 |
-
"transformer.h.2.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 68 |
-
"transformer.h.2.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
| 69 |
-
"transformer.h.2.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
|
| 70 |
-
"transformer.h.2.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
|
| 71 |
-
"transformer.h.2.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
|
| 72 |
-
"transformer.h.2.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
|
| 73 |
-
"transformer.h.2.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 74 |
-
"transformer.h.2.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 75 |
-
"transformer.h.2.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 76 |
-
"transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 77 |
-
"transformer.h.3.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 78 |
-
"transformer.h.3.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 79 |
-
"transformer.h.3.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 80 |
-
"transformer.h.3.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 81 |
-
"transformer.h.3.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 82 |
-
"transformer.h.3.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 83 |
-
"transformer.h.3.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 84 |
-
"transformer.h.3.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 85 |
-
"transformer.h.3.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 86 |
-
"transformer.h.3.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 87 |
-
"transformer.h.3.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 88 |
-
"transformer.h.3.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 89 |
-
"transformer.h.3.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 90 |
-
"transformer.h.3.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 91 |
-
"transformer.h.3.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
| 92 |
-
"transformer.h.3.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
|
| 93 |
-
"transformer.h.3.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
|
| 94 |
-
"transformer.h.3.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
|
| 95 |
-
"transformer.h.3.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
|
| 96 |
-
"transformer.h.3.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 97 |
-
"transformer.h.3.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 98 |
-
"transformer.h.3.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 99 |
-
"transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 100 |
-
"transformer.h.4.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 101 |
-
"transformer.h.4.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 102 |
-
"transformer.h.4.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 103 |
-
"transformer.h.4.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 104 |
-
"transformer.h.4.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 105 |
-
"transformer.h.4.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 106 |
-
"transformer.h.4.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 107 |
-
"transformer.h.4.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 108 |
-
"transformer.h.4.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 109 |
-
"transformer.h.4.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 110 |
-
"transformer.h.4.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 111 |
-
"transformer.h.4.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 112 |
-
"transformer.h.4.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 113 |
-
"transformer.h.4.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 114 |
-
"transformer.h.4.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
| 115 |
-
"transformer.h.4.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
|
| 116 |
-
"transformer.h.4.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
|
| 117 |
-
"transformer.h.4.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
|
| 118 |
-
"transformer.h.4.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
|
| 119 |
-
"transformer.h.4.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 120 |
-
"transformer.h.4.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 121 |
-
"transformer.h.4.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 122 |
-
"transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 123 |
-
"transformer.h.5.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 124 |
-
"transformer.h.5.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 125 |
-
"transformer.h.5.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 126 |
-
"transformer.h.5.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 127 |
-
"transformer.h.5.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 128 |
-
"transformer.h.5.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 129 |
-
"transformer.h.5.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 130 |
-
"transformer.h.5.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 131 |
-
"transformer.h.5.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 132 |
-
"transformer.h.5.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 133 |
-
"transformer.h.5.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 134 |
-
"transformer.h.5.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 135 |
-
"transformer.h.5.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 136 |
-
"transformer.h.5.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 137 |
-
"transformer.h.5.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
| 138 |
-
"transformer.h.5.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
|
| 139 |
-
"transformer.h.5.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
|
| 140 |
-
"transformer.h.5.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
|
| 141 |
-
"transformer.h.5.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
|
| 142 |
-
"transformer.h.5.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 143 |
-
"transformer.h.5.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 144 |
-
"transformer.h.5.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 145 |
-
"transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 146 |
-
"transformer.h.6.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 147 |
-
"transformer.h.6.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 148 |
-
"transformer.h.6.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 149 |
-
"transformer.h.6.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 150 |
-
"transformer.h.6.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 151 |
-
"transformer.h.6.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 152 |
-
"transformer.h.6.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 153 |
-
"transformer.h.6.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 154 |
-
"transformer.h.6.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 155 |
-
"transformer.h.6.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 156 |
-
"transformer.h.6.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 157 |
-
"transformer.h.6.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 158 |
-
"transformer.h.6.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 159 |
-
"transformer.h.6.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 160 |
-
"transformer.h.6.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
| 161 |
-
"transformer.h.6.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
|
| 162 |
-
"transformer.h.6.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
|
| 163 |
-
"transformer.h.6.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
|
| 164 |
-
"transformer.h.6.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
|
| 165 |
-
"transformer.h.6.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 166 |
-
"transformer.h.6.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 167 |
-
"transformer.h.6.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 168 |
-
"transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 169 |
-
"transformer.h.7.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 170 |
-
"transformer.h.7.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 171 |
-
"transformer.h.7.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 172 |
-
"transformer.h.7.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 173 |
-
"transformer.h.7.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 174 |
-
"transformer.h.7.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 175 |
-
"transformer.h.7.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 176 |
-
"transformer.h.7.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 177 |
-
"transformer.h.7.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 178 |
-
"transformer.h.7.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 179 |
-
"transformer.h.7.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 180 |
-
"transformer.h.7.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 181 |
-
"transformer.h.7.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 182 |
-
"transformer.h.7.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 183 |
-
"transformer.h.7.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
| 184 |
-
"transformer.h.7.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
|
| 185 |
-
"transformer.h.7.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
|
| 186 |
-
"transformer.h.7.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
|
| 187 |
-
"transformer.h.7.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
|
| 188 |
-
"transformer.h.7.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 189 |
-
"transformer.h.7.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 190 |
-
"transformer.h.7.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 191 |
-
"transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 192 |
-
"transformer.h.8.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 193 |
-
"transformer.h.8.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 194 |
-
"transformer.h.8.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 195 |
-
"transformer.h.8.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 196 |
-
"transformer.h.8.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 197 |
-
"transformer.h.8.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 198 |
-
"transformer.h.8.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 199 |
-
"transformer.h.8.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 200 |
-
"transformer.h.8.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 201 |
-
"transformer.h.8.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 202 |
-
"transformer.h.8.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 203 |
-
"transformer.h.8.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 204 |
-
"transformer.h.8.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 205 |
-
"transformer.h.8.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 206 |
-
"transformer.h.8.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
| 207 |
-
"transformer.h.8.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
|
| 208 |
-
"transformer.h.8.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
|
| 209 |
-
"transformer.h.8.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
|
| 210 |
-
"transformer.h.8.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
|
| 211 |
-
"transformer.h.8.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 212 |
-
"transformer.h.8.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 213 |
-
"transformer.h.8.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 214 |
-
"transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 215 |
-
"transformer.h.9.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 216 |
-
"transformer.h.9.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 217 |
-
"transformer.h.9.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 218 |
-
"transformer.h.9.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 219 |
-
"transformer.h.9.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 220 |
-
"transformer.h.9.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 221 |
-
"transformer.h.9.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 222 |
-
"transformer.h.9.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 223 |
-
"transformer.h.9.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 224 |
-
"transformer.h.9.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 225 |
-
"transformer.h.9.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 226 |
-
"transformer.h.9.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 227 |
-
"transformer.h.9.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 228 |
-
"transformer.h.9.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 229 |
-
"transformer.h.9.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
| 230 |
-
"transformer.h.9.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
|
| 231 |
-
"transformer.h.9.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
|
| 232 |
-
"transformer.h.9.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
|
| 233 |
-
"transformer.h.9.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
|
| 234 |
-
"transformer.h.9.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 235 |
-
"transformer.h.9.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 236 |
-
"transformer.h.9.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 237 |
-
"transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 238 |
"transformer.h.10.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 239 |
"transformer.h.10.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 240 |
"transformer.h.10.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 241 |
-
"transformer.h.10.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 242 |
-
"transformer.h.10.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 243 |
-
"transformer.h.10.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 244 |
-
"transformer.h.10.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 245 |
-
"transformer.h.10.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 246 |
-
"transformer.h.10.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 247 |
"transformer.h.10.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 248 |
"transformer.h.10.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 249 |
"transformer.h.10.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 250 |
"transformer.h.10.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 251 |
"transformer.h.10.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 252 |
"transformer.h.10.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
@@ -257,19 +73,19 @@
|
|
| 257 |
"transformer.h.10.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 258 |
"transformer.h.10.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 259 |
"transformer.h.10.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 260 |
-
"transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 261 |
"transformer.h.11.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 262 |
"transformer.h.11.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 263 |
"transformer.h.11.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 264 |
-
"transformer.h.11.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 265 |
-
"transformer.h.11.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 266 |
-
"transformer.h.11.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 267 |
-
"transformer.h.11.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 268 |
-
"transformer.h.11.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 269 |
-
"transformer.h.11.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 270 |
"transformer.h.11.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 271 |
"transformer.h.11.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 272 |
"transformer.h.11.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 273 |
"transformer.h.11.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 274 |
"transformer.h.11.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 275 |
"transformer.h.11.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
@@ -280,19 +96,19 @@
|
|
| 280 |
"transformer.h.11.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 281 |
"transformer.h.11.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 282 |
"transformer.h.11.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 283 |
-
"transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 284 |
"transformer.h.12.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 285 |
"transformer.h.12.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 286 |
"transformer.h.12.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 287 |
-
"transformer.h.12.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 288 |
-
"transformer.h.12.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 289 |
-
"transformer.h.12.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 290 |
-
"transformer.h.12.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 291 |
-
"transformer.h.12.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 292 |
-
"transformer.h.12.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 293 |
"transformer.h.12.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 294 |
"transformer.h.12.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 295 |
"transformer.h.12.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 296 |
"transformer.h.12.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 297 |
"transformer.h.12.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 298 |
"transformer.h.12.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
@@ -303,19 +119,19 @@
|
|
| 303 |
"transformer.h.12.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 304 |
"transformer.h.12.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 305 |
"transformer.h.12.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 306 |
-
"transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 307 |
"transformer.h.13.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 308 |
"transformer.h.13.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 309 |
"transformer.h.13.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 310 |
-
"transformer.h.13.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 311 |
-
"transformer.h.13.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 312 |
-
"transformer.h.13.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 313 |
-
"transformer.h.13.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 314 |
-
"transformer.h.13.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 315 |
-
"transformer.h.13.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 316 |
"transformer.h.13.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 317 |
"transformer.h.13.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 318 |
"transformer.h.13.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 319 |
"transformer.h.13.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 320 |
"transformer.h.13.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 321 |
"transformer.h.13.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
@@ -326,19 +142,19 @@
|
|
| 326 |
"transformer.h.13.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 327 |
"transformer.h.13.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 328 |
"transformer.h.13.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 329 |
-
"transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 330 |
"transformer.h.14.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 331 |
"transformer.h.14.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 332 |
"transformer.h.14.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 333 |
-
"transformer.h.14.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 334 |
-
"transformer.h.14.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 335 |
-
"transformer.h.14.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 336 |
-
"transformer.h.14.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 337 |
-
"transformer.h.14.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 338 |
-
"transformer.h.14.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 339 |
"transformer.h.14.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 340 |
"transformer.h.14.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 341 |
"transformer.h.14.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 342 |
"transformer.h.14.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 343 |
"transformer.h.14.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 344 |
"transformer.h.14.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
@@ -349,19 +165,19 @@
|
|
| 349 |
"transformer.h.14.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 350 |
"transformer.h.14.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 351 |
"transformer.h.14.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 352 |
-
"transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 353 |
"transformer.h.15.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 354 |
"transformer.h.15.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 355 |
"transformer.h.15.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 356 |
-
"transformer.h.15.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 357 |
-
"transformer.h.15.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 358 |
-
"transformer.h.15.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 359 |
-
"transformer.h.15.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 360 |
-
"transformer.h.15.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 361 |
-
"transformer.h.15.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 362 |
"transformer.h.15.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 363 |
"transformer.h.15.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 364 |
"transformer.h.15.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 365 |
"transformer.h.15.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 366 |
"transformer.h.15.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 367 |
"transformer.h.15.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
@@ -372,19 +188,19 @@
|
|
| 372 |
"transformer.h.15.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 373 |
"transformer.h.15.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 374 |
"transformer.h.15.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 375 |
-
"transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 376 |
"transformer.h.16.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 377 |
"transformer.h.16.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 378 |
"transformer.h.16.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 379 |
-
"transformer.h.16.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 380 |
-
"transformer.h.16.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 381 |
-
"transformer.h.16.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 382 |
-
"transformer.h.16.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 383 |
-
"transformer.h.16.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 384 |
-
"transformer.h.16.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 385 |
"transformer.h.16.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 386 |
"transformer.h.16.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 387 |
"transformer.h.16.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 388 |
"transformer.h.16.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 389 |
"transformer.h.16.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 390 |
"transformer.h.16.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
@@ -395,19 +211,19 @@
|
|
| 395 |
"transformer.h.16.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 396 |
"transformer.h.16.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 397 |
"transformer.h.16.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 398 |
-
"transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 399 |
"transformer.h.17.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 400 |
"transformer.h.17.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 401 |
"transformer.h.17.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 402 |
-
"transformer.h.17.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 403 |
-
"transformer.h.17.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 404 |
-
"transformer.h.17.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 405 |
-
"transformer.h.17.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 406 |
-
"transformer.h.17.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 407 |
-
"transformer.h.17.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 408 |
"transformer.h.17.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 409 |
"transformer.h.17.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 410 |
"transformer.h.17.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 411 |
"transformer.h.17.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 412 |
"transformer.h.17.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 413 |
"transformer.h.17.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
@@ -418,19 +234,19 @@
|
|
| 418 |
"transformer.h.17.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 419 |
"transformer.h.17.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 420 |
"transformer.h.17.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 421 |
-
"transformer.h.18.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 422 |
"transformer.h.18.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 423 |
"transformer.h.18.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 424 |
"transformer.h.18.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 425 |
-
"transformer.h.18.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 426 |
-
"transformer.h.18.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 427 |
-
"transformer.h.18.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 428 |
-
"transformer.h.18.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 429 |
-
"transformer.h.18.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 430 |
-
"transformer.h.18.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 431 |
"transformer.h.18.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 432 |
"transformer.h.18.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 433 |
"transformer.h.18.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 434 |
"transformer.h.18.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 435 |
"transformer.h.18.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 436 |
"transformer.h.18.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
@@ -441,19 +257,19 @@
|
|
| 441 |
"transformer.h.18.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 442 |
"transformer.h.18.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 443 |
"transformer.h.18.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 444 |
-
"transformer.h.19.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 445 |
"transformer.h.19.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 446 |
"transformer.h.19.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 447 |
"transformer.h.19.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 448 |
-
"transformer.h.19.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 449 |
-
"transformer.h.19.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 450 |
-
"transformer.h.19.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 451 |
-
"transformer.h.19.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 452 |
-
"transformer.h.19.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 453 |
-
"transformer.h.19.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 454 |
"transformer.h.19.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 455 |
"transformer.h.19.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 456 |
"transformer.h.19.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 457 |
"transformer.h.19.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 458 |
"transformer.h.19.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 459 |
"transformer.h.19.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
@@ -464,19 +280,42 @@
|
|
| 464 |
"transformer.h.19.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 465 |
"transformer.h.19.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 466 |
"transformer.h.19.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 467 |
-
"transformer.h.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 468 |
"transformer.h.20.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 469 |
"transformer.h.20.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 470 |
"transformer.h.20.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 471 |
-
"transformer.h.20.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 472 |
-
"transformer.h.20.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 473 |
-
"transformer.h.20.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 474 |
-
"transformer.h.20.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 475 |
-
"transformer.h.20.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 476 |
-
"transformer.h.20.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 477 |
"transformer.h.20.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 478 |
"transformer.h.20.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 479 |
"transformer.h.20.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 480 |
"transformer.h.20.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 481 |
"transformer.h.20.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 482 |
"transformer.h.20.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
@@ -487,19 +326,19 @@
|
|
| 487 |
"transformer.h.20.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 488 |
"transformer.h.20.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 489 |
"transformer.h.20.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 490 |
-
"transformer.h.21.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 491 |
"transformer.h.21.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 492 |
"transformer.h.21.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 493 |
"transformer.h.21.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 494 |
-
"transformer.h.21.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 495 |
-
"transformer.h.21.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 496 |
-
"transformer.h.21.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 497 |
-
"transformer.h.21.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 498 |
-
"transformer.h.21.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 499 |
-
"transformer.h.21.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 500 |
"transformer.h.21.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 501 |
"transformer.h.21.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 502 |
"transformer.h.21.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 503 |
"transformer.h.21.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 504 |
"transformer.h.21.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 505 |
"transformer.h.21.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
@@ -510,19 +349,19 @@
|
|
| 510 |
"transformer.h.21.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 511 |
"transformer.h.21.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 512 |
"transformer.h.21.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 513 |
-
"transformer.h.22.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 514 |
"transformer.h.22.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 515 |
"transformer.h.22.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 516 |
"transformer.h.22.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 517 |
-
"transformer.h.22.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 518 |
-
"transformer.h.22.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 519 |
-
"transformer.h.22.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 520 |
-
"transformer.h.22.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 521 |
-
"transformer.h.22.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 522 |
-
"transformer.h.22.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 523 |
"transformer.h.22.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 524 |
"transformer.h.22.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 525 |
"transformer.h.22.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 526 |
"transformer.h.22.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 527 |
"transformer.h.22.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 528 |
"transformer.h.22.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
@@ -533,19 +372,19 @@
|
|
| 533 |
"transformer.h.22.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 534 |
"transformer.h.22.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 535 |
"transformer.h.22.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 536 |
-
"transformer.h.23.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 537 |
"transformer.h.23.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 538 |
"transformer.h.23.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 539 |
"transformer.h.23.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 540 |
-
"transformer.h.23.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 541 |
-
"transformer.h.23.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 542 |
-
"transformer.h.23.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 543 |
-
"transformer.h.23.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 544 |
-
"transformer.h.23.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 545 |
-
"transformer.h.23.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 546 |
"transformer.h.23.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 547 |
"transformer.h.23.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 548 |
"transformer.h.23.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 549 |
"transformer.h.23.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 550 |
"transformer.h.23.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 551 |
"transformer.h.23.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
@@ -556,19 +395,19 @@
|
|
| 556 |
"transformer.h.23.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 557 |
"transformer.h.23.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 558 |
"transformer.h.23.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 559 |
-
"transformer.h.24.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 560 |
"transformer.h.24.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 561 |
"transformer.h.24.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 562 |
"transformer.h.24.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 563 |
-
"transformer.h.24.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 564 |
-
"transformer.h.24.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 565 |
-
"transformer.h.24.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 566 |
-
"transformer.h.24.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 567 |
-
"transformer.h.24.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 568 |
-
"transformer.h.24.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 569 |
"transformer.h.24.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 570 |
"transformer.h.24.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 571 |
"transformer.h.24.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 572 |
"transformer.h.24.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 573 |
"transformer.h.24.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 574 |
"transformer.h.24.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
@@ -578,20 +417,20 @@
|
|
| 578 |
"transformer.h.24.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
|
| 579 |
"transformer.h.24.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 580 |
"transformer.h.24.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 581 |
-
"transformer.h.24.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 582 |
-
"transformer.h.25.
|
| 583 |
-
"transformer.h.25.attn.attention.k_proj.
|
| 584 |
-
"transformer.h.25.attn.attention.k_proj.
|
| 585 |
-
"transformer.h.25.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 586 |
-
"transformer.h.25.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 587 |
-
"transformer.h.25.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 588 |
-
"transformer.h.25.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 589 |
-
"transformer.h.25.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 590 |
-
"transformer.h.25.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 591 |
-
"transformer.h.25.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 592 |
"transformer.h.25.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 593 |
"transformer.h.25.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 594 |
"transformer.h.25.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 595 |
"transformer.h.25.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 596 |
"transformer.h.25.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 597 |
"transformer.h.25.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
@@ -602,19 +441,19 @@
|
|
| 602 |
"transformer.h.25.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 603 |
"transformer.h.25.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 604 |
"transformer.h.25.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 605 |
-
"transformer.h.26.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 606 |
"transformer.h.26.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 607 |
"transformer.h.26.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 608 |
"transformer.h.26.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 609 |
-
"transformer.h.26.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 610 |
-
"transformer.h.26.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 611 |
-
"transformer.h.26.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 612 |
-
"transformer.h.26.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 613 |
-
"transformer.h.26.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 614 |
-
"transformer.h.26.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 615 |
"transformer.h.26.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 616 |
"transformer.h.26.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 617 |
"transformer.h.26.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 618 |
"transformer.h.26.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 619 |
"transformer.h.26.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 620 |
"transformer.h.26.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
@@ -625,19 +464,19 @@
|
|
| 625 |
"transformer.h.26.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 626 |
"transformer.h.26.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 627 |
"transformer.h.26.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 628 |
-
"transformer.h.27.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 629 |
"transformer.h.27.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 630 |
"transformer.h.27.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 631 |
"transformer.h.27.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 632 |
-
"transformer.h.27.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 633 |
-
"transformer.h.27.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 634 |
-
"transformer.h.27.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 635 |
-
"transformer.h.27.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 636 |
-
"transformer.h.27.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 637 |
-
"transformer.h.27.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 638 |
"transformer.h.27.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 639 |
"transformer.h.27.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 640 |
"transformer.h.27.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 641 |
"transformer.h.27.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 642 |
"transformer.h.27.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 643 |
"transformer.h.27.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
@@ -648,19 +487,19 @@
|
|
| 648 |
"transformer.h.27.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 649 |
"transformer.h.27.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 650 |
"transformer.h.27.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 651 |
-
"transformer.h.28.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 652 |
"transformer.h.28.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 653 |
"transformer.h.28.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 654 |
"transformer.h.28.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 655 |
-
"transformer.h.28.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 656 |
-
"transformer.h.28.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 657 |
-
"transformer.h.28.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 658 |
-
"transformer.h.28.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 659 |
-
"transformer.h.28.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 660 |
-
"transformer.h.28.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 661 |
"transformer.h.28.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 662 |
"transformer.h.28.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 663 |
"transformer.h.28.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 664 |
"transformer.h.28.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 665 |
"transformer.h.28.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 666 |
"transformer.h.28.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
@@ -671,19 +510,19 @@
|
|
| 671 |
"transformer.h.28.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 672 |
"transformer.h.28.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 673 |
"transformer.h.28.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 674 |
-
"transformer.h.29.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 675 |
"transformer.h.29.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 676 |
"transformer.h.29.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 677 |
"transformer.h.29.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 678 |
-
"transformer.h.29.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 679 |
-
"transformer.h.29.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 680 |
-
"transformer.h.29.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 681 |
-
"transformer.h.29.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 682 |
-
"transformer.h.29.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 683 |
-
"transformer.h.29.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 684 |
"transformer.h.29.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 685 |
"transformer.h.29.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 686 |
"transformer.h.29.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 687 |
"transformer.h.29.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 688 |
"transformer.h.29.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 689 |
"transformer.h.29.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
@@ -694,19 +533,42 @@
|
|
| 694 |
"transformer.h.29.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 695 |
"transformer.h.29.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 696 |
"transformer.h.29.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 697 |
-
"transformer.h.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 698 |
"transformer.h.30.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 699 |
"transformer.h.30.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 700 |
"transformer.h.30.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 701 |
-
"transformer.h.30.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 702 |
-
"transformer.h.30.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 703 |
-
"transformer.h.30.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 704 |
-
"transformer.h.30.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 705 |
-
"transformer.h.30.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 706 |
-
"transformer.h.30.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 707 |
"transformer.h.30.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 708 |
"transformer.h.30.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 709 |
"transformer.h.30.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 710 |
"transformer.h.30.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 711 |
"transformer.h.30.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 712 |
"transformer.h.30.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
@@ -717,19 +579,19 @@
|
|
| 717 |
"transformer.h.30.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 718 |
"transformer.h.30.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 719 |
"transformer.h.30.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 720 |
-
"transformer.h.31.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 721 |
"transformer.h.31.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 722 |
"transformer.h.31.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 723 |
"transformer.h.31.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 724 |
-
"transformer.h.31.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 725 |
-
"transformer.h.31.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 726 |
-
"transformer.h.31.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 727 |
-
"transformer.h.31.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 728 |
-
"transformer.h.31.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 729 |
-
"transformer.h.31.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 730 |
"transformer.h.31.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 731 |
"transformer.h.31.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 732 |
"transformer.h.31.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 733 |
"transformer.h.31.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 734 |
"transformer.h.31.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 735 |
"transformer.h.31.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
@@ -740,7 +602,145 @@
|
|
| 740 |
"transformer.h.31.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 741 |
"transformer.h.31.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 742 |
"transformer.h.31.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 743 |
"transformer.ln_f.weight": "model-00001-of-00002.safetensors",
|
| 744 |
-
"
|
| 745 |
}
|
| 746 |
-
}
|
|
|
|
| 3 |
"total_size": 5304229888
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 7 |
"transformer.h.0.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 8 |
"transformer.h.0.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 9 |
"transformer.h.0.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
"transformer.h.0.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 11 |
"transformer.h.0.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 12 |
"transformer.h.0.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 13 |
+
"transformer.h.0.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"transformer.h.0.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 15 |
+
"transformer.h.0.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 16 |
+
"transformer.h.0.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"transformer.h.0.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 18 |
+
"transformer.h.0.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 19 |
+
"transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 20 |
"transformer.h.0.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 21 |
"transformer.h.0.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 22 |
"transformer.h.0.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
|
|
| 27 |
"transformer.h.0.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 28 |
"transformer.h.0.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 29 |
"transformer.h.0.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
| 30 |
"transformer.h.1.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 31 |
"transformer.h.1.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 32 |
"transformer.h.1.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
"transformer.h.1.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 34 |
"transformer.h.1.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 35 |
"transformer.h.1.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 36 |
+
"transformer.h.1.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"transformer.h.1.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 38 |
+
"transformer.h.1.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 39 |
+
"transformer.h.1.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"transformer.h.1.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 41 |
+
"transformer.h.1.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 42 |
+
"transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 43 |
"transformer.h.1.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 44 |
"transformer.h.1.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 45 |
"transformer.h.1.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
|
|
| 50 |
"transformer.h.1.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 51 |
"transformer.h.1.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 52 |
"transformer.h.1.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
"transformer.h.10.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 54 |
"transformer.h.10.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 55 |
"transformer.h.10.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
"transformer.h.10.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 57 |
"transformer.h.10.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 58 |
"transformer.h.10.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 59 |
+
"transformer.h.10.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"transformer.h.10.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 61 |
+
"transformer.h.10.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 62 |
+
"transformer.h.10.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"transformer.h.10.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 64 |
+
"transformer.h.10.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 65 |
+
"transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 66 |
"transformer.h.10.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 67 |
"transformer.h.10.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 68 |
"transformer.h.10.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
|
|
| 73 |
"transformer.h.10.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 74 |
"transformer.h.10.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 75 |
"transformer.h.10.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
| 76 |
"transformer.h.11.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 77 |
"transformer.h.11.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 78 |
"transformer.h.11.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 79 |
"transformer.h.11.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 80 |
"transformer.h.11.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 81 |
"transformer.h.11.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 82 |
+
"transformer.h.11.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"transformer.h.11.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 84 |
+
"transformer.h.11.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 85 |
+
"transformer.h.11.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"transformer.h.11.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 87 |
+
"transformer.h.11.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 88 |
+
"transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 89 |
"transformer.h.11.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 90 |
"transformer.h.11.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 91 |
"transformer.h.11.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
|
|
| 96 |
"transformer.h.11.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 97 |
"transformer.h.11.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 98 |
"transformer.h.11.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
| 99 |
"transformer.h.12.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 100 |
"transformer.h.12.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 101 |
"transformer.h.12.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 102 |
"transformer.h.12.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 103 |
"transformer.h.12.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 104 |
"transformer.h.12.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 105 |
+
"transformer.h.12.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"transformer.h.12.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 107 |
+
"transformer.h.12.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 108 |
+
"transformer.h.12.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"transformer.h.12.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 110 |
+
"transformer.h.12.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 111 |
+
"transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 112 |
"transformer.h.12.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 113 |
"transformer.h.12.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 114 |
"transformer.h.12.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
|
|
| 119 |
"transformer.h.12.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 120 |
"transformer.h.12.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 121 |
"transformer.h.12.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
| 122 |
"transformer.h.13.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 123 |
"transformer.h.13.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 124 |
"transformer.h.13.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 125 |
"transformer.h.13.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 126 |
"transformer.h.13.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 127 |
"transformer.h.13.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 128 |
+
"transformer.h.13.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"transformer.h.13.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 130 |
+
"transformer.h.13.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 131 |
+
"transformer.h.13.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"transformer.h.13.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 133 |
+
"transformer.h.13.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 134 |
+
"transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 135 |
"transformer.h.13.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 136 |
"transformer.h.13.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 137 |
"transformer.h.13.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
|
|
| 142 |
"transformer.h.13.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 143 |
"transformer.h.13.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 144 |
"transformer.h.13.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
| 145 |
"transformer.h.14.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 146 |
"transformer.h.14.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 147 |
"transformer.h.14.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 148 |
"transformer.h.14.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 149 |
"transformer.h.14.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 150 |
"transformer.h.14.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 151 |
+
"transformer.h.14.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"transformer.h.14.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 153 |
+
"transformer.h.14.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 154 |
+
"transformer.h.14.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"transformer.h.14.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 156 |
+
"transformer.h.14.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 157 |
+
"transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 158 |
"transformer.h.14.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 159 |
"transformer.h.14.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 160 |
"transformer.h.14.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
|
|
| 165 |
"transformer.h.14.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 166 |
"transformer.h.14.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 167 |
"transformer.h.14.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
| 168 |
"transformer.h.15.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 169 |
"transformer.h.15.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 170 |
"transformer.h.15.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 171 |
"transformer.h.15.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 172 |
"transformer.h.15.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 173 |
"transformer.h.15.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 174 |
+
"transformer.h.15.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"transformer.h.15.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 176 |
+
"transformer.h.15.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 177 |
+
"transformer.h.15.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"transformer.h.15.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 179 |
+
"transformer.h.15.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 180 |
+
"transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 181 |
"transformer.h.15.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 182 |
"transformer.h.15.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 183 |
"transformer.h.15.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
|
|
| 188 |
"transformer.h.15.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 189 |
"transformer.h.15.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 190 |
"transformer.h.15.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
| 191 |
"transformer.h.16.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 192 |
"transformer.h.16.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 193 |
"transformer.h.16.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 194 |
"transformer.h.16.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 195 |
"transformer.h.16.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 196 |
"transformer.h.16.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 197 |
+
"transformer.h.16.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 198 |
+
"transformer.h.16.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 199 |
+
"transformer.h.16.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 200 |
+
"transformer.h.16.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"transformer.h.16.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 202 |
+
"transformer.h.16.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 203 |
+
"transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 204 |
"transformer.h.16.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 205 |
"transformer.h.16.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 206 |
"transformer.h.16.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
|
|
| 211 |
"transformer.h.16.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 212 |
"transformer.h.16.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 213 |
"transformer.h.16.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
| 214 |
"transformer.h.17.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 215 |
"transformer.h.17.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 216 |
"transformer.h.17.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 217 |
"transformer.h.17.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 218 |
"transformer.h.17.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 219 |
"transformer.h.17.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 220 |
+
"transformer.h.17.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"transformer.h.17.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 222 |
+
"transformer.h.17.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 223 |
+
"transformer.h.17.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 224 |
+
"transformer.h.17.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 225 |
+
"transformer.h.17.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 226 |
+
"transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 227 |
"transformer.h.17.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 228 |
"transformer.h.17.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 229 |
"transformer.h.17.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
|
|
| 234 |
"transformer.h.17.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 235 |
"transformer.h.17.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 236 |
"transformer.h.17.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
| 237 |
"transformer.h.18.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 238 |
"transformer.h.18.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 239 |
"transformer.h.18.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 240 |
"transformer.h.18.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 241 |
"transformer.h.18.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 242 |
"transformer.h.18.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 243 |
+
"transformer.h.18.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 244 |
+
"transformer.h.18.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 245 |
+
"transformer.h.18.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 246 |
+
"transformer.h.18.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 247 |
+
"transformer.h.18.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 248 |
+
"transformer.h.18.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 249 |
+
"transformer.h.18.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 250 |
"transformer.h.18.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 251 |
"transformer.h.18.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 252 |
"transformer.h.18.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
|
|
| 257 |
"transformer.h.18.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 258 |
"transformer.h.18.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 259 |
"transformer.h.18.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
| 260 |
"transformer.h.19.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 261 |
"transformer.h.19.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 262 |
"transformer.h.19.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 263 |
"transformer.h.19.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 264 |
"transformer.h.19.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 265 |
"transformer.h.19.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 266 |
+
"transformer.h.19.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"transformer.h.19.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 268 |
+
"transformer.h.19.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 269 |
+
"transformer.h.19.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"transformer.h.19.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 271 |
+
"transformer.h.19.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 272 |
+
"transformer.h.19.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 273 |
"transformer.h.19.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 274 |
"transformer.h.19.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 275 |
"transformer.h.19.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
|
|
| 280 |
"transformer.h.19.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 281 |
"transformer.h.19.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 282 |
"transformer.h.19.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 283 |
+
"transformer.h.2.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"transformer.h.2.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 285 |
+
"transformer.h.2.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 286 |
+
"transformer.h.2.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"transformer.h.2.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 288 |
+
"transformer.h.2.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 289 |
+
"transformer.h.2.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 290 |
+
"transformer.h.2.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 291 |
+
"transformer.h.2.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 292 |
+
"transformer.h.2.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"transformer.h.2.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 294 |
+
"transformer.h.2.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 295 |
+
"transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"transformer.h.2.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"transformer.h.2.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"transformer.h.2.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
| 299 |
+
"transformer.h.2.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
|
| 300 |
+
"transformer.h.2.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"transformer.h.2.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
|
| 302 |
+
"transformer.h.2.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
|
| 303 |
+
"transformer.h.2.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"transformer.h.2.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 305 |
+
"transformer.h.2.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 306 |
"transformer.h.20.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 307 |
"transformer.h.20.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 308 |
"transformer.h.20.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 309 |
"transformer.h.20.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 310 |
"transformer.h.20.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 311 |
"transformer.h.20.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 312 |
+
"transformer.h.20.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"transformer.h.20.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 314 |
+
"transformer.h.20.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 315 |
+
"transformer.h.20.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"transformer.h.20.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 317 |
+
"transformer.h.20.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 318 |
+
"transformer.h.20.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 319 |
"transformer.h.20.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 320 |
"transformer.h.20.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 321 |
"transformer.h.20.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
|
|
| 326 |
"transformer.h.20.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 327 |
"transformer.h.20.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 328 |
"transformer.h.20.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
| 329 |
"transformer.h.21.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 330 |
"transformer.h.21.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 331 |
"transformer.h.21.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 332 |
"transformer.h.21.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 333 |
"transformer.h.21.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 334 |
"transformer.h.21.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 335 |
+
"transformer.h.21.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 336 |
+
"transformer.h.21.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 337 |
+
"transformer.h.21.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 338 |
+
"transformer.h.21.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"transformer.h.21.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 340 |
+
"transformer.h.21.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 341 |
+
"transformer.h.21.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 342 |
"transformer.h.21.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 343 |
"transformer.h.21.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 344 |
"transformer.h.21.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
|
|
| 349 |
"transformer.h.21.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 350 |
"transformer.h.21.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 351 |
"transformer.h.21.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
| 352 |
"transformer.h.22.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 353 |
"transformer.h.22.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 354 |
"transformer.h.22.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 355 |
"transformer.h.22.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 356 |
"transformer.h.22.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 357 |
"transformer.h.22.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 358 |
+
"transformer.h.22.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"transformer.h.22.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 360 |
+
"transformer.h.22.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 361 |
+
"transformer.h.22.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"transformer.h.22.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 363 |
+
"transformer.h.22.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 364 |
+
"transformer.h.22.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 365 |
"transformer.h.22.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 366 |
"transformer.h.22.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 367 |
"transformer.h.22.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
|
|
| 372 |
"transformer.h.22.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 373 |
"transformer.h.22.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 374 |
"transformer.h.22.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
| 375 |
"transformer.h.23.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 376 |
"transformer.h.23.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 377 |
"transformer.h.23.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 378 |
"transformer.h.23.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 379 |
"transformer.h.23.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 380 |
"transformer.h.23.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 381 |
+
"transformer.h.23.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"transformer.h.23.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 383 |
+
"transformer.h.23.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 384 |
+
"transformer.h.23.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"transformer.h.23.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 386 |
+
"transformer.h.23.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 387 |
+
"transformer.h.23.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 388 |
"transformer.h.23.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 389 |
"transformer.h.23.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 390 |
"transformer.h.23.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
|
|
| 395 |
"transformer.h.23.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 396 |
"transformer.h.23.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 397 |
"transformer.h.23.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
| 398 |
"transformer.h.24.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 399 |
"transformer.h.24.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 400 |
"transformer.h.24.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 401 |
"transformer.h.24.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 402 |
"transformer.h.24.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 403 |
"transformer.h.24.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 404 |
+
"transformer.h.24.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"transformer.h.24.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 406 |
+
"transformer.h.24.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 407 |
+
"transformer.h.24.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 408 |
+
"transformer.h.24.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 409 |
+
"transformer.h.24.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 410 |
+
"transformer.h.24.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 411 |
"transformer.h.24.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 412 |
"transformer.h.24.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 413 |
"transformer.h.24.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
|
|
| 417 |
"transformer.h.24.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
|
| 418 |
"transformer.h.24.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 419 |
"transformer.h.24.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 420 |
+
"transformer.h.24.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 421 |
+
"transformer.h.25.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 422 |
+
"transformer.h.25.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 423 |
+
"transformer.h.25.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 424 |
"transformer.h.25.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 425 |
"transformer.h.25.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 426 |
"transformer.h.25.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 427 |
+
"transformer.h.25.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 428 |
+
"transformer.h.25.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 429 |
+
"transformer.h.25.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 430 |
+
"transformer.h.25.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 431 |
+
"transformer.h.25.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 432 |
+
"transformer.h.25.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 433 |
+
"transformer.h.25.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 434 |
"transformer.h.25.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 435 |
"transformer.h.25.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 436 |
"transformer.h.25.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
|
|
| 441 |
"transformer.h.25.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 442 |
"transformer.h.25.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 443 |
"transformer.h.25.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
| 444 |
"transformer.h.26.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 445 |
"transformer.h.26.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 446 |
"transformer.h.26.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 447 |
"transformer.h.26.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 448 |
"transformer.h.26.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 449 |
"transformer.h.26.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 450 |
+
"transformer.h.26.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 451 |
+
"transformer.h.26.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 452 |
+
"transformer.h.26.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 453 |
+
"transformer.h.26.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 454 |
+
"transformer.h.26.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 455 |
+
"transformer.h.26.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 456 |
+
"transformer.h.26.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 457 |
"transformer.h.26.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 458 |
"transformer.h.26.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 459 |
"transformer.h.26.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
|
|
| 464 |
"transformer.h.26.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 465 |
"transformer.h.26.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 466 |
"transformer.h.26.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
| 467 |
"transformer.h.27.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 468 |
"transformer.h.27.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 469 |
"transformer.h.27.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 470 |
"transformer.h.27.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 471 |
"transformer.h.27.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 472 |
"transformer.h.27.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 473 |
+
"transformer.h.27.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 474 |
+
"transformer.h.27.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 475 |
+
"transformer.h.27.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 476 |
+
"transformer.h.27.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 477 |
+
"transformer.h.27.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 478 |
+
"transformer.h.27.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 479 |
+
"transformer.h.27.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 480 |
"transformer.h.27.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 481 |
"transformer.h.27.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 482 |
"transformer.h.27.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
|
|
| 487 |
"transformer.h.27.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 488 |
"transformer.h.27.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 489 |
"transformer.h.27.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
| 490 |
"transformer.h.28.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 491 |
"transformer.h.28.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 492 |
"transformer.h.28.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 493 |
"transformer.h.28.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 494 |
"transformer.h.28.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 495 |
"transformer.h.28.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 496 |
+
"transformer.h.28.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 497 |
+
"transformer.h.28.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 498 |
+
"transformer.h.28.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 499 |
+
"transformer.h.28.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 500 |
+
"transformer.h.28.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 501 |
+
"transformer.h.28.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 502 |
+
"transformer.h.28.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 503 |
"transformer.h.28.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 504 |
"transformer.h.28.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 505 |
"transformer.h.28.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
|
|
| 510 |
"transformer.h.28.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 511 |
"transformer.h.28.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 512 |
"transformer.h.28.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
| 513 |
"transformer.h.29.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 514 |
"transformer.h.29.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 515 |
"transformer.h.29.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 516 |
"transformer.h.29.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 517 |
"transformer.h.29.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 518 |
"transformer.h.29.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 519 |
+
"transformer.h.29.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 520 |
+
"transformer.h.29.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 521 |
+
"transformer.h.29.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 522 |
+
"transformer.h.29.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 523 |
+
"transformer.h.29.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 524 |
+
"transformer.h.29.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 525 |
+
"transformer.h.29.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 526 |
"transformer.h.29.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 527 |
"transformer.h.29.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 528 |
"transformer.h.29.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
|
|
| 533 |
"transformer.h.29.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 534 |
"transformer.h.29.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 535 |
"transformer.h.29.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 536 |
+
"transformer.h.3.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 537 |
+
"transformer.h.3.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 538 |
+
"transformer.h.3.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 539 |
+
"transformer.h.3.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 540 |
+
"transformer.h.3.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 541 |
+
"transformer.h.3.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 542 |
+
"transformer.h.3.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 543 |
+
"transformer.h.3.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 544 |
+
"transformer.h.3.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 545 |
+
"transformer.h.3.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 546 |
+
"transformer.h.3.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 547 |
+
"transformer.h.3.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 548 |
+
"transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 549 |
+
"transformer.h.3.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 550 |
+
"transformer.h.3.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 551 |
+
"transformer.h.3.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
| 552 |
+
"transformer.h.3.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
|
| 553 |
+
"transformer.h.3.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
|
| 554 |
+
"transformer.h.3.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
|
| 555 |
+
"transformer.h.3.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
|
| 556 |
+
"transformer.h.3.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 557 |
+
"transformer.h.3.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 558 |
+
"transformer.h.3.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 559 |
"transformer.h.30.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 560 |
"transformer.h.30.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 561 |
"transformer.h.30.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 562 |
"transformer.h.30.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 563 |
"transformer.h.30.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 564 |
"transformer.h.30.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 565 |
+
"transformer.h.30.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 566 |
+
"transformer.h.30.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 567 |
+
"transformer.h.30.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 568 |
+
"transformer.h.30.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 569 |
+
"transformer.h.30.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 570 |
+
"transformer.h.30.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 571 |
+
"transformer.h.30.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 572 |
"transformer.h.30.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 573 |
"transformer.h.30.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 574 |
"transformer.h.30.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
|
|
| 579 |
"transformer.h.30.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 580 |
"transformer.h.30.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 581 |
"transformer.h.30.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
| 582 |
"transformer.h.31.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 583 |
"transformer.h.31.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 584 |
"transformer.h.31.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 585 |
"transformer.h.31.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 586 |
"transformer.h.31.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 587 |
"transformer.h.31.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 588 |
+
"transformer.h.31.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 589 |
+
"transformer.h.31.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 590 |
+
"transformer.h.31.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 591 |
+
"transformer.h.31.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 592 |
+
"transformer.h.31.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 593 |
+
"transformer.h.31.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 594 |
+
"transformer.h.31.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 595 |
"transformer.h.31.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 596 |
"transformer.h.31.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 597 |
"transformer.h.31.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
|
|
|
| 602 |
"transformer.h.31.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 603 |
"transformer.h.31.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 604 |
"transformer.h.31.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 605 |
+
"transformer.h.4.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 606 |
+
"transformer.h.4.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 607 |
+
"transformer.h.4.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 608 |
+
"transformer.h.4.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 609 |
+
"transformer.h.4.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 610 |
+
"transformer.h.4.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 611 |
+
"transformer.h.4.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 612 |
+
"transformer.h.4.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 613 |
+
"transformer.h.4.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 614 |
+
"transformer.h.4.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 615 |
+
"transformer.h.4.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 616 |
+
"transformer.h.4.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 617 |
+
"transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 618 |
+
"transformer.h.4.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 619 |
+
"transformer.h.4.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 620 |
+
"transformer.h.4.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
| 621 |
+
"transformer.h.4.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
|
| 622 |
+
"transformer.h.4.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
|
| 623 |
+
"transformer.h.4.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
|
| 624 |
+
"transformer.h.4.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
|
| 625 |
+
"transformer.h.4.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 626 |
+
"transformer.h.4.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 627 |
+
"transformer.h.4.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 628 |
+
"transformer.h.5.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 629 |
+
"transformer.h.5.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 630 |
+
"transformer.h.5.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 631 |
+
"transformer.h.5.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 632 |
+
"transformer.h.5.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 633 |
+
"transformer.h.5.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 634 |
+
"transformer.h.5.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 635 |
+
"transformer.h.5.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 636 |
+
"transformer.h.5.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 637 |
+
"transformer.h.5.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 638 |
+
"transformer.h.5.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 639 |
+
"transformer.h.5.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 640 |
+
"transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 641 |
+
"transformer.h.5.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 642 |
+
"transformer.h.5.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 643 |
+
"transformer.h.5.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
| 644 |
+
"transformer.h.5.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
|
| 645 |
+
"transformer.h.5.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
|
| 646 |
+
"transformer.h.5.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
|
| 647 |
+
"transformer.h.5.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
|
| 648 |
+
"transformer.h.5.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 649 |
+
"transformer.h.5.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 650 |
+
"transformer.h.5.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 651 |
+
"transformer.h.6.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 652 |
+
"transformer.h.6.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 653 |
+
"transformer.h.6.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 654 |
+
"transformer.h.6.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 655 |
+
"transformer.h.6.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 656 |
+
"transformer.h.6.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 657 |
+
"transformer.h.6.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 658 |
+
"transformer.h.6.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 659 |
+
"transformer.h.6.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 660 |
+
"transformer.h.6.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 661 |
+
"transformer.h.6.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 662 |
+
"transformer.h.6.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 663 |
+
"transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 664 |
+
"transformer.h.6.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 665 |
+
"transformer.h.6.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 666 |
+
"transformer.h.6.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
| 667 |
+
"transformer.h.6.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
|
| 668 |
+
"transformer.h.6.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
|
| 669 |
+
"transformer.h.6.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
|
| 670 |
+
"transformer.h.6.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
|
| 671 |
+
"transformer.h.6.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 672 |
+
"transformer.h.6.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 673 |
+
"transformer.h.6.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 674 |
+
"transformer.h.7.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 675 |
+
"transformer.h.7.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 676 |
+
"transformer.h.7.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 677 |
+
"transformer.h.7.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 678 |
+
"transformer.h.7.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 679 |
+
"transformer.h.7.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 680 |
+
"transformer.h.7.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 681 |
+
"transformer.h.7.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 682 |
+
"transformer.h.7.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 683 |
+
"transformer.h.7.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 684 |
+
"transformer.h.7.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 685 |
+
"transformer.h.7.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 686 |
+
"transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 687 |
+
"transformer.h.7.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 688 |
+
"transformer.h.7.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 689 |
+
"transformer.h.7.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
| 690 |
+
"transformer.h.7.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
|
| 691 |
+
"transformer.h.7.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
|
| 692 |
+
"transformer.h.7.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
|
| 693 |
+
"transformer.h.7.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
|
| 694 |
+
"transformer.h.7.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 695 |
+
"transformer.h.7.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 696 |
+
"transformer.h.7.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 697 |
+
"transformer.h.8.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 698 |
+
"transformer.h.8.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 699 |
+
"transformer.h.8.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 700 |
+
"transformer.h.8.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 701 |
+
"transformer.h.8.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 702 |
+
"transformer.h.8.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 703 |
+
"transformer.h.8.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 704 |
+
"transformer.h.8.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 705 |
+
"transformer.h.8.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 706 |
+
"transformer.h.8.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 707 |
+
"transformer.h.8.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 708 |
+
"transformer.h.8.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 709 |
+
"transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 710 |
+
"transformer.h.8.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 711 |
+
"transformer.h.8.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 712 |
+
"transformer.h.8.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
| 713 |
+
"transformer.h.8.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
|
| 714 |
+
"transformer.h.8.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
|
| 715 |
+
"transformer.h.8.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
|
| 716 |
+
"transformer.h.8.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
|
| 717 |
+
"transformer.h.8.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 718 |
+
"transformer.h.8.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 719 |
+
"transformer.h.8.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 720 |
+
"transformer.h.9.attn.attention.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 721 |
+
"transformer.h.9.attn.attention.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 722 |
+
"transformer.h.9.attn.attention.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 723 |
+
"transformer.h.9.attn.attention.out_proj.qweight": "model-00001-of-00002.safetensors",
|
| 724 |
+
"transformer.h.9.attn.attention.out_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 725 |
+
"transformer.h.9.attn.attention.out_proj.scales": "model-00001-of-00002.safetensors",
|
| 726 |
+
"transformer.h.9.attn.attention.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 727 |
+
"transformer.h.9.attn.attention.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 728 |
+
"transformer.h.9.attn.attention.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 729 |
+
"transformer.h.9.attn.attention.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 730 |
+
"transformer.h.9.attn.attention.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 731 |
+
"transformer.h.9.attn.attention.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 732 |
+
"transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
|
| 733 |
+
"transformer.h.9.ln_2.weight": "model-00001-of-00002.safetensors",
|
| 734 |
+
"transformer.h.9.mlp.c_fc_0.qweight": "model-00001-of-00002.safetensors",
|
| 735 |
+
"transformer.h.9.mlp.c_fc_0.qzeros": "model-00001-of-00002.safetensors",
|
| 736 |
+
"transformer.h.9.mlp.c_fc_0.scales": "model-00001-of-00002.safetensors",
|
| 737 |
+
"transformer.h.9.mlp.c_fc_1.qweight": "model-00001-of-00002.safetensors",
|
| 738 |
+
"transformer.h.9.mlp.c_fc_1.qzeros": "model-00001-of-00002.safetensors",
|
| 739 |
+
"transformer.h.9.mlp.c_fc_1.scales": "model-00001-of-00002.safetensors",
|
| 740 |
+
"transformer.h.9.mlp.c_proj.qweight": "model-00001-of-00002.safetensors",
|
| 741 |
+
"transformer.h.9.mlp.c_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 742 |
+
"transformer.h.9.mlp.c_proj.scales": "model-00001-of-00002.safetensors",
|
| 743 |
"transformer.ln_f.weight": "model-00001-of-00002.safetensors",
|
| 744 |
+
"transformer.wte.weight": "model-00001-of-00002.safetensors"
|
| 745 |
}
|
| 746 |
+
}
|