new_merged_weights
Browse files- config.json +1 -1
- pytorch_model-00001-of-00003.bin +2 -2
- pytorch_model-00002-of-00003.bin +2 -2
- pytorch_model-00003-of-00003.bin +2 -2
- pytorch_model.bin.index.json +1 -161
config.json
CHANGED
@@ -19,7 +19,7 @@
|
|
19 |
"rms_norm_eps": 1e-06,
|
20 |
"rope_scaling": null,
|
21 |
"tie_word_embeddings": false,
|
22 |
-
"torch_dtype": "
|
23 |
"transformers_version": "4.31.0",
|
24 |
"use_cache": true,
|
25 |
"vocab_size": 32000
|
|
|
19 |
"rms_norm_eps": 1e-06,
|
20 |
"rope_scaling": null,
|
21 |
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "float16",
|
23 |
"transformers_version": "4.31.0",
|
24 |
"use_cache": true,
|
25 |
"vocab_size": 32000
|
pytorch_model-00001-of-00003.bin
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 sha256:21bc8e213ae073fa43b0459d1475729e114c1dbdaf49583bcb95308e991c2fb3
|
3 |
+
size 9948728430
|
pytorch_model-00002-of-00003.bin
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 sha256:4327fdcb882c7f817ed86192902410cd7292b97799b4d0a0f415dd46d0cd2f22
|
3 |
+
size 9904165024
|
pytorch_model-00003-of-00003.bin
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:f3e0150b358b8e0c950daa1f2baca6288e8035702f5216f22c4b926684965bfc
|
3 |
+
size 6178983625
|
pytorch_model.bin.index.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "pytorch_model-00003-of-00003.bin",
|
@@ -12,12 +12,8 @@
|
|
12 |
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
13 |
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
14 |
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
15 |
-
"model.layers.0.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
16 |
-
"model.layers.0.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
17 |
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
18 |
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
19 |
-
"model.layers.0.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
20 |
-
"model.layers.0.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
21 |
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
22 |
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
23 |
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
@@ -26,12 +22,8 @@
|
|
26 |
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
27 |
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
28 |
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
29 |
-
"model.layers.1.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
30 |
-
"model.layers.1.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
31 |
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
32 |
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
33 |
-
"model.layers.1.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
34 |
-
"model.layers.1.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
35 |
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
36 |
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
37 |
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
@@ -40,12 +32,8 @@
|
|
40 |
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
41 |
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
42 |
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
43 |
-
"model.layers.10.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
44 |
-
"model.layers.10.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
45 |
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
46 |
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
47 |
-
"model.layers.10.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
48 |
-
"model.layers.10.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
49 |
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
50 |
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
51 |
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
@@ -54,12 +42,8 @@
|
|
54 |
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
55 |
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
56 |
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
57 |
-
"model.layers.11.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
58 |
-
"model.layers.11.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
59 |
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
60 |
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
61 |
-
"model.layers.11.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
62 |
-
"model.layers.11.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
63 |
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
64 |
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
65 |
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
@@ -68,12 +52,8 @@
|
|
68 |
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
69 |
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
70 |
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
71 |
-
"model.layers.12.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
72 |
-
"model.layers.12.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
73 |
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
74 |
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
75 |
-
"model.layers.12.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
76 |
-
"model.layers.12.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
77 |
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
78 |
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
79 |
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
@@ -82,12 +62,8 @@
|
|
82 |
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
83 |
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
84 |
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
85 |
-
"model.layers.13.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
86 |
-
"model.layers.13.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
87 |
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
88 |
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
89 |
-
"model.layers.13.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
90 |
-
"model.layers.13.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
91 |
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
92 |
"model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
93 |
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
@@ -96,12 +72,8 @@
|
|
96 |
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
97 |
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
98 |
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
99 |
-
"model.layers.14.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
100 |
-
"model.layers.14.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
101 |
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
102 |
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
103 |
-
"model.layers.14.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
104 |
-
"model.layers.14.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
105 |
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
106 |
"model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
107 |
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
@@ -110,12 +82,8 @@
|
|
110 |
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
111 |
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
112 |
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
113 |
-
"model.layers.15.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
114 |
-
"model.layers.15.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
115 |
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
116 |
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
117 |
-
"model.layers.15.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
118 |
-
"model.layers.15.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
119 |
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
120 |
"model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
121 |
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
@@ -124,12 +92,8 @@
|
|
124 |
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
125 |
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
126 |
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
127 |
-
"model.layers.16.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
128 |
-
"model.layers.16.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
129 |
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
130 |
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
131 |
-
"model.layers.16.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
132 |
-
"model.layers.16.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
133 |
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
134 |
"model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
135 |
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
@@ -138,12 +102,8 @@
|
|
138 |
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
139 |
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
140 |
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
141 |
-
"model.layers.17.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
142 |
-
"model.layers.17.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
143 |
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
144 |
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
145 |
-
"model.layers.17.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
146 |
-
"model.layers.17.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
147 |
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
148 |
"model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
149 |
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
@@ -152,12 +112,8 @@
|
|
152 |
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
153 |
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
154 |
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
155 |
-
"model.layers.18.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
156 |
-
"model.layers.18.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
157 |
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
158 |
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
159 |
-
"model.layers.18.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
160 |
-
"model.layers.18.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
161 |
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
162 |
"model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
163 |
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
@@ -166,12 +122,8 @@
|
|
166 |
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
167 |
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
168 |
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
169 |
-
"model.layers.19.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
170 |
-
"model.layers.19.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
171 |
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
172 |
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
173 |
-
"model.layers.19.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
174 |
-
"model.layers.19.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
175 |
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
176 |
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
177 |
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
@@ -180,12 +132,8 @@
|
|
180 |
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
181 |
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
182 |
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
183 |
-
"model.layers.2.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
184 |
-
"model.layers.2.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
185 |
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
186 |
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
187 |
-
"model.layers.2.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
188 |
-
"model.layers.2.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
189 |
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
190 |
"model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
191 |
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
@@ -194,12 +142,8 @@
|
|
194 |
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
195 |
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
196 |
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
197 |
-
"model.layers.20.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
198 |
-
"model.layers.20.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
199 |
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
200 |
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
201 |
-
"model.layers.20.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
202 |
-
"model.layers.20.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
203 |
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
204 |
"model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
205 |
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
@@ -208,12 +152,8 @@
|
|
208 |
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
209 |
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
210 |
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
211 |
-
"model.layers.21.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
212 |
-
"model.layers.21.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
213 |
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
214 |
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
215 |
-
"model.layers.21.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
216 |
-
"model.layers.21.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
217 |
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
218 |
"model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
219 |
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
@@ -222,12 +162,8 @@
|
|
222 |
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
223 |
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
224 |
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
225 |
-
"model.layers.22.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
226 |
-
"model.layers.22.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
227 |
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
228 |
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
229 |
-
"model.layers.22.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
230 |
-
"model.layers.22.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
231 |
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
232 |
"model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
233 |
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
@@ -236,12 +172,8 @@
|
|
236 |
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
237 |
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
238 |
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
239 |
-
"model.layers.23.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
240 |
-
"model.layers.23.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
241 |
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
242 |
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
243 |
-
"model.layers.23.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
244 |
-
"model.layers.23.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
245 |
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
246 |
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
247 |
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
@@ -250,12 +182,8 @@
|
|
250 |
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
251 |
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
252 |
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
253 |
-
"model.layers.24.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
254 |
-
"model.layers.24.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
255 |
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
256 |
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
257 |
-
"model.layers.24.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
258 |
-
"model.layers.24.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
259 |
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
260 |
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
261 |
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
@@ -264,12 +192,8 @@
|
|
264 |
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
265 |
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
266 |
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
267 |
-
"model.layers.25.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
268 |
-
"model.layers.25.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
269 |
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
270 |
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
271 |
-
"model.layers.25.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
272 |
-
"model.layers.25.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
273 |
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
274 |
"model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
275 |
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
@@ -278,12 +202,8 @@
|
|
278 |
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
279 |
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
280 |
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
281 |
-
"model.layers.26.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
282 |
-
"model.layers.26.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
283 |
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
284 |
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
285 |
-
"model.layers.26.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
286 |
-
"model.layers.26.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
287 |
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
288 |
"model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
289 |
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
@@ -292,12 +212,8 @@
|
|
292 |
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
293 |
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
294 |
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
295 |
-
"model.layers.27.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
296 |
-
"model.layers.27.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
297 |
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
298 |
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
299 |
-
"model.layers.27.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
300 |
-
"model.layers.27.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
301 |
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
302 |
"model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
303 |
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
@@ -306,12 +222,8 @@
|
|
306 |
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
307 |
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
308 |
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
309 |
-
"model.layers.28.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
310 |
-
"model.layers.28.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
311 |
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
312 |
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
313 |
-
"model.layers.28.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
314 |
-
"model.layers.28.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
315 |
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
316 |
"model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
317 |
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
@@ -320,12 +232,8 @@
|
|
320 |
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
321 |
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
322 |
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
323 |
-
"model.layers.29.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
324 |
-
"model.layers.29.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
325 |
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
326 |
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
327 |
-
"model.layers.29.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
328 |
-
"model.layers.29.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
329 |
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
330 |
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
331 |
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
@@ -334,12 +242,8 @@
|
|
334 |
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
335 |
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
336 |
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
337 |
-
"model.layers.3.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
338 |
-
"model.layers.3.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
339 |
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
340 |
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
341 |
-
"model.layers.3.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
342 |
-
"model.layers.3.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
343 |
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
344 |
"model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
345 |
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
@@ -348,12 +252,8 @@
|
|
348 |
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
349 |
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
350 |
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
351 |
-
"model.layers.30.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
352 |
-
"model.layers.30.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
353 |
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
354 |
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
355 |
-
"model.layers.30.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00002-of-00003.bin",
|
356 |
-
"model.layers.30.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00002-of-00003.bin",
|
357 |
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
358 |
"model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
359 |
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
@@ -362,12 +262,8 @@
|
|
362 |
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
363 |
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
364 |
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
365 |
-
"model.layers.31.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
|
366 |
-
"model.layers.31.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
|
367 |
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
368 |
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
369 |
-
"model.layers.31.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
|
370 |
-
"model.layers.31.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
|
371 |
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
372 |
"model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
373 |
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
@@ -376,12 +272,8 @@
|
|
376 |
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
377 |
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
378 |
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
379 |
-
"model.layers.32.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
|
380 |
-
"model.layers.32.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
|
381 |
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
382 |
"model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
383 |
-
"model.layers.32.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
|
384 |
-
"model.layers.32.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
|
385 |
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
386 |
"model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
387 |
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
@@ -390,12 +282,8 @@
|
|
390 |
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
391 |
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
392 |
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
393 |
-
"model.layers.33.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
|
394 |
-
"model.layers.33.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
|
395 |
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
396 |
"model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
397 |
-
"model.layers.33.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
|
398 |
-
"model.layers.33.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
|
399 |
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
400 |
"model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
401 |
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
@@ -404,12 +292,8 @@
|
|
404 |
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
405 |
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
406 |
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
407 |
-
"model.layers.34.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
|
408 |
-
"model.layers.34.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
|
409 |
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
410 |
"model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
411 |
-
"model.layers.34.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
|
412 |
-
"model.layers.34.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
|
413 |
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
414 |
"model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
415 |
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
@@ -418,12 +302,8 @@
|
|
418 |
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
419 |
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
420 |
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
421 |
-
"model.layers.35.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
|
422 |
-
"model.layers.35.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
|
423 |
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
424 |
"model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
425 |
-
"model.layers.35.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
|
426 |
-
"model.layers.35.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
|
427 |
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
428 |
"model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
429 |
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
@@ -432,12 +312,8 @@
|
|
432 |
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
433 |
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
434 |
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
435 |
-
"model.layers.36.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
|
436 |
-
"model.layers.36.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
|
437 |
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
438 |
"model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
439 |
-
"model.layers.36.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
|
440 |
-
"model.layers.36.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
|
441 |
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
442 |
"model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
443 |
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
@@ -446,12 +322,8 @@
|
|
446 |
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
447 |
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
448 |
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
449 |
-
"model.layers.37.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
|
450 |
-
"model.layers.37.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
|
451 |
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
452 |
"model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
453 |
-
"model.layers.37.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
|
454 |
-
"model.layers.37.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
|
455 |
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
456 |
"model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
457 |
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
@@ -460,12 +332,8 @@
|
|
460 |
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
461 |
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
462 |
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
463 |
-
"model.layers.38.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
|
464 |
-
"model.layers.38.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
|
465 |
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
466 |
"model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
467 |
-
"model.layers.38.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
|
468 |
-
"model.layers.38.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
|
469 |
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
470 |
"model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
471 |
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
@@ -474,12 +342,8 @@
|
|
474 |
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
475 |
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
476 |
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
477 |
-
"model.layers.39.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
|
478 |
-
"model.layers.39.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
|
479 |
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
480 |
"model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
481 |
-
"model.layers.39.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00003-of-00003.bin",
|
482 |
-
"model.layers.39.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00003-of-00003.bin",
|
483 |
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
484 |
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
485 |
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
@@ -488,12 +352,8 @@
|
|
488 |
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
489 |
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
490 |
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
491 |
-
"model.layers.4.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
492 |
-
"model.layers.4.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
493 |
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
494 |
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
495 |
-
"model.layers.4.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
496 |
-
"model.layers.4.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
497 |
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
498 |
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
499 |
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
@@ -502,12 +362,8 @@
|
|
502 |
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
503 |
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
504 |
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
505 |
-
"model.layers.5.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
506 |
-
"model.layers.5.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
507 |
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
508 |
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
509 |
-
"model.layers.5.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
510 |
-
"model.layers.5.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
511 |
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
512 |
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
513 |
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
@@ -516,12 +372,8 @@
|
|
516 |
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
517 |
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
518 |
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
519 |
-
"model.layers.6.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
520 |
-
"model.layers.6.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
521 |
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
522 |
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
523 |
-
"model.layers.6.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
524 |
-
"model.layers.6.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
525 |
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
526 |
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
527 |
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
@@ -530,12 +382,8 @@
|
|
530 |
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
531 |
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
532 |
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
533 |
-
"model.layers.7.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
534 |
-
"model.layers.7.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
535 |
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
536 |
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
537 |
-
"model.layers.7.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
538 |
-
"model.layers.7.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
539 |
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
540 |
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
541 |
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
@@ -544,12 +392,8 @@
|
|
544 |
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
545 |
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
546 |
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
547 |
-
"model.layers.8.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
548 |
-
"model.layers.8.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
549 |
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
550 |
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
551 |
-
"model.layers.8.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
552 |
-
"model.layers.8.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
553 |
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
554 |
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
555 |
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
@@ -558,12 +402,8 @@
|
|
558 |
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
559 |
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
560 |
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
561 |
-
"model.layers.9.self_attn.q_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
562 |
-
"model.layers.9.self_attn.q_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
563 |
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
564 |
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
565 |
-
"model.layers.9.self_attn.v_proj.lora_A.default.weight": "pytorch_model-00001-of-00003.bin",
|
566 |
-
"model.layers.9.self_attn.v_proj.lora_B.default.weight": "pytorch_model-00001-of-00003.bin",
|
567 |
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
568 |
"model.norm.weight": "pytorch_model-00003-of-00003.bin"
|
569 |
}
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 26031738880
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "pytorch_model-00003-of-00003.bin",
|
|
|
12 |
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
13 |
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
14 |
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
15 |
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
16 |
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
17 |
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
18 |
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
19 |
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
22 |
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
23 |
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
24 |
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
25 |
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
26 |
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
27 |
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
28 |
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
29 |
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
32 |
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
33 |
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
34 |
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
35 |
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
36 |
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
37 |
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
38 |
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
39 |
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
42 |
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
43 |
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
44 |
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
45 |
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
46 |
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
47 |
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
48 |
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
49 |
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
52 |
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
53 |
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
54 |
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
55 |
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
56 |
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
57 |
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
58 |
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
59 |
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
62 |
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
63 |
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
64 |
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
65 |
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
66 |
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
67 |
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
68 |
"model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
69 |
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
72 |
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
73 |
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
74 |
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
75 |
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
76 |
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
77 |
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
78 |
"model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
79 |
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
82 |
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
83 |
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
84 |
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
85 |
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
86 |
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
87 |
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
88 |
"model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
89 |
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
92 |
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
93 |
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
94 |
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
95 |
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
96 |
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
97 |
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
98 |
"model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
99 |
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
102 |
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
103 |
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
104 |
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
105 |
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
106 |
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
107 |
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
108 |
"model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
109 |
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
112 |
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
113 |
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
114 |
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
115 |
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
116 |
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
117 |
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
118 |
"model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
119 |
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
122 |
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
123 |
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
124 |
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
125 |
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
126 |
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
127 |
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
128 |
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
129 |
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
132 |
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
133 |
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
134 |
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
135 |
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
136 |
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
137 |
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
138 |
"model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
139 |
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
142 |
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
143 |
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
144 |
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
145 |
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
146 |
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
147 |
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
148 |
"model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
149 |
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
152 |
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
153 |
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
154 |
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
155 |
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
156 |
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
157 |
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
158 |
"model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
159 |
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
162 |
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
163 |
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
164 |
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
165 |
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
166 |
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
167 |
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
168 |
"model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
169 |
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
172 |
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
173 |
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
174 |
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
175 |
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
176 |
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
177 |
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
178 |
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
179 |
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
182 |
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
183 |
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
184 |
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
185 |
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
186 |
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
187 |
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
188 |
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
189 |
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
192 |
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
193 |
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
194 |
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
195 |
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
196 |
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
197 |
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
198 |
"model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
199 |
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
202 |
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
203 |
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
204 |
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
205 |
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
206 |
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
207 |
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
208 |
"model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
209 |
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
212 |
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
213 |
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
214 |
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
215 |
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
216 |
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
217 |
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
218 |
"model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
219 |
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
222 |
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
223 |
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
224 |
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
225 |
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
226 |
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
227 |
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
228 |
"model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
229 |
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
232 |
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
233 |
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
234 |
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
235 |
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
236 |
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
237 |
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
238 |
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
239 |
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
242 |
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
243 |
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
244 |
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
245 |
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
246 |
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
247 |
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
248 |
"model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
249 |
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
|
|
252 |
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
253 |
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
254 |
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
255 |
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
256 |
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
|
|
|
|
257 |
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
258 |
"model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
259 |
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
|
|
262 |
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
263 |
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
264 |
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
|
|
|
|
265 |
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
266 |
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
|
|
|
|
267 |
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
268 |
"model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
269 |
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
|
|
272 |
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
273 |
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
274 |
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
|
|
|
|
275 |
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
276 |
"model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
|
|
|
|
277 |
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
278 |
"model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
279 |
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
|
|
282 |
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
283 |
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
284 |
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
|
|
|
|
285 |
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
286 |
"model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
|
|
|
|
287 |
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
288 |
"model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
289 |
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
|
|
292 |
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
293 |
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
294 |
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
|
|
|
|
295 |
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
296 |
"model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
|
|
|
|
297 |
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
298 |
"model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
299 |
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
|
|
302 |
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
303 |
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
304 |
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
|
|
|
|
305 |
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
306 |
"model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
|
|
|
|
307 |
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
308 |
"model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
309 |
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
|
|
312 |
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
313 |
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
314 |
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
|
|
|
|
315 |
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
316 |
"model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
|
|
|
|
317 |
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
318 |
"model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
319 |
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
|
|
322 |
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
323 |
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
324 |
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
|
|
|
|
325 |
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
326 |
"model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
|
|
|
|
327 |
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
328 |
"model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
329 |
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
|
|
332 |
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
333 |
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
334 |
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
|
|
|
|
335 |
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
336 |
"model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
|
|
|
|
337 |
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
338 |
"model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
339 |
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
|
|
342 |
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
343 |
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
344 |
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
|
|
|
|
345 |
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
346 |
"model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
|
|
|
|
347 |
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
348 |
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
349 |
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
352 |
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
353 |
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
354 |
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
355 |
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
356 |
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
357 |
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
358 |
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
359 |
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
362 |
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
363 |
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
364 |
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
365 |
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
366 |
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
367 |
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
368 |
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
369 |
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
372 |
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
373 |
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
374 |
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
375 |
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
376 |
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
377 |
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
378 |
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
379 |
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
382 |
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
383 |
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
384 |
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
385 |
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
386 |
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
387 |
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
388 |
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
389 |
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
392 |
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
393 |
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
394 |
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
395 |
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
396 |
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
397 |
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
398 |
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
399 |
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
402 |
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
403 |
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
404 |
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
405 |
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
406 |
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
|
|
|
|
407 |
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
408 |
"model.norm.weight": "pytorch_model-00003-of-00003.bin"
|
409 |
}
|