Upload folder using huggingface_hub
Browse files- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +112 -112
- tokenizer.json +3 -0
model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:920101ef445341261c32267787209868fd47c529abbea30c0726b53839d60bb3
|
3 |
+
size 4988032848
|
model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1df700e1de159311417205444bb334ff4817169199b079d5475a00a19db3418e
|
3 |
+
size 4660036776
|
model.safetensors.index.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"embed_tokens.weight": "model-00001-of-00002.safetensors",
|
@@ -52,102 +52,102 @@
|
|
52 |
"layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
53 |
"layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
54 |
"layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
55 |
-
"layers.12.input_layernorm.weight": "model-
|
56 |
-
"layers.12.mlp.down_proj.weight": "model-
|
57 |
-
"layers.12.mlp.gate_proj.weight": "model-
|
58 |
-
"layers.12.mlp.up_proj.weight": "model-
|
59 |
-
"layers.12.post_attention_layernorm.weight": "model-
|
60 |
"layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
61 |
"layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
62 |
-
"layers.12.self_attn.o_proj.weight": "model-
|
63 |
"layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
64 |
"layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
65 |
"layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
66 |
"layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
67 |
-
"layers.13.input_layernorm.weight": "model-
|
68 |
-
"layers.13.mlp.down_proj.weight": "model-
|
69 |
-
"layers.13.mlp.gate_proj.weight": "model-
|
70 |
-
"layers.13.mlp.up_proj.weight": "model-
|
71 |
-
"layers.13.post_attention_layernorm.weight": "model-
|
72 |
-
"layers.13.self_attn.k_proj.bias": "model-
|
73 |
-
"layers.13.self_attn.k_proj.weight": "model-
|
74 |
-
"layers.13.self_attn.o_proj.weight": "model-
|
75 |
-
"layers.13.self_attn.q_proj.bias": "model-
|
76 |
-
"layers.13.self_attn.q_proj.weight": "model-
|
77 |
-
"layers.13.self_attn.v_proj.bias": "model-
|
78 |
-
"layers.13.self_attn.v_proj.weight": "model-
|
79 |
-
"layers.14.input_layernorm.weight": "model-
|
80 |
-
"layers.14.mlp.down_proj.weight": "model-
|
81 |
-
"layers.14.mlp.gate_proj.weight": "model-
|
82 |
-
"layers.14.mlp.up_proj.weight": "model-
|
83 |
-
"layers.14.post_attention_layernorm.weight": "model-
|
84 |
-
"layers.14.self_attn.k_proj.bias": "model-
|
85 |
-
"layers.14.self_attn.k_proj.weight": "model-
|
86 |
-
"layers.14.self_attn.o_proj.weight": "model-
|
87 |
-
"layers.14.self_attn.q_proj.bias": "model-
|
88 |
-
"layers.14.self_attn.q_proj.weight": "model-
|
89 |
-
"layers.14.self_attn.v_proj.bias": "model-
|
90 |
-
"layers.14.self_attn.v_proj.weight": "model-
|
91 |
-
"layers.15.input_layernorm.weight": "model-
|
92 |
-
"layers.15.mlp.down_proj.weight": "model-
|
93 |
-
"layers.15.mlp.gate_proj.weight": "model-
|
94 |
-
"layers.15.mlp.up_proj.weight": "model-
|
95 |
-
"layers.15.post_attention_layernorm.weight": "model-
|
96 |
-
"layers.15.self_attn.k_proj.bias": "model-
|
97 |
-
"layers.15.self_attn.k_proj.weight": "model-
|
98 |
-
"layers.15.self_attn.o_proj.weight": "model-
|
99 |
-
"layers.15.self_attn.q_proj.bias": "model-
|
100 |
-
"layers.15.self_attn.q_proj.weight": "model-
|
101 |
-
"layers.15.self_attn.v_proj.bias": "model-
|
102 |
-
"layers.15.self_attn.v_proj.weight": "model-
|
103 |
-
"layers.16.input_layernorm.weight": "model-
|
104 |
-
"layers.16.mlp.down_proj.weight": "model-
|
105 |
-
"layers.16.mlp.gate_proj.weight": "model-
|
106 |
-
"layers.16.mlp.up_proj.weight": "model-
|
107 |
-
"layers.16.post_attention_layernorm.weight": "model-
|
108 |
-
"layers.16.self_attn.k_proj.bias": "model-
|
109 |
-
"layers.16.self_attn.k_proj.weight": "model-
|
110 |
-
"layers.16.self_attn.o_proj.weight": "model-
|
111 |
-
"layers.16.self_attn.q_proj.bias": "model-
|
112 |
-
"layers.16.self_attn.q_proj.weight": "model-
|
113 |
-
"layers.16.self_attn.v_proj.bias": "model-
|
114 |
-
"layers.16.self_attn.v_proj.weight": "model-
|
115 |
-
"layers.17.input_layernorm.weight": "model-
|
116 |
-
"layers.17.mlp.down_proj.weight": "model-
|
117 |
-
"layers.17.mlp.gate_proj.weight": "model-
|
118 |
-
"layers.17.mlp.up_proj.weight": "model-
|
119 |
-
"layers.17.post_attention_layernorm.weight": "model-
|
120 |
-
"layers.17.self_attn.k_proj.bias": "model-
|
121 |
-
"layers.17.self_attn.k_proj.weight": "model-
|
122 |
-
"layers.17.self_attn.o_proj.weight": "model-
|
123 |
-
"layers.17.self_attn.q_proj.bias": "model-
|
124 |
-
"layers.17.self_attn.q_proj.weight": "model-
|
125 |
-
"layers.17.self_attn.v_proj.bias": "model-
|
126 |
-
"layers.17.self_attn.v_proj.weight": "model-
|
127 |
-
"layers.18.input_layernorm.weight": "model-
|
128 |
-
"layers.18.mlp.down_proj.weight": "model-
|
129 |
-
"layers.18.mlp.gate_proj.weight": "model-
|
130 |
-
"layers.18.mlp.up_proj.weight": "model-
|
131 |
-
"layers.18.post_attention_layernorm.weight": "model-
|
132 |
-
"layers.18.self_attn.k_proj.bias": "model-
|
133 |
-
"layers.18.self_attn.k_proj.weight": "model-
|
134 |
-
"layers.18.self_attn.o_proj.weight": "model-
|
135 |
-
"layers.18.self_attn.q_proj.bias": "model-
|
136 |
-
"layers.18.self_attn.q_proj.weight": "model-
|
137 |
-
"layers.18.self_attn.v_proj.bias": "model-
|
138 |
-
"layers.18.self_attn.v_proj.weight": "model-
|
139 |
-
"layers.19.input_layernorm.weight": "model-
|
140 |
-
"layers.19.mlp.down_proj.weight": "model-
|
141 |
-
"layers.19.mlp.gate_proj.weight": "model-
|
142 |
-
"layers.19.mlp.up_proj.weight": "model-
|
143 |
-
"layers.19.post_attention_layernorm.weight": "model-
|
144 |
-
"layers.19.self_attn.k_proj.bias": "model-
|
145 |
-
"layers.19.self_attn.k_proj.weight": "model-
|
146 |
-
"layers.19.self_attn.o_proj.weight": "model-
|
147 |
-
"layers.19.self_attn.q_proj.bias": "model-
|
148 |
-
"layers.19.self_attn.q_proj.weight": "model-
|
149 |
-
"layers.19.self_attn.v_proj.bias": "model-
|
150 |
-
"layers.19.self_attn.v_proj.weight": "model-
|
151 |
"layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
152 |
"layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
153 |
"layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -160,30 +160,30 @@
|
|
160 |
"layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
161 |
"layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
162 |
"layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
163 |
-
"layers.20.input_layernorm.weight": "model-
|
164 |
-
"layers.20.mlp.down_proj.weight": "model-
|
165 |
-
"layers.20.mlp.gate_proj.weight": "model-
|
166 |
-
"layers.20.mlp.up_proj.weight": "model-
|
167 |
-
"layers.20.post_attention_layernorm.weight": "model-
|
168 |
-
"layers.20.self_attn.k_proj.bias": "model-
|
169 |
-
"layers.20.self_attn.k_proj.weight": "model-
|
170 |
-
"layers.20.self_attn.o_proj.weight": "model-
|
171 |
-
"layers.20.self_attn.q_proj.bias": "model-
|
172 |
-
"layers.20.self_attn.q_proj.weight": "model-
|
173 |
-
"layers.20.self_attn.v_proj.bias": "model-
|
174 |
-
"layers.20.self_attn.v_proj.weight": "model-
|
175 |
"layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
176 |
"layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
177 |
-
"layers.21.mlp.gate_proj.weight": "model-
|
178 |
-
"layers.21.mlp.up_proj.weight": "model-
|
179 |
"layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
180 |
-
"layers.21.self_attn.k_proj.bias": "model-
|
181 |
-
"layers.21.self_attn.k_proj.weight": "model-
|
182 |
-
"layers.21.self_attn.o_proj.weight": "model-
|
183 |
-
"layers.21.self_attn.q_proj.bias": "model-
|
184 |
-
"layers.21.self_attn.q_proj.weight": "model-
|
185 |
-
"layers.21.self_attn.v_proj.bias": "model-
|
186 |
-
"layers.21.self_attn.v_proj.weight": "model-
|
187 |
"layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
188 |
"layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
189 |
"layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 9648033280
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"embed_tokens.weight": "model-00001-of-00002.safetensors",
|
|
|
52 |
"layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
53 |
"layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
54 |
"layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
55 |
+
"layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
56 |
+
"layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
57 |
+
"layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
58 |
+
"layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
59 |
+
"layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
60 |
"layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
61 |
"layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
62 |
+
"layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
63 |
"layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
64 |
"layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
65 |
"layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
66 |
"layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
67 |
+
"layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
68 |
+
"layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
69 |
+
"layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
70 |
+
"layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
71 |
+
"layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
72 |
+
"layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
73 |
+
"layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
74 |
+
"layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
75 |
+
"layers.13.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
76 |
+
"layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
77 |
+
"layers.13.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
78 |
+
"layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
79 |
+
"layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
80 |
+
"layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
81 |
+
"layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
82 |
+
"layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
83 |
+
"layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
84 |
+
"layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
85 |
+
"layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
86 |
+
"layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
87 |
+
"layers.14.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
88 |
+
"layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
89 |
+
"layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
90 |
+
"layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
91 |
+
"layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
92 |
+
"layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
93 |
+
"layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
94 |
+
"layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
95 |
+
"layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
96 |
+
"layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
97 |
+
"layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
98 |
+
"layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
99 |
+
"layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
100 |
+
"layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
101 |
+
"layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
102 |
+
"layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
103 |
+
"layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
104 |
+
"layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
105 |
+
"layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
106 |
+
"layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
107 |
+
"layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
108 |
+
"layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
109 |
+
"layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
110 |
+
"layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
111 |
+
"layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
112 |
+
"layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
113 |
+
"layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
114 |
+
"layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
115 |
+
"layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
116 |
+
"layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
117 |
+
"layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
118 |
+
"layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
119 |
+
"layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
120 |
+
"layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
121 |
+
"layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
122 |
+
"layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
123 |
+
"layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
124 |
+
"layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
125 |
+
"layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
126 |
+
"layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
127 |
+
"layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
128 |
+
"layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
129 |
+
"layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
130 |
+
"layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
131 |
+
"layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
132 |
+
"layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
133 |
+
"layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
134 |
+
"layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
135 |
+
"layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
136 |
+
"layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
137 |
+
"layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
138 |
+
"layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
139 |
+
"layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
140 |
+
"layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
141 |
+
"layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
142 |
+
"layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
143 |
+
"layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
144 |
+
"layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
145 |
+
"layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
146 |
+
"layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
147 |
+
"layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
148 |
+
"layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
149 |
+
"layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
150 |
+
"layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
151 |
"layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
152 |
"layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
153 |
"layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
160 |
"layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
161 |
"layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
162 |
"layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
163 |
+
"layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
164 |
+
"layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
165 |
+
"layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
166 |
+
"layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
167 |
+
"layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
168 |
+
"layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
169 |
+
"layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
170 |
+
"layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
171 |
+
"layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
172 |
+
"layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
173 |
+
"layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
174 |
+
"layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
175 |
"layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
176 |
"layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
177 |
+
"layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
178 |
+
"layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
179 |
"layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
180 |
+
"layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
181 |
+
"layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
182 |
+
"layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
183 |
+
"layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
184 |
+
"layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
185 |
+
"layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
186 |
+
"layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
187 |
"layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
188 |
"layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
189 |
"layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
3 |
+
size 11421896
|