Commit
•
f4d7a60
1
Parent(s):
a409bf1
Upload model
Browse files- config.json +1 -1
- model-00001-of-00002.safetensors +2 -2
- model-00002-of-00002.safetensors +2 -2
- model.safetensors.index.json +70 -70
config.json
CHANGED
@@ -23,7 +23,7 @@
|
|
23 |
"rope_scaling": null,
|
24 |
"rope_theta": 10000,
|
25 |
"tie_word_embeddings": false,
|
26 |
-
"torch_dtype": "
|
27 |
"transformers_version": "4.41.0",
|
28 |
"use_cache": false,
|
29 |
"use_parallel_residual": false,
|
|
|
23 |
"rope_scaling": null,
|
24 |
"rope_theta": 10000,
|
25 |
"tie_word_embeddings": false,
|
26 |
+
"torch_dtype": "float16",
|
27 |
"transformers_version": "4.41.0",
|
28 |
"use_cache": false,
|
29 |
"use_parallel_residual": false,
|
model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:652773d22cd0719bf6b8b294cbd515596413337d77c656a03315b9350fa4316c
|
3 |
+
size 1986469888
|
model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a974801b9c9a0bdca1737a91c6f0f58efccace3055b86529c3931a9036512f0
|
3 |
+
size 1302599056
|
model.safetensors.index.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00002-of-00002.safetensors",
|
@@ -103,13 +103,13 @@
|
|
103 |
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
104 |
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
105 |
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
106 |
-
"model.layers.15.input_layernorm.bias": "model-
|
107 |
-
"model.layers.15.input_layernorm.weight": "model-
|
108 |
-
"model.layers.15.mlp.down_proj.weight": "model-
|
109 |
-
"model.layers.15.mlp.gate_proj.weight": "model-
|
110 |
-
"model.layers.15.mlp.up_proj.weight": "model-
|
111 |
-
"model.layers.15.post_attention_layernorm.bias": "model-
|
112 |
-
"model.layers.15.post_attention_layernorm.weight": "model-
|
113 |
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
114 |
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
115 |
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -117,62 +117,62 @@
|
|
117 |
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
118 |
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
119 |
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
120 |
-
"model.layers.16.input_layernorm.bias": "model-
|
121 |
-
"model.layers.16.input_layernorm.weight": "model-
|
122 |
-
"model.layers.16.mlp.down_proj.weight": "model-
|
123 |
-
"model.layers.16.mlp.gate_proj.weight": "model-
|
124 |
-
"model.layers.16.mlp.up_proj.weight": "model-
|
125 |
-
"model.layers.16.post_attention_layernorm.bias": "model-
|
126 |
-
"model.layers.16.post_attention_layernorm.weight": "model-
|
127 |
-
"model.layers.16.self_attn.k_proj.bias": "model-
|
128 |
-
"model.layers.16.self_attn.k_proj.weight": "model-
|
129 |
-
"model.layers.16.self_attn.o_proj.weight": "model-
|
130 |
-
"model.layers.16.self_attn.q_proj.bias": "model-
|
131 |
-
"model.layers.16.self_attn.q_proj.weight": "model-
|
132 |
-
"model.layers.16.self_attn.v_proj.bias": "model-
|
133 |
-
"model.layers.16.self_attn.v_proj.weight": "model-
|
134 |
-
"model.layers.17.input_layernorm.bias": "model-
|
135 |
-
"model.layers.17.input_layernorm.weight": "model-
|
136 |
-
"model.layers.17.mlp.down_proj.weight": "model-
|
137 |
-
"model.layers.17.mlp.gate_proj.weight": "model-
|
138 |
-
"model.layers.17.mlp.up_proj.weight": "model-
|
139 |
-
"model.layers.17.post_attention_layernorm.bias": "model-
|
140 |
-
"model.layers.17.post_attention_layernorm.weight": "model-
|
141 |
-
"model.layers.17.self_attn.k_proj.bias": "model-
|
142 |
-
"model.layers.17.self_attn.k_proj.weight": "model-
|
143 |
-
"model.layers.17.self_attn.o_proj.weight": "model-
|
144 |
-
"model.layers.17.self_attn.q_proj.bias": "model-
|
145 |
-
"model.layers.17.self_attn.q_proj.weight": "model-
|
146 |
-
"model.layers.17.self_attn.v_proj.bias": "model-
|
147 |
-
"model.layers.17.self_attn.v_proj.weight": "model-
|
148 |
-
"model.layers.18.input_layernorm.bias": "model-
|
149 |
-
"model.layers.18.input_layernorm.weight": "model-
|
150 |
-
"model.layers.18.mlp.down_proj.weight": "model-
|
151 |
-
"model.layers.18.mlp.gate_proj.weight": "model-
|
152 |
-
"model.layers.18.mlp.up_proj.weight": "model-
|
153 |
-
"model.layers.18.post_attention_layernorm.bias": "model-
|
154 |
-
"model.layers.18.post_attention_layernorm.weight": "model-
|
155 |
-
"model.layers.18.self_attn.k_proj.bias": "model-
|
156 |
-
"model.layers.18.self_attn.k_proj.weight": "model-
|
157 |
-
"model.layers.18.self_attn.o_proj.weight": "model-
|
158 |
-
"model.layers.18.self_attn.q_proj.bias": "model-
|
159 |
-
"model.layers.18.self_attn.q_proj.weight": "model-
|
160 |
-
"model.layers.18.self_attn.v_proj.bias": "model-
|
161 |
-
"model.layers.18.self_attn.v_proj.weight": "model-
|
162 |
-
"model.layers.19.input_layernorm.bias": "model-
|
163 |
-
"model.layers.19.input_layernorm.weight": "model-
|
164 |
-
"model.layers.19.mlp.down_proj.weight": "model-
|
165 |
-
"model.layers.19.mlp.gate_proj.weight": "model-
|
166 |
-
"model.layers.19.mlp.up_proj.weight": "model-
|
167 |
-
"model.layers.19.post_attention_layernorm.bias": "model-
|
168 |
-
"model.layers.19.post_attention_layernorm.weight": "model-
|
169 |
-
"model.layers.19.self_attn.k_proj.bias": "model-
|
170 |
-
"model.layers.19.self_attn.k_proj.weight": "model-
|
171 |
-
"model.layers.19.self_attn.o_proj.weight": "model-
|
172 |
-
"model.layers.19.self_attn.q_proj.bias": "model-
|
173 |
-
"model.layers.19.self_attn.q_proj.weight": "model-
|
174 |
-
"model.layers.19.self_attn.v_proj.bias": "model-
|
175 |
-
"model.layers.19.self_attn.v_proj.weight": "model-
|
176 |
"model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
177 |
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
178 |
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -194,13 +194,13 @@
|
|
194 |
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
195 |
"model.layers.20.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
|
196 |
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
197 |
-
"model.layers.20.self_attn.k_proj.bias": "model-
|
198 |
-
"model.layers.20.self_attn.k_proj.weight": "model-
|
199 |
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
200 |
-
"model.layers.20.self_attn.q_proj.bias": "model-
|
201 |
-
"model.layers.20.self_attn.q_proj.weight": "model-
|
202 |
-
"model.layers.20.self_attn.v_proj.bias": "model-
|
203 |
-
"model.layers.20.self_attn.v_proj.weight": "model-
|
204 |
"model.layers.21.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
205 |
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
206 |
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 3289030656
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00002-of-00002.safetensors",
|
|
|
103 |
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
104 |
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
105 |
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
106 |
+
"model.layers.15.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
107 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
108 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
109 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
110 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
111 |
+
"model.layers.15.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
|
112 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
113 |
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
114 |
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
115 |
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
117 |
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
118 |
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
119 |
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
120 |
+
"model.layers.16.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
121 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
122 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
123 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
124 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
125 |
+
"model.layers.16.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
|
126 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
127 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
128 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
129 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
130 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
131 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
132 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
133 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
134 |
+
"model.layers.17.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
135 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
136 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
137 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
138 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
139 |
+
"model.layers.17.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
|
140 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
141 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
142 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
143 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
144 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
145 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
146 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
147 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
148 |
+
"model.layers.18.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
149 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
150 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
151 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
152 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
153 |
+
"model.layers.18.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
|
154 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
155 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
156 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
157 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
158 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
159 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
160 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
161 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
162 |
+
"model.layers.19.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
163 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
164 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
165 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
166 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
167 |
+
"model.layers.19.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
|
168 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
169 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
170 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
171 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
172 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
173 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
174 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
175 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
176 |
"model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
177 |
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
178 |
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
194 |
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
195 |
"model.layers.20.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
|
196 |
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
197 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
198 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
199 |
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
200 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
201 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
202 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
203 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
204 |
"model.layers.21.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
205 |
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
206 |
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|