Upload TransformerForCausalLM
Browse files- README.md +1 -1
- config.json +8 -2
- generation_config.json +1 -1
- model-00001-of-00002.safetensors +2 -2
- model-00002-of-00002.safetensors +2 -2
- model.safetensors.index.json +32 -0
README.md
CHANGED
@@ -8,4 +8,4 @@ license: mit
|
|
8 |
datasets:
|
9 |
- cerebras/SlimPajama-627B
|
10 |
library_name: fla
|
11 |
-
---
|
|
|
8 |
datasets:
|
9 |
- cerebras/SlimPajama-627B
|
10 |
library_name: fla
|
11 |
+
---
|
config.json
CHANGED
@@ -5,9 +5,11 @@
|
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
"bos_token_id": 1,
|
|
|
8 |
"eos_token_id": 2,
|
9 |
"fuse_cross_entropy": true,
|
10 |
"fuse_norm": true,
|
|
|
11 |
"hidden_act": "swish",
|
12 |
"hidden_ratio": 4,
|
13 |
"hidden_size": 2560,
|
@@ -15,12 +17,16 @@
|
|
15 |
"intermediate_size": null,
|
16 |
"max_position_embeddings": 2048,
|
17 |
"model_type": "transformer",
|
|
|
18 |
"num_heads": 20,
|
19 |
"num_hidden_layers": 32,
|
|
|
20 |
"rms_norm_eps": 1e-06,
|
|
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "bfloat16",
|
23 |
-
"transformers_version": "4.
|
24 |
"use_cache": true,
|
25 |
-
"vocab_size": 32000
|
|
|
26 |
}
|
|
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
"bos_token_id": 1,
|
8 |
+
"elementwise_affine": true,
|
9 |
"eos_token_id": 2,
|
10 |
"fuse_cross_entropy": true,
|
11 |
"fuse_norm": true,
|
12 |
+
"fuse_swiglu": true,
|
13 |
"hidden_act": "swish",
|
14 |
"hidden_ratio": 4,
|
15 |
"hidden_size": 2560,
|
|
|
17 |
"intermediate_size": null,
|
18 |
"max_position_embeddings": 2048,
|
19 |
"model_type": "transformer",
|
20 |
+
"norm_eps": 1e-06,
|
21 |
"num_heads": 20,
|
22 |
"num_hidden_layers": 32,
|
23 |
+
"num_kv_heads": null,
|
24 |
"rms_norm_eps": 1e-06,
|
25 |
+
"rope_theta": 10000.0,
|
26 |
"tie_word_embeddings": false,
|
27 |
"torch_dtype": "bfloat16",
|
28 |
+
"transformers_version": "4.48.2",
|
29 |
"use_cache": true,
|
30 |
+
"vocab_size": 32000,
|
31 |
+
"window_size": null
|
32 |
}
|
generation_config.json
CHANGED
@@ -2,5 +2,5 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
-
"transformers_version": "4.
|
6 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.48.2"
|
6 |
}
|
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 sha256:19c08e94c9d4c4a985d07b57823fa7aa589becb294af61a454b69f18f35ce360
|
3 |
+
size 4974530632
|
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 sha256:1960431ae037a4a71d147ca442c04d3810bbe9f2f2f564b286616c0b77235c72
|
3 |
+
size 428622344
|
model.safetensors.index.json
CHANGED
@@ -12,6 +12,7 @@
|
|
12 |
"model.layers.0.attn_norm.weight": "model-00001-of-00002.safetensors",
|
13 |
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
14 |
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
15 |
"model.layers.0.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
16 |
"model.layers.1.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
17 |
"model.layers.1.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -20,6 +21,7 @@
|
|
20 |
"model.layers.1.attn_norm.weight": "model-00001-of-00002.safetensors",
|
21 |
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
22 |
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
23 |
"model.layers.1.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
24 |
"model.layers.10.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
25 |
"model.layers.10.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -28,6 +30,7 @@
|
|
28 |
"model.layers.10.attn_norm.weight": "model-00001-of-00002.safetensors",
|
29 |
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
30 |
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
31 |
"model.layers.10.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
32 |
"model.layers.11.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
33 |
"model.layers.11.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -36,6 +39,7 @@
|
|
36 |
"model.layers.11.attn_norm.weight": "model-00001-of-00002.safetensors",
|
37 |
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
38 |
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
39 |
"model.layers.11.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
40 |
"model.layers.12.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
41 |
"model.layers.12.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -44,6 +48,7 @@
|
|
44 |
"model.layers.12.attn_norm.weight": "model-00001-of-00002.safetensors",
|
45 |
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
46 |
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
47 |
"model.layers.12.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
48 |
"model.layers.13.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
49 |
"model.layers.13.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -52,6 +57,7 @@
|
|
52 |
"model.layers.13.attn_norm.weight": "model-00001-of-00002.safetensors",
|
53 |
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
54 |
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
55 |
"model.layers.13.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
56 |
"model.layers.14.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
57 |
"model.layers.14.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -60,6 +66,7 @@
|
|
60 |
"model.layers.14.attn_norm.weight": "model-00001-of-00002.safetensors",
|
61 |
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
62 |
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
63 |
"model.layers.14.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
64 |
"model.layers.15.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
65 |
"model.layers.15.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -68,6 +75,7 @@
|
|
68 |
"model.layers.15.attn_norm.weight": "model-00001-of-00002.safetensors",
|
69 |
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
70 |
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
71 |
"model.layers.15.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
72 |
"model.layers.16.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
73 |
"model.layers.16.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -76,6 +84,7 @@
|
|
76 |
"model.layers.16.attn_norm.weight": "model-00001-of-00002.safetensors",
|
77 |
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
78 |
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
79 |
"model.layers.16.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
80 |
"model.layers.17.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
81 |
"model.layers.17.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -84,6 +93,7 @@
|
|
84 |
"model.layers.17.attn_norm.weight": "model-00001-of-00002.safetensors",
|
85 |
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
86 |
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
87 |
"model.layers.17.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
88 |
"model.layers.18.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
89 |
"model.layers.18.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -92,6 +102,7 @@
|
|
92 |
"model.layers.18.attn_norm.weight": "model-00001-of-00002.safetensors",
|
93 |
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
94 |
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
95 |
"model.layers.18.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
96 |
"model.layers.19.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
97 |
"model.layers.19.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -100,6 +111,7 @@
|
|
100 |
"model.layers.19.attn_norm.weight": "model-00001-of-00002.safetensors",
|
101 |
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
102 |
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
103 |
"model.layers.19.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
104 |
"model.layers.2.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
105 |
"model.layers.2.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -108,6 +120,7 @@
|
|
108 |
"model.layers.2.attn_norm.weight": "model-00001-of-00002.safetensors",
|
109 |
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
110 |
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
111 |
"model.layers.2.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
112 |
"model.layers.20.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
113 |
"model.layers.20.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -116,6 +129,7 @@
|
|
116 |
"model.layers.20.attn_norm.weight": "model-00001-of-00002.safetensors",
|
117 |
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
118 |
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
119 |
"model.layers.20.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
120 |
"model.layers.21.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
121 |
"model.layers.21.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -124,6 +138,7 @@
|
|
124 |
"model.layers.21.attn_norm.weight": "model-00001-of-00002.safetensors",
|
125 |
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
126 |
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
127 |
"model.layers.21.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
128 |
"model.layers.22.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
129 |
"model.layers.22.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -132,6 +147,7 @@
|
|
132 |
"model.layers.22.attn_norm.weight": "model-00001-of-00002.safetensors",
|
133 |
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
134 |
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
135 |
"model.layers.22.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
136 |
"model.layers.23.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
137 |
"model.layers.23.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -140,6 +156,7 @@
|
|
140 |
"model.layers.23.attn_norm.weight": "model-00001-of-00002.safetensors",
|
141 |
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
142 |
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
143 |
"model.layers.23.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
144 |
"model.layers.24.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
145 |
"model.layers.24.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -148,6 +165,7 @@
|
|
148 |
"model.layers.24.attn_norm.weight": "model-00001-of-00002.safetensors",
|
149 |
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
150 |
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
151 |
"model.layers.24.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
152 |
"model.layers.25.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
153 |
"model.layers.25.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -156,6 +174,7 @@
|
|
156 |
"model.layers.25.attn_norm.weight": "model-00001-of-00002.safetensors",
|
157 |
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
158 |
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
159 |
"model.layers.25.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
160 |
"model.layers.26.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
161 |
"model.layers.26.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -164,6 +183,7 @@
|
|
164 |
"model.layers.26.attn_norm.weight": "model-00001-of-00002.safetensors",
|
165 |
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
166 |
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
167 |
"model.layers.26.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
168 |
"model.layers.27.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
169 |
"model.layers.27.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -172,6 +192,7 @@
|
|
172 |
"model.layers.27.attn_norm.weight": "model-00001-of-00002.safetensors",
|
173 |
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
174 |
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
175 |
"model.layers.27.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
176 |
"model.layers.28.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
177 |
"model.layers.28.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -180,6 +201,7 @@
|
|
180 |
"model.layers.28.attn_norm.weight": "model-00001-of-00002.safetensors",
|
181 |
"model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
182 |
"model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
183 |
"model.layers.28.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
184 |
"model.layers.29.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
185 |
"model.layers.29.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -188,6 +210,7 @@
|
|
188 |
"model.layers.29.attn_norm.weight": "model-00001-of-00002.safetensors",
|
189 |
"model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
190 |
"model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
191 |
"model.layers.29.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
192 |
"model.layers.3.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
193 |
"model.layers.3.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -196,6 +219,7 @@
|
|
196 |
"model.layers.3.attn_norm.weight": "model-00001-of-00002.safetensors",
|
197 |
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
198 |
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
199 |
"model.layers.3.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
200 |
"model.layers.30.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
201 |
"model.layers.30.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -204,6 +228,7 @@
|
|
204 |
"model.layers.30.attn_norm.weight": "model-00001-of-00002.safetensors",
|
205 |
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
206 |
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
207 |
"model.layers.30.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
208 |
"model.layers.31.attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
209 |
"model.layers.31.attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
@@ -212,6 +237,7 @@
|
|
212 |
"model.layers.31.attn_norm.weight": "model-00002-of-00002.safetensors",
|
213 |
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
214 |
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
215 |
"model.layers.31.mlp_norm.weight": "model-00002-of-00002.safetensors",
|
216 |
"model.layers.4.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
217 |
"model.layers.4.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -220,6 +246,7 @@
|
|
220 |
"model.layers.4.attn_norm.weight": "model-00001-of-00002.safetensors",
|
221 |
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
222 |
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
223 |
"model.layers.4.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
224 |
"model.layers.5.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
225 |
"model.layers.5.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -228,6 +255,7 @@
|
|
228 |
"model.layers.5.attn_norm.weight": "model-00001-of-00002.safetensors",
|
229 |
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
230 |
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
231 |
"model.layers.5.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
232 |
"model.layers.6.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
233 |
"model.layers.6.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -236,6 +264,7 @@
|
|
236 |
"model.layers.6.attn_norm.weight": "model-00001-of-00002.safetensors",
|
237 |
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
238 |
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
239 |
"model.layers.6.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
240 |
"model.layers.7.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
241 |
"model.layers.7.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -244,6 +273,7 @@
|
|
244 |
"model.layers.7.attn_norm.weight": "model-00001-of-00002.safetensors",
|
245 |
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
246 |
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
247 |
"model.layers.7.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
248 |
"model.layers.8.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
249 |
"model.layers.8.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -252,6 +282,7 @@
|
|
252 |
"model.layers.8.attn_norm.weight": "model-00001-of-00002.safetensors",
|
253 |
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
254 |
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
255 |
"model.layers.8.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
256 |
"model.layers.9.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
257 |
"model.layers.9.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
@@ -260,6 +291,7 @@
|
|
260 |
"model.layers.9.attn_norm.weight": "model-00001-of-00002.safetensors",
|
261 |
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
262 |
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
263 |
"model.layers.9.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
264 |
"model.norm.weight": "model-00002-of-00002.safetensors"
|
265 |
}
|
|
|
12 |
"model.layers.0.attn_norm.weight": "model-00001-of-00002.safetensors",
|
13 |
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
14 |
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
15 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
16 |
"model.layers.0.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
17 |
"model.layers.1.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
18 |
"model.layers.1.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
21 |
"model.layers.1.attn_norm.weight": "model-00001-of-00002.safetensors",
|
22 |
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
23 |
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
24 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
25 |
"model.layers.1.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
26 |
"model.layers.10.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
27 |
"model.layers.10.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
30 |
"model.layers.10.attn_norm.weight": "model-00001-of-00002.safetensors",
|
31 |
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
32 |
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
33 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
34 |
"model.layers.10.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
35 |
"model.layers.11.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
36 |
"model.layers.11.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
39 |
"model.layers.11.attn_norm.weight": "model-00001-of-00002.safetensors",
|
40 |
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
41 |
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
42 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
43 |
"model.layers.11.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
44 |
"model.layers.12.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
45 |
"model.layers.12.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
48 |
"model.layers.12.attn_norm.weight": "model-00001-of-00002.safetensors",
|
49 |
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
50 |
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
51 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
52 |
"model.layers.12.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
53 |
"model.layers.13.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
54 |
"model.layers.13.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
57 |
"model.layers.13.attn_norm.weight": "model-00001-of-00002.safetensors",
|
58 |
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
59 |
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
60 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
61 |
"model.layers.13.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
62 |
"model.layers.14.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
63 |
"model.layers.14.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
66 |
"model.layers.14.attn_norm.weight": "model-00001-of-00002.safetensors",
|
67 |
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
68 |
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
69 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
70 |
"model.layers.14.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
71 |
"model.layers.15.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
72 |
"model.layers.15.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
75 |
"model.layers.15.attn_norm.weight": "model-00001-of-00002.safetensors",
|
76 |
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
77 |
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
78 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
79 |
"model.layers.15.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
80 |
"model.layers.16.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
81 |
"model.layers.16.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
84 |
"model.layers.16.attn_norm.weight": "model-00001-of-00002.safetensors",
|
85 |
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
86 |
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
87 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
88 |
"model.layers.16.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
89 |
"model.layers.17.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
90 |
"model.layers.17.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
93 |
"model.layers.17.attn_norm.weight": "model-00001-of-00002.safetensors",
|
94 |
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
95 |
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
96 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
97 |
"model.layers.17.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
98 |
"model.layers.18.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
99 |
"model.layers.18.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
102 |
"model.layers.18.attn_norm.weight": "model-00001-of-00002.safetensors",
|
103 |
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
104 |
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
105 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
106 |
"model.layers.18.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
107 |
"model.layers.19.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
108 |
"model.layers.19.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
111 |
"model.layers.19.attn_norm.weight": "model-00001-of-00002.safetensors",
|
112 |
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
113 |
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
114 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
115 |
"model.layers.19.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
116 |
"model.layers.2.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
117 |
"model.layers.2.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
120 |
"model.layers.2.attn_norm.weight": "model-00001-of-00002.safetensors",
|
121 |
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
122 |
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
123 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
124 |
"model.layers.2.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
125 |
"model.layers.20.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
126 |
"model.layers.20.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
129 |
"model.layers.20.attn_norm.weight": "model-00001-of-00002.safetensors",
|
130 |
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
131 |
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
132 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
133 |
"model.layers.20.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
134 |
"model.layers.21.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
135 |
"model.layers.21.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
138 |
"model.layers.21.attn_norm.weight": "model-00001-of-00002.safetensors",
|
139 |
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
140 |
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
141 |
+
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
142 |
"model.layers.21.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
143 |
"model.layers.22.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
144 |
"model.layers.22.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
147 |
"model.layers.22.attn_norm.weight": "model-00001-of-00002.safetensors",
|
148 |
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
149 |
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
150 |
+
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
151 |
"model.layers.22.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
152 |
"model.layers.23.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
153 |
"model.layers.23.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
156 |
"model.layers.23.attn_norm.weight": "model-00001-of-00002.safetensors",
|
157 |
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
158 |
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
159 |
+
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
160 |
"model.layers.23.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
161 |
"model.layers.24.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
162 |
"model.layers.24.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
165 |
"model.layers.24.attn_norm.weight": "model-00001-of-00002.safetensors",
|
166 |
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
167 |
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
168 |
+
"model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
169 |
"model.layers.24.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
170 |
"model.layers.25.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
171 |
"model.layers.25.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
174 |
"model.layers.25.attn_norm.weight": "model-00001-of-00002.safetensors",
|
175 |
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
176 |
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
177 |
+
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
178 |
"model.layers.25.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
179 |
"model.layers.26.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
180 |
"model.layers.26.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
183 |
"model.layers.26.attn_norm.weight": "model-00001-of-00002.safetensors",
|
184 |
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
185 |
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
186 |
+
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
187 |
"model.layers.26.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
188 |
"model.layers.27.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
189 |
"model.layers.27.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
192 |
"model.layers.27.attn_norm.weight": "model-00001-of-00002.safetensors",
|
193 |
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
194 |
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
195 |
+
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
196 |
"model.layers.27.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
197 |
"model.layers.28.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
198 |
"model.layers.28.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
201 |
"model.layers.28.attn_norm.weight": "model-00001-of-00002.safetensors",
|
202 |
"model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
203 |
"model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
204 |
+
"model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
205 |
"model.layers.28.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
206 |
"model.layers.29.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
207 |
"model.layers.29.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
210 |
"model.layers.29.attn_norm.weight": "model-00001-of-00002.safetensors",
|
211 |
"model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
212 |
"model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
213 |
+
"model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
214 |
"model.layers.29.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
215 |
"model.layers.3.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
216 |
"model.layers.3.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
219 |
"model.layers.3.attn_norm.weight": "model-00001-of-00002.safetensors",
|
220 |
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
221 |
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
222 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
223 |
"model.layers.3.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
224 |
"model.layers.30.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
225 |
"model.layers.30.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
228 |
"model.layers.30.attn_norm.weight": "model-00001-of-00002.safetensors",
|
229 |
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
230 |
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
231 |
+
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
232 |
"model.layers.30.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
233 |
"model.layers.31.attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
234 |
"model.layers.31.attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
237 |
"model.layers.31.attn_norm.weight": "model-00002-of-00002.safetensors",
|
238 |
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
239 |
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
240 |
+
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
241 |
"model.layers.31.mlp_norm.weight": "model-00002-of-00002.safetensors",
|
242 |
"model.layers.4.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
243 |
"model.layers.4.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
246 |
"model.layers.4.attn_norm.weight": "model-00001-of-00002.safetensors",
|
247 |
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
248 |
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
249 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
250 |
"model.layers.4.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
251 |
"model.layers.5.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
252 |
"model.layers.5.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
255 |
"model.layers.5.attn_norm.weight": "model-00001-of-00002.safetensors",
|
256 |
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
257 |
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
258 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
259 |
"model.layers.5.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
260 |
"model.layers.6.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
261 |
"model.layers.6.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
264 |
"model.layers.6.attn_norm.weight": "model-00001-of-00002.safetensors",
|
265 |
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
266 |
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
267 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
268 |
"model.layers.6.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
269 |
"model.layers.7.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
270 |
"model.layers.7.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
273 |
"model.layers.7.attn_norm.weight": "model-00001-of-00002.safetensors",
|
274 |
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
275 |
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
276 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
277 |
"model.layers.7.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
278 |
"model.layers.8.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
279 |
"model.layers.8.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
282 |
"model.layers.8.attn_norm.weight": "model-00001-of-00002.safetensors",
|
283 |
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
284 |
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
285 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
286 |
"model.layers.8.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
287 |
"model.layers.9.attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
288 |
"model.layers.9.attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
291 |
"model.layers.9.attn_norm.weight": "model-00001-of-00002.safetensors",
|
292 |
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
293 |
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
294 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
295 |
"model.layers.9.mlp_norm.weight": "model-00001-of-00002.safetensors",
|
296 |
"model.norm.weight": "model-00002-of-00002.safetensors"
|
297 |
}
|