Add files using upload-large-folder tool
Browse files
tllm-checkpoint/config.json
CHANGED
@@ -66,105 +66,105 @@
|
|
66 |
"has_zero_point": false,
|
67 |
"pre_quant_scale": false,
|
68 |
"exclude_modules": [
|
69 |
-
"transformer.layers.
|
70 |
-
"transformer.layers.22.input_layernorm",
|
71 |
-
"transformer.layers.11.mlp.shared_expert_gate",
|
72 |
-
"transformer.layers.22.post_layernorm",
|
73 |
"transformer.layers.20.mlp.router",
|
74 |
-
"
|
|
|
|
|
|
|
75 |
"transformer.layers.14.mlp.router",
|
76 |
-
"transformer.layers.16.mlp.shared_expert_gate",
|
77 |
-
"transformer.layers.7.post_layernorm",
|
78 |
-
"transformer.layers.0.mlp.shared_expert_gate",
|
79 |
-
"transformer.layers.1.post_layernorm",
|
80 |
-
"transformer.layers.4.mlp.shared_expert_gate",
|
81 |
-
"transformer.layers.8.post_layernorm",
|
82 |
-
"transformer.layers.5.mlp.router",
|
83 |
-
"transformer.layers.8.mlp.router",
|
84 |
-
"transformer.layers.21.post_layernorm",
|
85 |
"transformer.layers.23.post_layernorm",
|
86 |
-
"transformer.layers.
|
87 |
-
"transformer.layers.
|
88 |
-
"transformer.layers.6.post_layernorm",
|
89 |
-
"transformer.layers.23.mlp.router",
|
90 |
-
"transformer.layers.8.input_layernorm",
|
91 |
-
"transformer.layers.17.mlp.shared_expert_gate",
|
92 |
-
"transformer.layers.8.mlp.shared_expert_gate",
|
93 |
"transformer.layers.9.mlp.shared_expert_gate",
|
94 |
-
"transformer.layers.
|
95 |
-
"transformer.layers.6.mlp.router",
|
96 |
-
"transformer.layers.10.post_layernorm",
|
97 |
-
"transformer.layers.0.post_layernorm",
|
98 |
-
"transformer.layers.14.input_layernorm",
|
99 |
-
"transformer.layers.13.mlp.router",
|
100 |
-
"transformer.layers.15.mlp.shared_expert_gate",
|
101 |
-
"transformer.layers.0.mlp.router",
|
102 |
-
"transformer.layers.5.post_layernorm",
|
103 |
-
"transformer.layers.9.post_layernorm",
|
104 |
-
"transformer.layers.17.post_layernorm",
|
105 |
-
"transformer.layers.2.input_layernorm",
|
106 |
"transformer.layers.11.mlp.router",
|
107 |
-
"transformer.layers.
|
108 |
-
"transformer.
|
109 |
-
"transformer.layers.22.mlp.router",
|
110 |
-
"transformer.layers.5.mlp.shared_expert_gate",
|
111 |
-
"transformer.layers.6.mlp.shared_expert_gate",
|
112 |
-
"transformer.layers.14.mlp.shared_expert_gate",
|
113 |
-
"transformer.layers.22.mlp.shared_expert_gate",
|
114 |
-
"transformer.layers.18.mlp.shared_expert_gate",
|
115 |
-
"transformer.layers.5.input_layernorm",
|
116 |
-
"transformer.layers.20.mlp.shared_expert_gate",
|
117 |
-
"transformer.layers.9.mlp.router",
|
118 |
"transformer.layers.3.mlp.shared_expert_gate",
|
119 |
-
"transformer.layers.10.input_layernorm",
|
120 |
"transformer.layers.14.post_layernorm",
|
121 |
-
"transformer.layers.
|
122 |
-
"transformer.layers.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
123 |
"transformer.layers.2.mlp.router",
|
|
|
|
|
|
|
|
|
124 |
"transformer.layers.23.input_layernorm",
|
125 |
-
"transformer.layers.
|
126 |
-
"transformer.layers.4.mlp.router",
|
127 |
-
"transformer.layers.12.mlp.shared_expert_gate",
|
128 |
-
"transformer.layers.1.mlp.shared_expert_gate",
|
129 |
"transformer.layers.20.input_layernorm",
|
130 |
-
"transformer.layers.
|
131 |
-
"transformer.layers.
|
132 |
-
"transformer.layers.
|
|
|
|
|
133 |
"transformer.layers.17.mlp.router",
|
134 |
-
"transformer.layers.
|
135 |
-
"transformer.layers.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
136 |
"transformer.layers.16.post_layernorm",
|
137 |
-
"transformer.layers.19.mlp.shared_expert_gate",
|
138 |
-
"transformer.layers.3.mlp.router",
|
139 |
-
"transformer.layers.4.input_layernorm",
|
140 |
"transformer.layers.19.input_layernorm",
|
141 |
-
"transformer.layers.
|
142 |
-
"transformer.layers.
|
143 |
-
"transformer.
|
144 |
-
"transformer.layers.
|
145 |
-
"transformer.layers.
|
146 |
-
"transformer.layers.
|
147 |
-
"transformer.layers.
|
|
|
|
|
|
|
|
|
148 |
"transformer.layers.11.input_layernorm",
|
149 |
-
"transformer.layers.
|
150 |
-
"transformer.layers.
|
151 |
-
"
|
152 |
-
"transformer.layers.
|
153 |
-
"transformer.layers.
|
154 |
-
"transformer.layers.18.post_layernorm",
|
155 |
-
"transformer.layers.21.mlp.shared_expert_gate",
|
156 |
-
"transformer.layers.6.input_layernorm",
|
157 |
-
"transformer.layers.7.mlp.shared_expert_gate",
|
158 |
"transformer.layers.11.post_layernorm",
|
|
|
|
|
159 |
"transformer.layers.1.input_layernorm",
|
160 |
-
"transformer.
|
161 |
-
"transformer.layers.13.post_layernorm",
|
162 |
-
"transformer.layers.12.input_layernorm",
|
163 |
-
"transformer.layers.13.mlp.shared_expert_gate",
|
164 |
"transformer.layers.12.mlp.router",
|
|
|
165 |
"transformer.layers.12.post_layernorm",
|
166 |
-
"transformer.
|
167 |
-
"transformer.layers.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
168 |
]
|
169 |
},
|
170 |
"qk_layernorm": false,
|
|
|
66 |
"has_zero_point": false,
|
67 |
"pre_quant_scale": false,
|
68 |
"exclude_modules": [
|
69 |
+
"transformer.layers.7.mlp.shared_expert_gate",
|
|
|
|
|
|
|
70 |
"transformer.layers.20.mlp.router",
|
71 |
+
"lm_head",
|
72 |
+
"transformer.layers.18.post_layernorm",
|
73 |
+
"transformer.layers.17.mlp.shared_expert_gate",
|
74 |
+
"transformer.layers.6.post_layernorm",
|
75 |
"transformer.layers.14.mlp.router",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
76 |
"transformer.layers.23.post_layernorm",
|
77 |
+
"transformer.layers.22.mlp.router",
|
78 |
+
"transformer.layers.7.input_layernorm",
|
|
|
|
|
|
|
|
|
|
|
79 |
"transformer.layers.9.mlp.shared_expert_gate",
|
80 |
+
"transformer.layers.8.mlp.router",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
81 |
"transformer.layers.11.mlp.router",
|
82 |
+
"transformer.layers.19.mlp.router",
|
83 |
+
"transformer.layers.13.mlp.router",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
84 |
"transformer.layers.3.mlp.shared_expert_gate",
|
|
|
85 |
"transformer.layers.14.post_layernorm",
|
86 |
+
"transformer.layers.10.mlp.shared_expert_gate",
|
87 |
+
"transformer.layers.6.input_layernorm",
|
88 |
+
"transformer.layers.1.mlp.router",
|
89 |
+
"transformer.layers.21.mlp.router",
|
90 |
+
"transformer.layers.20.mlp.shared_expert_gate",
|
91 |
+
"transformer.layers.13.input_layernorm",
|
92 |
+
"transformer.layers.1.mlp.shared_expert_gate",
|
93 |
+
"transformer.layers.9.input_layernorm",
|
94 |
+
"transformer.layers.18.mlp.router",
|
95 |
+
"transformer.layers.18.mlp.shared_expert_gate",
|
96 |
+
"transformer.layers.21.input_layernorm",
|
97 |
+
"transformer.layers.15.post_layernorm",
|
98 |
+
"transformer.layers.22.mlp.shared_expert_gate",
|
99 |
+
"transformer.layers.4.post_layernorm",
|
100 |
+
"transformer.layers.15.input_layernorm",
|
101 |
+
"transformer.layers.13.post_layernorm",
|
102 |
+
"transformer.layers.4.mlp.router",
|
103 |
+
"transformer.layers.23.mlp.router",
|
104 |
+
"transformer.layers.3.mlp.router",
|
105 |
"transformer.layers.2.mlp.router",
|
106 |
+
"transformer.layers.21.post_layernorm",
|
107 |
+
"transformer.layers.9.post_layernorm",
|
108 |
+
"transformer.layers.5.mlp.shared_expert_gate",
|
109 |
+
"transformer.layers.1.post_layernorm",
|
110 |
"transformer.layers.23.input_layernorm",
|
111 |
+
"transformer.layers.7.mlp.router",
|
|
|
|
|
|
|
112 |
"transformer.layers.20.input_layernorm",
|
113 |
+
"transformer.layers.13.mlp.shared_expert_gate",
|
114 |
+
"transformer.layers.15.mlp.router",
|
115 |
+
"transformer.layers.7.post_layernorm",
|
116 |
+
"transformer.layers.22.input_layernorm",
|
117 |
+
"transformer.layers.2.mlp.shared_expert_gate",
|
118 |
"transformer.layers.17.mlp.router",
|
119 |
+
"transformer.layers.19.post_layernorm",
|
120 |
+
"transformer.layers.4.mlp.shared_expert_gate",
|
121 |
+
"transformer.layers.6.mlp.shared_expert_gate",
|
122 |
+
"transformer.layers.9.mlp.router",
|
123 |
+
"transformer.layers.16.input_layernorm",
|
124 |
+
"transformer.layers.0.input_layernorm",
|
125 |
+
"transformer.layers.11.mlp.shared_expert_gate",
|
126 |
+
"transformer.layers.12.mlp.shared_expert_gate",
|
127 |
+
"transformer.layers.16.mlp.shared_expert_gate",
|
128 |
"transformer.layers.16.post_layernorm",
|
|
|
|
|
|
|
129 |
"transformer.layers.19.input_layernorm",
|
130 |
+
"transformer.layers.14.mlp.shared_expert_gate",
|
131 |
+
"transformer.layers.10.post_layernorm",
|
132 |
+
"transformer.vocab_embedding",
|
133 |
+
"transformer.layers.8.post_layernorm",
|
134 |
+
"transformer.layers.10.input_layernorm",
|
135 |
+
"transformer.layers.2.input_layernorm",
|
136 |
+
"transformer.layers.14.input_layernorm",
|
137 |
+
"transformer.layers.5.input_layernorm",
|
138 |
+
"transformer.layers.18.input_layernorm",
|
139 |
+
"transformer.layers.3.post_layernorm",
|
140 |
+
"transformer.layers.5.post_layernorm",
|
141 |
"transformer.layers.11.input_layernorm",
|
142 |
+
"transformer.layers.12.input_layernorm",
|
143 |
+
"transformer.layers.23.mlp.shared_expert_gate",
|
144 |
+
"transformer.layers.16.mlp.router",
|
145 |
+
"transformer.layers.15.mlp.shared_expert_gate",
|
146 |
+
"transformer.layers.0.mlp.shared_expert_gate",
|
|
|
|
|
|
|
|
|
147 |
"transformer.layers.11.post_layernorm",
|
148 |
+
"transformer.layers.22.post_layernorm",
|
149 |
+
"transformer.layers.10.mlp.router",
|
150 |
"transformer.layers.1.input_layernorm",
|
151 |
+
"transformer.layers.17.post_layernorm",
|
|
|
|
|
|
|
152 |
"transformer.layers.12.mlp.router",
|
153 |
+
"transformer.layers.19.mlp.shared_expert_gate",
|
154 |
"transformer.layers.12.post_layernorm",
|
155 |
+
"transformer.ln_f",
|
156 |
+
"transformer.layers.3.input_layernorm",
|
157 |
+
"transformer.layers.17.input_layernorm",
|
158 |
+
"transformer.layers.8.mlp.shared_expert_gate",
|
159 |
+
"transformer.layers.0.post_layernorm",
|
160 |
+
"transformer.layers.0.mlp.router",
|
161 |
+
"transformer.layers.2.post_layernorm",
|
162 |
+
"transformer.layers.8.input_layernorm",
|
163 |
+
"transformer.layers.4.input_layernorm",
|
164 |
+
"transformer.layers.21.mlp.shared_expert_gate",
|
165 |
+
"transformer.layers.6.mlp.router",
|
166 |
+
"transformer.layers.5.mlp.router",
|
167 |
+
"transformer.layers.20.post_layernorm"
|
168 |
]
|
169 |
},
|
170 |
"qk_layernorm": false,
|
tllm-checkpoint/rank0.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 sha256:4f1209747dafd1fe1b4db5cf54b6e747c5234252e38bf30e1adf5503ed96ebed
|
3 |
+
size 8725465656
|
tllm-checkpoint/rank1.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 sha256:680fbac67d297f021d2f4c1f5320b86d167e973aef2947228d4228f1da981aed
|
3 |
+
size 8725465656
|