Yishi Xu
commited on
Commit
•
898d006
1
Parent(s):
0ec72f2
add CerebrasGPT-111_muP
Browse files
CerebrasGPT-111_muP/config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"attn_pdrop": 0.0,
|
3 |
+
"scale_attn_weights": true,
|
4 |
+
"resid_pdrop": 0.0,
|
5 |
+
"n_inner": 3072,
|
6 |
+
"n_embd": 768,
|
7 |
+
"layer_norm_epsilon": 1e-05,
|
8 |
+
"n_positions": 2048,
|
9 |
+
"mup_embeddings_scale": 10,
|
10 |
+
"activation_function": "gelu",
|
11 |
+
"n_head": 12,
|
12 |
+
"n_layer": 10,
|
13 |
+
"position_embedding_type": "learned",
|
14 |
+
"mup_scale_qk_dot_by_d": true,
|
15 |
+
"tie_word_embeddings": true,
|
16 |
+
"vocab_size": 50257,
|
17 |
+
"alibi_scaling": null,
|
18 |
+
"embd_pdrop": 0.0,
|
19 |
+
"model_type": "btlm",
|
20 |
+
"use_cache": true,
|
21 |
+
"auto_map": {
|
22 |
+
"AutoConfig": "cerebras/btlm-3b-8k-base--configuration_btlm.BTLMConfig",
|
23 |
+
"AutoModel": "cerebras/btlm-3b-8k-base--modeling_btlm.BTLMModel",
|
24 |
+
"AutoModelForCausalLM": "cerebras/btlm-3b-8k-base--modeling_btlm.BTLMLMHeadModel"
|
25 |
+
}
|
26 |
+
}
|
CerebrasGPT-111_muP/pytorch_model-00001-of-00001.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2358a4a5122966c3e777dcf24b3170ad4aa0eebae041382da41c8aa5635dcca5
|
3 |
+
size 598632525
|
CerebrasGPT-111_muP/pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 598591488
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"transformer.wte.weight": "pytorch_model-00001-of-00001.bin",
|
7 |
+
"transformer.wpe.weight": "pytorch_model-00001-of-00001.bin",
|
8 |
+
"transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00001.bin",
|
9 |
+
"transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00001.bin",
|
10 |
+
"transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00001.bin",
|
11 |
+
"transformer.h.0.attn.c_proj.bias": "pytorch_model-00001-of-00001.bin",
|
12 |
+
"transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00001.bin",
|
13 |
+
"transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00001.bin",
|
14 |
+
"transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00001.bin",
|
15 |
+
"transformer.h.0.ln_2.bias": "pytorch_model-00001-of-00001.bin",
|
16 |
+
"transformer.h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00001.bin",
|
17 |
+
"transformer.h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00001.bin",
|
18 |
+
"transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00001.bin",
|
19 |
+
"transformer.h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00001.bin",
|
20 |
+
"transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00001.bin",
|
21 |
+
"transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00001.bin",
|
22 |
+
"transformer.h.1.attn.c_proj.weight": "pytorch_model-00001-of-00001.bin",
|
23 |
+
"transformer.h.1.attn.c_proj.bias": "pytorch_model-00001-of-00001.bin",
|
24 |
+
"transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00001.bin",
|
25 |
+
"transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00001.bin",
|
26 |
+
"transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00001.bin",
|
27 |
+
"transformer.h.1.ln_2.bias": "pytorch_model-00001-of-00001.bin",
|
28 |
+
"transformer.h.1.mlp.c_fc.weight": "pytorch_model-00001-of-00001.bin",
|
29 |
+
"transformer.h.1.mlp.c_fc.bias": "pytorch_model-00001-of-00001.bin",
|
30 |
+
"transformer.h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00001.bin",
|
31 |
+
"transformer.h.1.mlp.c_proj.bias": "pytorch_model-00001-of-00001.bin",
|
32 |
+
"transformer.h.2.attn.c_attn.weight": "pytorch_model-00001-of-00001.bin",
|
33 |
+
"transformer.h.2.attn.c_attn.bias": "pytorch_model-00001-of-00001.bin",
|
34 |
+
"transformer.h.2.attn.c_proj.weight": "pytorch_model-00001-of-00001.bin",
|
35 |
+
"transformer.h.2.attn.c_proj.bias": "pytorch_model-00001-of-00001.bin",
|
36 |
+
"transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00001.bin",
|
37 |
+
"transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00001.bin",
|
38 |
+
"transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00001.bin",
|
39 |
+
"transformer.h.2.ln_2.bias": "pytorch_model-00001-of-00001.bin",
|
40 |
+
"transformer.h.2.mlp.c_fc.weight": "pytorch_model-00001-of-00001.bin",
|
41 |
+
"transformer.h.2.mlp.c_fc.bias": "pytorch_model-00001-of-00001.bin",
|
42 |
+
"transformer.h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00001.bin",
|
43 |
+
"transformer.h.2.mlp.c_proj.bias": "pytorch_model-00001-of-00001.bin",
|
44 |
+
"transformer.h.3.attn.c_attn.weight": "pytorch_model-00001-of-00001.bin",
|
45 |
+
"transformer.h.3.attn.c_attn.bias": "pytorch_model-00001-of-00001.bin",
|
46 |
+
"transformer.h.3.attn.c_proj.weight": "pytorch_model-00001-of-00001.bin",
|
47 |
+
"transformer.h.3.attn.c_proj.bias": "pytorch_model-00001-of-00001.bin",
|
48 |
+
"transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00001.bin",
|
49 |
+
"transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00001.bin",
|
50 |
+
"transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00001.bin",
|
51 |
+
"transformer.h.3.ln_2.bias": "pytorch_model-00001-of-00001.bin",
|
52 |
+
"transformer.h.3.mlp.c_fc.weight": "pytorch_model-00001-of-00001.bin",
|
53 |
+
"transformer.h.3.mlp.c_fc.bias": "pytorch_model-00001-of-00001.bin",
|
54 |
+
"transformer.h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00001.bin",
|
55 |
+
"transformer.h.3.mlp.c_proj.bias": "pytorch_model-00001-of-00001.bin",
|
56 |
+
"transformer.h.4.attn.c_attn.weight": "pytorch_model-00001-of-00001.bin",
|
57 |
+
"transformer.h.4.attn.c_attn.bias": "pytorch_model-00001-of-00001.bin",
|
58 |
+
"transformer.h.4.attn.c_proj.weight": "pytorch_model-00001-of-00001.bin",
|
59 |
+
"transformer.h.4.attn.c_proj.bias": "pytorch_model-00001-of-00001.bin",
|
60 |
+
"transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00001.bin",
|
61 |
+
"transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00001.bin",
|
62 |
+
"transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00001.bin",
|
63 |
+
"transformer.h.4.ln_2.bias": "pytorch_model-00001-of-00001.bin",
|
64 |
+
"transformer.h.4.mlp.c_fc.weight": "pytorch_model-00001-of-00001.bin",
|
65 |
+
"transformer.h.4.mlp.c_fc.bias": "pytorch_model-00001-of-00001.bin",
|
66 |
+
"transformer.h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00001.bin",
|
67 |
+
"transformer.h.4.mlp.c_proj.bias": "pytorch_model-00001-of-00001.bin",
|
68 |
+
"transformer.h.5.attn.c_attn.weight": "pytorch_model-00001-of-00001.bin",
|
69 |
+
"transformer.h.5.attn.c_attn.bias": "pytorch_model-00001-of-00001.bin",
|
70 |
+
"transformer.h.5.attn.c_proj.weight": "pytorch_model-00001-of-00001.bin",
|
71 |
+
"transformer.h.5.attn.c_proj.bias": "pytorch_model-00001-of-00001.bin",
|
72 |
+
"transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00001.bin",
|
73 |
+
"transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00001.bin",
|
74 |
+
"transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00001.bin",
|
75 |
+
"transformer.h.5.ln_2.bias": "pytorch_model-00001-of-00001.bin",
|
76 |
+
"transformer.h.5.mlp.c_fc.weight": "pytorch_model-00001-of-00001.bin",
|
77 |
+
"transformer.h.5.mlp.c_fc.bias": "pytorch_model-00001-of-00001.bin",
|
78 |
+
"transformer.h.5.mlp.c_proj.weight": "pytorch_model-00001-of-00001.bin",
|
79 |
+
"transformer.h.5.mlp.c_proj.bias": "pytorch_model-00001-of-00001.bin",
|
80 |
+
"transformer.h.6.attn.c_attn.weight": "pytorch_model-00001-of-00001.bin",
|
81 |
+
"transformer.h.6.attn.c_attn.bias": "pytorch_model-00001-of-00001.bin",
|
82 |
+
"transformer.h.6.attn.c_proj.weight": "pytorch_model-00001-of-00001.bin",
|
83 |
+
"transformer.h.6.attn.c_proj.bias": "pytorch_model-00001-of-00001.bin",
|
84 |
+
"transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00001.bin",
|
85 |
+
"transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00001.bin",
|
86 |
+
"transformer.h.6.ln_2.weight": "pytorch_model-00001-of-00001.bin",
|
87 |
+
"transformer.h.6.ln_2.bias": "pytorch_model-00001-of-00001.bin",
|
88 |
+
"transformer.h.6.mlp.c_fc.weight": "pytorch_model-00001-of-00001.bin",
|
89 |
+
"transformer.h.6.mlp.c_fc.bias": "pytorch_model-00001-of-00001.bin",
|
90 |
+
"transformer.h.6.mlp.c_proj.weight": "pytorch_model-00001-of-00001.bin",
|
91 |
+
"transformer.h.6.mlp.c_proj.bias": "pytorch_model-00001-of-00001.bin",
|
92 |
+
"transformer.h.7.attn.c_attn.weight": "pytorch_model-00001-of-00001.bin",
|
93 |
+
"transformer.h.7.attn.c_attn.bias": "pytorch_model-00001-of-00001.bin",
|
94 |
+
"transformer.h.7.attn.c_proj.weight": "pytorch_model-00001-of-00001.bin",
|
95 |
+
"transformer.h.7.attn.c_proj.bias": "pytorch_model-00001-of-00001.bin",
|
96 |
+
"transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00001.bin",
|
97 |
+
"transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00001.bin",
|
98 |
+
"transformer.h.7.ln_2.weight": "pytorch_model-00001-of-00001.bin",
|
99 |
+
"transformer.h.7.ln_2.bias": "pytorch_model-00001-of-00001.bin",
|
100 |
+
"transformer.h.7.mlp.c_fc.weight": "pytorch_model-00001-of-00001.bin",
|
101 |
+
"transformer.h.7.mlp.c_fc.bias": "pytorch_model-00001-of-00001.bin",
|
102 |
+
"transformer.h.7.mlp.c_proj.weight": "pytorch_model-00001-of-00001.bin",
|
103 |
+
"transformer.h.7.mlp.c_proj.bias": "pytorch_model-00001-of-00001.bin",
|
104 |
+
"transformer.h.8.attn.c_attn.weight": "pytorch_model-00001-of-00001.bin",
|
105 |
+
"transformer.h.8.attn.c_attn.bias": "pytorch_model-00001-of-00001.bin",
|
106 |
+
"transformer.h.8.attn.c_proj.weight": "pytorch_model-00001-of-00001.bin",
|
107 |
+
"transformer.h.8.attn.c_proj.bias": "pytorch_model-00001-of-00001.bin",
|
108 |
+
"transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00001.bin",
|
109 |
+
"transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00001.bin",
|
110 |
+
"transformer.h.8.ln_2.weight": "pytorch_model-00001-of-00001.bin",
|
111 |
+
"transformer.h.8.ln_2.bias": "pytorch_model-00001-of-00001.bin",
|
112 |
+
"transformer.h.8.mlp.c_fc.weight": "pytorch_model-00001-of-00001.bin",
|
113 |
+
"transformer.h.8.mlp.c_fc.bias": "pytorch_model-00001-of-00001.bin",
|
114 |
+
"transformer.h.8.mlp.c_proj.weight": "pytorch_model-00001-of-00001.bin",
|
115 |
+
"transformer.h.8.mlp.c_proj.bias": "pytorch_model-00001-of-00001.bin",
|
116 |
+
"transformer.h.9.attn.c_attn.weight": "pytorch_model-00001-of-00001.bin",
|
117 |
+
"transformer.h.9.attn.c_attn.bias": "pytorch_model-00001-of-00001.bin",
|
118 |
+
"transformer.h.9.attn.c_proj.weight": "pytorch_model-00001-of-00001.bin",
|
119 |
+
"transformer.h.9.attn.c_proj.bias": "pytorch_model-00001-of-00001.bin",
|
120 |
+
"transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00001.bin",
|
121 |
+
"transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00001.bin",
|
122 |
+
"transformer.h.9.ln_2.weight": "pytorch_model-00001-of-00001.bin",
|
123 |
+
"transformer.h.9.ln_2.bias": "pytorch_model-00001-of-00001.bin",
|
124 |
+
"transformer.h.9.mlp.c_fc.weight": "pytorch_model-00001-of-00001.bin",
|
125 |
+
"transformer.h.9.mlp.c_fc.bias": "pytorch_model-00001-of-00001.bin",
|
126 |
+
"transformer.h.9.mlp.c_proj.weight": "pytorch_model-00001-of-00001.bin",
|
127 |
+
"transformer.h.9.mlp.c_proj.bias": "pytorch_model-00001-of-00001.bin",
|
128 |
+
"transformer.ln_f.weight": "pytorch_model-00001-of-00001.bin",
|
129 |
+
"transformer.ln_f.bias": "pytorch_model-00001-of-00001.bin",
|
130 |
+
"lm_head.weight": "pytorch_model-00001-of-00001.bin"
|
131 |
+
}
|
132 |
+
}
|