DrNicefellow
commited on
Commit
•
a32fcf6
1
Parent(s):
c412fb7
Upload 10 files
Browse files- config.json +27 -0
- generation_config.json +6 -0
- optimizer.pt +3 -0
- pytorch_model-00001-of-00002.bin +3 -0
- pytorch_model-00002-of-00002.bin +3 -0
- pytorch_model.bin.index.json +233 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"OlmoForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_bias": false,
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"clip_qkv": null,
|
8 |
+
"eos_token_id": 50279,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 2048,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 8192,
|
13 |
+
"max_position_embeddings": 2048,
|
14 |
+
"model_type": "olmo",
|
15 |
+
"num_attention_heads": 16,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"num_key_value_heads": 4,
|
18 |
+
"pad_token_id": 1,
|
19 |
+
"pretraining_tp": 1,
|
20 |
+
"rope_scaling": null,
|
21 |
+
"rope_theta": 10000.0,
|
22 |
+
"tie_word_embeddings": true,
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.41.0",
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 50304
|
27 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"eos_token_id": 50279,
|
4 |
+
"pad_token_id": 1,
|
5 |
+
"transformers_version": "4.41.0"
|
6 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8172a8c484f11d6742573614c7b07c798762ef786cdb038a5d0b1ff1a878ccb6
|
3 |
+
size 16393633958
|
pytorch_model-00001-of-00002.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c72e99c0faaf72fce7bec25c8fd4a68e0ba866167a39940dcb2ce62ea9b82f0
|
3 |
+
size 4967152029
|
pytorch_model-00002-of-00002.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb58b3683d4f9da4fb41294d1bb8b18046a04d62f47bc58667cdae02e76ac0af
|
3 |
+
size 3229646818
|
pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,233 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 8196718592
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "pytorch_model-00001-of-00002.bin",
|
7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
|
8 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
9 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
10 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
11 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
12 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
13 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
14 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
15 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
16 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
17 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
18 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
19 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
20 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
21 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
22 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
23 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
24 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
25 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
26 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
27 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
28 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
29 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
30 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
31 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
32 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
33 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
34 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
35 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
36 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
37 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
38 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
39 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
40 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
41 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
42 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
43 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
44 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
45 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
46 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
47 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
48 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
49 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
50 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
51 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
52 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
53 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
54 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
55 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
56 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
57 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
58 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
59 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
60 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
61 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
62 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
63 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
64 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
65 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
66 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
67 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
68 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
69 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
70 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
71 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
72 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
73 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
74 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
75 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
76 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
77 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
78 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
79 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
80 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
81 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
82 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
83 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
84 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
85 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
86 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
87 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
88 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
89 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
90 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
91 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
92 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
93 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
94 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
95 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
96 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
97 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
98 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
99 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
100 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
101 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
102 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
103 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
104 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
105 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
106 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
107 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
108 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
109 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
110 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
111 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
112 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
113 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
114 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
115 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
116 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
117 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
118 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
119 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
120 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
121 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
122 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
123 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
124 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
125 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
126 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
127 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
128 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
129 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
130 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
131 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
132 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
133 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
134 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
135 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
136 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
137 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
138 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
139 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
140 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
141 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
142 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
143 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
144 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
145 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
146 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
147 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
148 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
149 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
150 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
151 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
152 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
153 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
154 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
155 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
156 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
157 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
158 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
159 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
160 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
161 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
162 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
163 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
164 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
165 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
166 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
167 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
168 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
169 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
170 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
171 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
172 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
173 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
174 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
175 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
176 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
177 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
178 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
179 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
180 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
181 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
182 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
183 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
184 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
185 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
186 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
187 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
188 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
189 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
190 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
191 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
192 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
193 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
194 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
195 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
196 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
197 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
198 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
199 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
200 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
201 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
202 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
203 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
204 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
205 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
206 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
207 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
208 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
209 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
210 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
211 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
212 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
213 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
214 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
215 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
216 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
217 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
218 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
219 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
220 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
221 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
222 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
223 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
224 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
225 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
226 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
227 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
228 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
229 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
230 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
231 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin"
|
232 |
+
}
|
233 |
+
}
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8dbf964f7f4f57544afbabc2e6664ff81ab52d338c1503de17fc0fb8251b362b
|
3 |
+
size 1064
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1fd3297bcb315b7c7d6b9f742905192ae81f2b10e332dd0ec9735cdbf68b8c1
|
3 |
+
size 5112
|