CreitinGameplays commited on
Commit
265e37a
1 Parent(s): 9dc4a34

Upload 17 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t\t": 50294,
3
+ "\t\t\t": 50293,
4
+ "\t\t\t\t": 50292,
5
+ "\t\t\t\t\t": 50291,
6
+ "\t\t\t\t\t\t": 50290,
7
+ "\t\t\t\t\t\t\t": 50289,
8
+ "\t\t\t\t\t\t\t\t": 50288,
9
+ "\t\t\t\t\t\t\t\t\t": 50287,
10
+ " ": 50286,
11
+ " ": 50285,
12
+ " ": 50284,
13
+ " ": 50283,
14
+ " ": 50282,
15
+ " ": 50281,
16
+ " ": 50280,
17
+ " ": 50279,
18
+ " ": 50278,
19
+ " ": 50277,
20
+ " ": 50276,
21
+ " ": 50275,
22
+ " ": 50274,
23
+ " ": 50273,
24
+ " ": 50272,
25
+ " ": 50271,
26
+ " ": 50270,
27
+ " ": 50269,
28
+ " ": 50268,
29
+ " ": 50267,
30
+ " ": 50266,
31
+ " ": 50265,
32
+ " ": 50264,
33
+ " ": 50263,
34
+ " ": 50262,
35
+ " ": 50261,
36
+ " ": 50260,
37
+ " ": 50259,
38
+ " ": 50258,
39
+ " ": 50257,
40
+ "[PAD]": 50295
41
+ }
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.23391734473466494,
4
+ "train_runtime": 1027.8255,
5
+ "train_samples": 10068,
6
+ "train_samples_per_second": 9.795,
7
+ "train_steps_per_second": 0.612
8
+ }
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/phi-2",
3
+ "architectures": [
4
+ "PhiForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
9
+ "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
10
+ },
11
+ "bos_token_id": 50256,
12
+ "embd_pdrop": 0.0,
13
+ "eos_token_id": 50256,
14
+ "hidden_act": "gelu_new",
15
+ "hidden_size": 2560,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 10240,
18
+ "layer_norm_eps": 1e-05,
19
+ "max_position_embeddings": 2048,
20
+ "model_type": "phi",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 32,
23
+ "num_key_value_heads": 32,
24
+ "partial_rotary_factor": 0.4,
25
+ "qk_layernorm": false,
26
+ "resid_pdrop": 0.1,
27
+ "rope_scaling": null,
28
+ "rope_theta": 10000.0,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.39.0.dev0",
32
+ "use_cache": true,
33
+ "vocab_size": 50296
34
+ }
generated_predictions_eval_greedy_5.txt ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ivolce in the sun sounds like a dream! I'm here to bring the party to our virtual conversations. Anything special you want to chat about or share today?
2
+ ingredients are authentic. It's a culinary delight! What's on your lunch menu?
3
+ fully! I'm grateful for your kindness. If there's anything specific you want to discuss or if you just want to chat, I'm here for you. Let's navigate through this together!
4
+ ooh, I'd love to join the party! Count me in for some fun and excitement. What's on your watchlist?
5
+ ooh, I'm not a rule follower! I'm more of a free spirit. How about you?
6
+ o No worries, it's just right for my hair! The water feels cool on my skin. What's your favorite shampoo?
7
+ fulfilling! I'm grateful for our boss's generosity. It's always a boost to my morale.
8
+ oohayaki! I'm excited to join the drama club. What's your dream?
9
+ ! I got it from a local store. It's a bit of a surprise, but I'm wearing it for good vibes!
10
+ ooh, that sounds like a dream! I'm more of a dreamer than a driver. What's your dream?
11
+ ingredients for a romantic dinner sound delightful! I'm not sure about the reason, but I'm curious to know. What made the romantic dinner special for you?
12
+ me too! I love the energy of rock. It's like a superpower. What's your favorite rock genre?
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.39.0.dev0"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1664e962900731c6c83625737a17266fa430af99b8b77ed9c2c86f9872c43f78
3
+ size 4999323416
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88e239d8605c711c7b0d0af64623f6bb6bb5f461ce1dcbc5bdaab9cbfd80571c
3
+ size 4982541984
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbd63d243827e29bda81fe0898da1bb63f6a9bb2926ba6fd9c653b16d9abd2b3
3
+ size 1118402176
model.safetensors.index.json ADDED
@@ -0,0 +1,460 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 11100217824
4
+ },
5
+ "weight_map": {
6
+ "lm_head.bias": "model-00003-of-00003.safetensors",
7
+ "lm_head.weight": "model-00003-of-00003.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
9
+ "model.final_layernorm.bias": "model-00003-of-00003.safetensors",
10
+ "model.final_layernorm.weight": "model-00003-of-00003.safetensors",
11
+ "model.layers.0.input_layernorm.bias": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.0.self_attn.dense.bias": "model-00001-of-00003.safetensors",
18
+ "model.layers.0.self_attn.dense.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
20
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
22
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
24
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
26
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
27
+ "model.layers.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
28
+ "model.layers.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
30
+ "model.layers.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
31
+ "model.layers.1.self_attn.dense.bias": "model-00001-of-00003.safetensors",
32
+ "model.layers.1.self_attn.dense.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
34
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
36
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
37
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
38
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
39
+ "model.layers.10.input_layernorm.bias": "model-00001-of-00003.safetensors",
40
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
41
+ "model.layers.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
42
+ "model.layers.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
43
+ "model.layers.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
44
+ "model.layers.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
45
+ "model.layers.10.self_attn.dense.bias": "model-00001-of-00003.safetensors",
46
+ "model.layers.10.self_attn.dense.weight": "model-00001-of-00003.safetensors",
47
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
48
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
49
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
50
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
51
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
52
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
53
+ "model.layers.11.input_layernorm.bias": "model-00001-of-00003.safetensors",
54
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
55
+ "model.layers.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
56
+ "model.layers.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
57
+ "model.layers.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
58
+ "model.layers.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
59
+ "model.layers.11.self_attn.dense.bias": "model-00001-of-00003.safetensors",
60
+ "model.layers.11.self_attn.dense.weight": "model-00001-of-00003.safetensors",
61
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
62
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
63
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
64
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
65
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
66
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
67
+ "model.layers.12.input_layernorm.bias": "model-00001-of-00003.safetensors",
68
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
69
+ "model.layers.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
70
+ "model.layers.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
71
+ "model.layers.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
72
+ "model.layers.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
73
+ "model.layers.12.self_attn.dense.bias": "model-00001-of-00003.safetensors",
74
+ "model.layers.12.self_attn.dense.weight": "model-00001-of-00003.safetensors",
75
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
76
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
77
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
78
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
79
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
80
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
81
+ "model.layers.13.input_layernorm.bias": "model-00001-of-00003.safetensors",
82
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
83
+ "model.layers.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
84
+ "model.layers.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
85
+ "model.layers.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
86
+ "model.layers.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
87
+ "model.layers.13.self_attn.dense.bias": "model-00001-of-00003.safetensors",
88
+ "model.layers.13.self_attn.dense.weight": "model-00001-of-00003.safetensors",
89
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
90
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
91
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
92
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
93
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
94
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
95
+ "model.layers.14.input_layernorm.bias": "model-00002-of-00003.safetensors",
96
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.14.mlp.fc1.bias": "model-00002-of-00003.safetensors",
98
+ "model.layers.14.mlp.fc1.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.14.mlp.fc2.bias": "model-00002-of-00003.safetensors",
100
+ "model.layers.14.mlp.fc2.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.14.self_attn.dense.bias": "model-00002-of-00003.safetensors",
102
+ "model.layers.14.self_attn.dense.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
104
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
105
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
106
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
107
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
108
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
109
+ "model.layers.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
110
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.15.mlp.fc1.bias": "model-00002-of-00003.safetensors",
112
+ "model.layers.15.mlp.fc1.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.15.mlp.fc2.bias": "model-00002-of-00003.safetensors",
114
+ "model.layers.15.mlp.fc2.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.15.self_attn.dense.bias": "model-00002-of-00003.safetensors",
116
+ "model.layers.15.self_attn.dense.weight": "model-00002-of-00003.safetensors",
117
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
118
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
119
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
120
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
121
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
122
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
123
+ "model.layers.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
124
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
125
+ "model.layers.16.mlp.fc1.bias": "model-00002-of-00003.safetensors",
126
+ "model.layers.16.mlp.fc1.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.16.mlp.fc2.bias": "model-00002-of-00003.safetensors",
128
+ "model.layers.16.mlp.fc2.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.16.self_attn.dense.bias": "model-00002-of-00003.safetensors",
130
+ "model.layers.16.self_attn.dense.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
132
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
134
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
136
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
138
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.17.mlp.fc1.bias": "model-00002-of-00003.safetensors",
140
+ "model.layers.17.mlp.fc1.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.17.mlp.fc2.bias": "model-00002-of-00003.safetensors",
142
+ "model.layers.17.mlp.fc2.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.17.self_attn.dense.bias": "model-00002-of-00003.safetensors",
144
+ "model.layers.17.self_attn.dense.weight": "model-00002-of-00003.safetensors",
145
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
146
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
147
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
148
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
150
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
152
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
153
+ "model.layers.18.mlp.fc1.bias": "model-00002-of-00003.safetensors",
154
+ "model.layers.18.mlp.fc1.weight": "model-00002-of-00003.safetensors",
155
+ "model.layers.18.mlp.fc2.bias": "model-00002-of-00003.safetensors",
156
+ "model.layers.18.mlp.fc2.weight": "model-00002-of-00003.safetensors",
157
+ "model.layers.18.self_attn.dense.bias": "model-00002-of-00003.safetensors",
158
+ "model.layers.18.self_attn.dense.weight": "model-00002-of-00003.safetensors",
159
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
160
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
161
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
162
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
163
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
164
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
165
+ "model.layers.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
166
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
167
+ "model.layers.19.mlp.fc1.bias": "model-00002-of-00003.safetensors",
168
+ "model.layers.19.mlp.fc1.weight": "model-00002-of-00003.safetensors",
169
+ "model.layers.19.mlp.fc2.bias": "model-00002-of-00003.safetensors",
170
+ "model.layers.19.mlp.fc2.weight": "model-00002-of-00003.safetensors",
171
+ "model.layers.19.self_attn.dense.bias": "model-00002-of-00003.safetensors",
172
+ "model.layers.19.self_attn.dense.weight": "model-00002-of-00003.safetensors",
173
+ "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
174
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
175
+ "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
176
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
177
+ "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
178
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
179
+ "model.layers.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
180
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
181
+ "model.layers.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
182
+ "model.layers.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
183
+ "model.layers.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
184
+ "model.layers.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
185
+ "model.layers.2.self_attn.dense.bias": "model-00001-of-00003.safetensors",
186
+ "model.layers.2.self_attn.dense.weight": "model-00001-of-00003.safetensors",
187
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
188
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
189
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
190
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
191
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
192
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
193
+ "model.layers.20.input_layernorm.bias": "model-00002-of-00003.safetensors",
194
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
195
+ "model.layers.20.mlp.fc1.bias": "model-00002-of-00003.safetensors",
196
+ "model.layers.20.mlp.fc1.weight": "model-00002-of-00003.safetensors",
197
+ "model.layers.20.mlp.fc2.bias": "model-00002-of-00003.safetensors",
198
+ "model.layers.20.mlp.fc2.weight": "model-00002-of-00003.safetensors",
199
+ "model.layers.20.self_attn.dense.bias": "model-00002-of-00003.safetensors",
200
+ "model.layers.20.self_attn.dense.weight": "model-00002-of-00003.safetensors",
201
+ "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
202
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
203
+ "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
204
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
205
+ "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
206
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
207
+ "model.layers.21.input_layernorm.bias": "model-00002-of-00003.safetensors",
208
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
209
+ "model.layers.21.mlp.fc1.bias": "model-00002-of-00003.safetensors",
210
+ "model.layers.21.mlp.fc1.weight": "model-00002-of-00003.safetensors",
211
+ "model.layers.21.mlp.fc2.bias": "model-00002-of-00003.safetensors",
212
+ "model.layers.21.mlp.fc2.weight": "model-00002-of-00003.safetensors",
213
+ "model.layers.21.self_attn.dense.bias": "model-00002-of-00003.safetensors",
214
+ "model.layers.21.self_attn.dense.weight": "model-00002-of-00003.safetensors",
215
+ "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
216
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
217
+ "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
218
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
219
+ "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
220
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
221
+ "model.layers.22.input_layernorm.bias": "model-00002-of-00003.safetensors",
222
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
223
+ "model.layers.22.mlp.fc1.bias": "model-00002-of-00003.safetensors",
224
+ "model.layers.22.mlp.fc1.weight": "model-00002-of-00003.safetensors",
225
+ "model.layers.22.mlp.fc2.bias": "model-00002-of-00003.safetensors",
226
+ "model.layers.22.mlp.fc2.weight": "model-00002-of-00003.safetensors",
227
+ "model.layers.22.self_attn.dense.bias": "model-00002-of-00003.safetensors",
228
+ "model.layers.22.self_attn.dense.weight": "model-00002-of-00003.safetensors",
229
+ "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
230
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
231
+ "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
232
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
233
+ "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
234
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
235
+ "model.layers.23.input_layernorm.bias": "model-00002-of-00003.safetensors",
236
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
237
+ "model.layers.23.mlp.fc1.bias": "model-00002-of-00003.safetensors",
238
+ "model.layers.23.mlp.fc1.weight": "model-00002-of-00003.safetensors",
239
+ "model.layers.23.mlp.fc2.bias": "model-00002-of-00003.safetensors",
240
+ "model.layers.23.mlp.fc2.weight": "model-00002-of-00003.safetensors",
241
+ "model.layers.23.self_attn.dense.bias": "model-00002-of-00003.safetensors",
242
+ "model.layers.23.self_attn.dense.weight": "model-00002-of-00003.safetensors",
243
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
244
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
245
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
246
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
247
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
248
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
249
+ "model.layers.24.input_layernorm.bias": "model-00002-of-00003.safetensors",
250
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
251
+ "model.layers.24.mlp.fc1.bias": "model-00002-of-00003.safetensors",
252
+ "model.layers.24.mlp.fc1.weight": "model-00002-of-00003.safetensors",
253
+ "model.layers.24.mlp.fc2.bias": "model-00002-of-00003.safetensors",
254
+ "model.layers.24.mlp.fc2.weight": "model-00002-of-00003.safetensors",
255
+ "model.layers.24.self_attn.dense.bias": "model-00002-of-00003.safetensors",
256
+ "model.layers.24.self_attn.dense.weight": "model-00002-of-00003.safetensors",
257
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
258
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
259
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
260
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
261
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
262
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
263
+ "model.layers.25.input_layernorm.bias": "model-00002-of-00003.safetensors",
264
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
265
+ "model.layers.25.mlp.fc1.bias": "model-00002-of-00003.safetensors",
266
+ "model.layers.25.mlp.fc1.weight": "model-00002-of-00003.safetensors",
267
+ "model.layers.25.mlp.fc2.bias": "model-00002-of-00003.safetensors",
268
+ "model.layers.25.mlp.fc2.weight": "model-00002-of-00003.safetensors",
269
+ "model.layers.25.self_attn.dense.bias": "model-00002-of-00003.safetensors",
270
+ "model.layers.25.self_attn.dense.weight": "model-00002-of-00003.safetensors",
271
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
272
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
273
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
274
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
275
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
276
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
277
+ "model.layers.26.input_layernorm.bias": "model-00002-of-00003.safetensors",
278
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
279
+ "model.layers.26.mlp.fc1.bias": "model-00002-of-00003.safetensors",
280
+ "model.layers.26.mlp.fc1.weight": "model-00002-of-00003.safetensors",
281
+ "model.layers.26.mlp.fc2.bias": "model-00002-of-00003.safetensors",
282
+ "model.layers.26.mlp.fc2.weight": "model-00002-of-00003.safetensors",
283
+ "model.layers.26.self_attn.dense.bias": "model-00002-of-00003.safetensors",
284
+ "model.layers.26.self_attn.dense.weight": "model-00002-of-00003.safetensors",
285
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
286
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
287
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
288
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
289
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
290
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
291
+ "model.layers.27.input_layernorm.bias": "model-00002-of-00003.safetensors",
292
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
293
+ "model.layers.27.mlp.fc1.bias": "model-00002-of-00003.safetensors",
294
+ "model.layers.27.mlp.fc1.weight": "model-00002-of-00003.safetensors",
295
+ "model.layers.27.mlp.fc2.bias": "model-00002-of-00003.safetensors",
296
+ "model.layers.27.mlp.fc2.weight": "model-00002-of-00003.safetensors",
297
+ "model.layers.27.self_attn.dense.bias": "model-00002-of-00003.safetensors",
298
+ "model.layers.27.self_attn.dense.weight": "model-00002-of-00003.safetensors",
299
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
300
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
301
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
302
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
303
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
304
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
305
+ "model.layers.28.input_layernorm.bias": "model-00002-of-00003.safetensors",
306
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
307
+ "model.layers.28.mlp.fc1.bias": "model-00002-of-00003.safetensors",
308
+ "model.layers.28.mlp.fc1.weight": "model-00002-of-00003.safetensors",
309
+ "model.layers.28.mlp.fc2.bias": "model-00002-of-00003.safetensors",
310
+ "model.layers.28.mlp.fc2.weight": "model-00002-of-00003.safetensors",
311
+ "model.layers.28.self_attn.dense.bias": "model-00002-of-00003.safetensors",
312
+ "model.layers.28.self_attn.dense.weight": "model-00002-of-00003.safetensors",
313
+ "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
314
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
315
+ "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
316
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
317
+ "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
318
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
319
+ "model.layers.29.input_layernorm.bias": "model-00002-of-00003.safetensors",
320
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
321
+ "model.layers.29.mlp.fc1.bias": "model-00002-of-00003.safetensors",
322
+ "model.layers.29.mlp.fc1.weight": "model-00002-of-00003.safetensors",
323
+ "model.layers.29.mlp.fc2.bias": "model-00002-of-00003.safetensors",
324
+ "model.layers.29.mlp.fc2.weight": "model-00002-of-00003.safetensors",
325
+ "model.layers.29.self_attn.dense.bias": "model-00002-of-00003.safetensors",
326
+ "model.layers.29.self_attn.dense.weight": "model-00002-of-00003.safetensors",
327
+ "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
328
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
329
+ "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
330
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
331
+ "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
332
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
333
+ "model.layers.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
334
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
335
+ "model.layers.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
336
+ "model.layers.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
337
+ "model.layers.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
338
+ "model.layers.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
339
+ "model.layers.3.self_attn.dense.bias": "model-00001-of-00003.safetensors",
340
+ "model.layers.3.self_attn.dense.weight": "model-00001-of-00003.safetensors",
341
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
342
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
343
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
344
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
345
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
346
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
347
+ "model.layers.30.input_layernorm.bias": "model-00003-of-00003.safetensors",
348
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
349
+ "model.layers.30.mlp.fc1.bias": "model-00003-of-00003.safetensors",
350
+ "model.layers.30.mlp.fc1.weight": "model-00003-of-00003.safetensors",
351
+ "model.layers.30.mlp.fc2.bias": "model-00003-of-00003.safetensors",
352
+ "model.layers.30.mlp.fc2.weight": "model-00003-of-00003.safetensors",
353
+ "model.layers.30.self_attn.dense.bias": "model-00003-of-00003.safetensors",
354
+ "model.layers.30.self_attn.dense.weight": "model-00003-of-00003.safetensors",
355
+ "model.layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
356
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
357
+ "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
358
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
359
+ "model.layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
360
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
361
+ "model.layers.31.input_layernorm.bias": "model-00003-of-00003.safetensors",
362
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
363
+ "model.layers.31.mlp.fc1.bias": "model-00003-of-00003.safetensors",
364
+ "model.layers.31.mlp.fc1.weight": "model-00003-of-00003.safetensors",
365
+ "model.layers.31.mlp.fc2.bias": "model-00003-of-00003.safetensors",
366
+ "model.layers.31.mlp.fc2.weight": "model-00003-of-00003.safetensors",
367
+ "model.layers.31.self_attn.dense.bias": "model-00003-of-00003.safetensors",
368
+ "model.layers.31.self_attn.dense.weight": "model-00003-of-00003.safetensors",
369
+ "model.layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
370
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
371
+ "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
372
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
373
+ "model.layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
374
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
375
+ "model.layers.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
376
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
377
+ "model.layers.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
378
+ "model.layers.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
379
+ "model.layers.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
380
+ "model.layers.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
381
+ "model.layers.4.self_attn.dense.bias": "model-00001-of-00003.safetensors",
382
+ "model.layers.4.self_attn.dense.weight": "model-00001-of-00003.safetensors",
383
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
384
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
385
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
386
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
387
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
388
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
389
+ "model.layers.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
390
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
391
+ "model.layers.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
392
+ "model.layers.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
393
+ "model.layers.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
394
+ "model.layers.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
395
+ "model.layers.5.self_attn.dense.bias": "model-00001-of-00003.safetensors",
396
+ "model.layers.5.self_attn.dense.weight": "model-00001-of-00003.safetensors",
397
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
398
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
399
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
400
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
401
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
402
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
403
+ "model.layers.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
404
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
405
+ "model.layers.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
406
+ "model.layers.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
407
+ "model.layers.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
408
+ "model.layers.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
409
+ "model.layers.6.self_attn.dense.bias": "model-00001-of-00003.safetensors",
410
+ "model.layers.6.self_attn.dense.weight": "model-00001-of-00003.safetensors",
411
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
412
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
413
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
414
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
415
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
416
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
417
+ "model.layers.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
418
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
419
+ "model.layers.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
420
+ "model.layers.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
421
+ "model.layers.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
422
+ "model.layers.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
423
+ "model.layers.7.self_attn.dense.bias": "model-00001-of-00003.safetensors",
424
+ "model.layers.7.self_attn.dense.weight": "model-00001-of-00003.safetensors",
425
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
426
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
427
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
428
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
429
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
430
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
431
+ "model.layers.8.input_layernorm.bias": "model-00001-of-00003.safetensors",
432
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
433
+ "model.layers.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
434
+ "model.layers.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
435
+ "model.layers.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
436
+ "model.layers.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
437
+ "model.layers.8.self_attn.dense.bias": "model-00001-of-00003.safetensors",
438
+ "model.layers.8.self_attn.dense.weight": "model-00001-of-00003.safetensors",
439
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
440
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
441
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
442
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
443
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
444
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
445
+ "model.layers.9.input_layernorm.bias": "model-00001-of-00003.safetensors",
446
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
447
+ "model.layers.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
448
+ "model.layers.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
449
+ "model.layers.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
450
+ "model.layers.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
451
+ "model.layers.9.self_attn.dense.bias": "model-00001-of-00003.safetensors",
452
+ "model.layers.9.self_attn.dense.weight": "model-00001-of-00003.safetensors",
453
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
454
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
455
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
456
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
457
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
458
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors"
459
+ }
460
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,332 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": " ",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": false
19
+ },
20
+ "50258": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50259": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50260": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50261": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50262": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50263": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50264": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50265": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50266": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50267": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50268": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50269": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50270": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50271": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50272": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50273": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50274": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50275": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50276": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50277": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50278": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50279": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50280": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "50281": {
205
+ "content": " ",
206
+ "lstrip": false,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "50282": {
213
+ "content": " ",
214
+ "lstrip": false,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "50283": {
221
+ "content": " ",
222
+ "lstrip": false,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "50284": {
229
+ "content": " ",
230
+ "lstrip": false,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
+ },
236
+ "50285": {
237
+ "content": " ",
238
+ "lstrip": false,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "50286": {
245
+ "content": " ",
246
+ "lstrip": false,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "50287": {
253
+ "content": "\t\t\t\t\t\t\t\t\t",
254
+ "lstrip": false,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "50288": {
261
+ "content": "\t\t\t\t\t\t\t\t",
262
+ "lstrip": false,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "50289": {
269
+ "content": "\t\t\t\t\t\t\t",
270
+ "lstrip": false,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "50290": {
277
+ "content": "\t\t\t\t\t\t",
278
+ "lstrip": false,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "50291": {
285
+ "content": "\t\t\t\t\t",
286
+ "lstrip": false,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "50292": {
293
+ "content": "\t\t\t\t",
294
+ "lstrip": false,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "50293": {
301
+ "content": "\t\t\t",
302
+ "lstrip": false,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "50294": {
309
+ "content": "\t\t",
310
+ "lstrip": false,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ },
316
+ "50295": {
317
+ "content": "[PAD]",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ }
324
+ },
325
+ "bos_token": "<|endoftext|>",
326
+ "clean_up_tokenization_spaces": true,
327
+ "eos_token": "<|endoftext|>",
328
+ "model_max_length": 2048,
329
+ "pad_token": "[PAD]",
330
+ "tokenizer_class": "CodeGenTokenizer",
331
+ "unk_token": "<|endoftext|>"
332
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.23391734473466494,
4
+ "train_runtime": 1027.8255,
5
+ "train_samples": 10068,
6
+ "train_samples_per_second": 9.795,
7
+ "train_steps_per_second": 0.612
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 6.0799336433410645,
3
+ "best_model_checkpoint": "./output_dir/checkpoint-629",
4
+ "epoch": 0.9996027016289233,
5
+ "eval_steps": 50.0,
6
+ "global_step": 629,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.08,
13
+ "grad_norm": 0.9626450538635254,
14
+ "learning_rate": 9.205087440381559e-05,
15
+ "loss": 0.8035,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.16,
20
+ "grad_norm": 0.889542281627655,
21
+ "learning_rate": 8.410174880763116e-05,
22
+ "loss": 0.3005,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.24,
27
+ "grad_norm": 0.5076414942741394,
28
+ "learning_rate": 7.615262321144675e-05,
29
+ "loss": 0.2731,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 0.32,
34
+ "grad_norm": 1.0295907258987427,
35
+ "learning_rate": 6.820349761526232e-05,
36
+ "loss": 0.2261,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.4,
41
+ "grad_norm": 0.3473876416683197,
42
+ "learning_rate": 6.0254372019077906e-05,
43
+ "loss": 0.1866,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 0.48,
48
+ "grad_norm": 0.5202713012695312,
49
+ "learning_rate": 5.2305246422893485e-05,
50
+ "loss": 0.1937,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 0.56,
55
+ "grad_norm": 0.25799375772476196,
56
+ "learning_rate": 4.4356120826709064e-05,
57
+ "loss": 0.1769,
58
+ "step": 350
59
+ },
60
+ {
61
+ "epoch": 0.64,
62
+ "grad_norm": 0.2543068826198578,
63
+ "learning_rate": 3.640699523052464e-05,
64
+ "loss": 0.1693,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 0.72,
69
+ "grad_norm": 0.5472003221511841,
70
+ "learning_rate": 2.8457869634340222e-05,
71
+ "loss": 0.1611,
72
+ "step": 450
73
+ },
74
+ {
75
+ "epoch": 0.79,
76
+ "grad_norm": 0.19463592767715454,
77
+ "learning_rate": 2.05087440381558e-05,
78
+ "loss": 0.1487,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 0.87,
83
+ "grad_norm": 0.7376086711883545,
84
+ "learning_rate": 1.2559618441971382e-05,
85
+ "loss": 0.1111,
86
+ "step": 550
87
+ },
88
+ {
89
+ "epoch": 0.95,
90
+ "grad_norm": 0.5419193506240845,
91
+ "learning_rate": 4.610492845786963e-06,
92
+ "loss": 0.122,
93
+ "step": 600
94
+ },
95
+ {
96
+ "epoch": 1.0,
97
+ "eval_bleu-1": 78.7702,
98
+ "eval_bleu-2": 75.9001,
99
+ "eval_bleu-3": 75.2623,
100
+ "eval_bleu-4": 74.9418,
101
+ "eval_gen_len": 128.0,
102
+ "eval_loss": 6.0799336433410645,
103
+ "eval_runtime": 5.1216,
104
+ "eval_samples_per_second": 2.343,
105
+ "eval_steps_per_second": 0.586,
106
+ "step": 629
107
+ },
108
+ {
109
+ "epoch": 1.0,
110
+ "step": 629,
111
+ "total_flos": 8.181451760192717e+16,
112
+ "train_loss": 0.23391734473466494,
113
+ "train_runtime": 1027.8255,
114
+ "train_samples_per_second": 9.795,
115
+ "train_steps_per_second": 0.612
116
+ }
117
+ ],
118
+ "logging_steps": 50,
119
+ "max_steps": 629,
120
+ "num_input_tokens_seen": 0,
121
+ "num_train_epochs": 1,
122
+ "save_steps": 500,
123
+ "total_flos": 8.181451760192717e+16,
124
+ "train_batch_size": 4,
125
+ "trial_name": null,
126
+ "trial_params": null
127
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41b9c19cb124ae3b714c706e92a4d05b9574602c30ed5815027ce662f6b917d4
3
+ size 5048
vocab.json ADDED
The diff for this file is too large to render. See raw diff