root commited on
Commit
171d73c
·
1 Parent(s): b68e31d

Initial Commit

Browse files
.ipynb_checkpoints/loss_curves-checkpoint.png ADDED
.ipynb_checkpoints/loss_metrics-checkpoint.json ADDED
@@ -0,0 +1 @@
 
 
1
+ []
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|end_of_role|>": 49153,
3
+ "<|start_of_role|>": 49152,
4
+ "<|tool_call|>": 49154
5
+ }
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ibm-granite/granite-3.0-8b-instruct",
3
+ "architectures": [
4
+ "GraniteForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.1,
8
+ "attention_multiplier": 0.0078125,
9
+ "bos_token_id": 0,
10
+ "embedding_multiplier": 12.0,
11
+ "eos_token_id": 0,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 4096,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 12800,
16
+ "logits_scaling": 16.0,
17
+ "max_position_embeddings": 4096,
18
+ "mlp_bias": false,
19
+ "model_type": "granite",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 40,
22
+ "num_key_value_heads": 8,
23
+ "pad_token_id": 0,
24
+ "residual_multiplier": 0.22,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_scaling": null,
27
+ "rope_theta": 10000,
28
+ "tie_word_embeddings": true,
29
+ "torch_dtype": "bfloat16",
30
+ "transformers_version": "4.46.3",
31
+ "use_cache": true,
32
+ "vocab_size": 49155
33
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.46.3"
7
+ }
loss_curves.png ADDED
loss_metrics.json ADDED
@@ -0,0 +1,215 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "step": 30,
4
+ "loss": 1.4062,
5
+ "type": "train",
6
+ "grad_norm": 8.482284545898438,
7
+ "learning_rate": 1.8347107438016528e-06,
8
+ "epoch": 0.2475502836513667
9
+ },
10
+ {
11
+ "step": 30,
12
+ "loss": 1.1563361883163452,
13
+ "type": "eval",
14
+ "eval_runtime": 238.6436,
15
+ "eval_samples_per_second": 2.891,
16
+ "eval_steps_per_second": 2.891,
17
+ "epoch": 0.2475502836513667
18
+ },
19
+ {
20
+ "step": 60,
21
+ "loss": 1.1662,
22
+ "type": "train",
23
+ "grad_norm": 6.751504898071289,
24
+ "learning_rate": 1.6694214876033058e-06,
25
+ "epoch": 0.4951005673027334
26
+ },
27
+ {
28
+ "step": 60,
29
+ "loss": 1.0914983749389648,
30
+ "type": "eval",
31
+ "eval_runtime": 248.6513,
32
+ "eval_samples_per_second": 2.775,
33
+ "eval_steps_per_second": 2.775,
34
+ "epoch": 0.4951005673027334
35
+ },
36
+ {
37
+ "step": 90,
38
+ "loss": 1.1109,
39
+ "type": "train",
40
+ "grad_norm": 4.135236740112305,
41
+ "learning_rate": 1.5041322314049587e-06,
42
+ "epoch": 0.7426508509541001
43
+ },
44
+ {
45
+ "step": 90,
46
+ "loss": 1.0496803522109985,
47
+ "type": "eval",
48
+ "eval_runtime": 239.5109,
49
+ "eval_samples_per_second": 2.881,
50
+ "eval_steps_per_second": 2.881,
51
+ "epoch": 0.7426508509541001
52
+ },
53
+ {
54
+ "step": 120,
55
+ "loss": 1.0639,
56
+ "type": "train",
57
+ "grad_norm": 5.695450782775879,
58
+ "learning_rate": 1.3388429752066116e-06,
59
+ "epoch": 0.9902011346054668
60
+ },
61
+ {
62
+ "step": 120,
63
+ "loss": 1.0101323127746582,
64
+ "type": "eval",
65
+ "eval_runtime": 234.2087,
66
+ "eval_samples_per_second": 2.946,
67
+ "eval_steps_per_second": 2.946,
68
+ "epoch": 0.9902011346054668
69
+ },
70
+ {
71
+ "step": 150,
72
+ "loss": 0.9416,
73
+ "type": "train",
74
+ "grad_norm": 7.571918487548828,
75
+ "learning_rate": 1.1735537190082645e-06,
76
+ "epoch": 1.2377514182568334
77
+ },
78
+ {
79
+ "step": 150,
80
+ "loss": 1.0040597915649414,
81
+ "type": "eval",
82
+ "eval_runtime": 247.1746,
83
+ "eval_samples_per_second": 2.792,
84
+ "eval_steps_per_second": 2.792,
85
+ "epoch": 1.2377514182568334
86
+ },
87
+ {
88
+ "step": 180,
89
+ "loss": 0.925,
90
+ "type": "train",
91
+ "grad_norm": 4.53548002243042,
92
+ "learning_rate": 1.0082644628099172e-06,
93
+ "epoch": 1.4853017019082002
94
+ },
95
+ {
96
+ "step": 180,
97
+ "loss": 0.9938931465148926,
98
+ "type": "eval",
99
+ "eval_runtime": 234.8252,
100
+ "eval_samples_per_second": 2.938,
101
+ "eval_steps_per_second": 2.938,
102
+ "epoch": 1.4853017019082002
103
+ },
104
+ {
105
+ "step": 210,
106
+ "loss": 0.9033,
107
+ "type": "train",
108
+ "grad_norm": 5.361794948577881,
109
+ "learning_rate": 8.429752066115701e-07,
110
+ "epoch": 1.7328519855595668
111
+ },
112
+ {
113
+ "step": 210,
114
+ "loss": 0.9868502020835876,
115
+ "type": "eval",
116
+ "eval_runtime": 234.8772,
117
+ "eval_samples_per_second": 2.938,
118
+ "eval_steps_per_second": 2.938,
119
+ "epoch": 1.7328519855595668
120
+ },
121
+ {
122
+ "step": 240,
123
+ "loss": 0.9087,
124
+ "type": "train",
125
+ "grad_norm": 4.525313377380371,
126
+ "learning_rate": 6.776859504132231e-07,
127
+ "epoch": 1.9804022692109333
128
+ },
129
+ {
130
+ "step": 240,
131
+ "loss": 0.9824326634407043,
132
+ "type": "eval",
133
+ "eval_runtime": 234.8918,
134
+ "eval_samples_per_second": 2.938,
135
+ "eval_steps_per_second": 2.938,
136
+ "epoch": 1.9804022692109333
137
+ },
138
+ {
139
+ "step": 270,
140
+ "loss": 0.8166,
141
+ "type": "train",
142
+ "grad_norm": 4.654973030090332,
143
+ "learning_rate": 5.12396694214876e-07,
144
+ "epoch": 2.2279525528623
145
+ },
146
+ {
147
+ "step": 270,
148
+ "loss": 0.9874295592308044,
149
+ "type": "eval",
150
+ "eval_runtime": 243.7953,
151
+ "eval_samples_per_second": 2.83,
152
+ "eval_steps_per_second": 2.83,
153
+ "epoch": 2.2279525528623
154
+ },
155
+ {
156
+ "step": 300,
157
+ "loss": 0.8226,
158
+ "type": "train",
159
+ "grad_norm": 5.9346442222595215,
160
+ "learning_rate": 3.471074380165289e-07,
161
+ "epoch": 2.475502836513667
162
+ },
163
+ {
164
+ "step": 300,
165
+ "loss": 0.9854046106338501,
166
+ "type": "eval",
167
+ "eval_runtime": 243.3847,
168
+ "eval_samples_per_second": 2.835,
169
+ "eval_steps_per_second": 2.835,
170
+ "epoch": 2.475502836513667
171
+ },
172
+ {
173
+ "step": 330,
174
+ "loss": 0.8289,
175
+ "type": "train",
176
+ "grad_norm": 4.637845516204834,
177
+ "learning_rate": 1.818181818181818e-07,
178
+ "epoch": 2.7230531201650336
179
+ },
180
+ {
181
+ "step": 330,
182
+ "loss": 0.9841367602348328,
183
+ "type": "eval",
184
+ "eval_runtime": 242.6797,
185
+ "eval_samples_per_second": 2.843,
186
+ "eval_steps_per_second": 2.843,
187
+ "epoch": 2.7230531201650336
188
+ },
189
+ {
190
+ "step": 360,
191
+ "loss": 0.8137,
192
+ "type": "train",
193
+ "grad_norm": 4.132049560546875,
194
+ "learning_rate": 1.652892561983471e-08,
195
+ "epoch": 2.9706034038164004
196
+ },
197
+ {
198
+ "step": 360,
199
+ "loss": 0.9834251403808594,
200
+ "type": "eval",
201
+ "eval_runtime": 242.7445,
202
+ "eval_samples_per_second": 2.842,
203
+ "eval_steps_per_second": 2.842,
204
+ "epoch": 2.9706034038164004
205
+ },
206
+ {
207
+ "step": 363,
208
+ "train_runtime": 22924.4691,
209
+ "train_samples_per_second": 0.507,
210
+ "train_steps_per_second": 0.016,
211
+ "total_flos": 7877706776576.0,
212
+ "train_loss": 0.9745982139892158,
213
+ "epoch": 2.9953584321815367
214
+ }
215
+ ]
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ee86e24c9c7ec40a68d28a401336c489e82876e145d774150fd99c0ea5659dd
3
+ size 4974661520
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03422d04527de3cbf5ac145a490b0d19647504f1ba751c374a91feadec2d3aa0
3
+ size 4991447808
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6f90e55a4397c0cd62528487df4dfb1a98ac7e308516391af7129bbfb0dda76
3
+ size 4970460032
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:047a3def219df936750e5d07737d52333049f6b8336e3bf865dd0e5d64247e98
3
+ size 1405169256
model.safetensors.index.json ADDED
@@ -0,0 +1,369 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16341696512
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
29
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
30
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
32
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
33
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
34
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
37
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
40
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
41
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
42
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
43
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
116
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
125
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
126
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
127
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
129
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
130
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
137
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
138
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
139
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
140
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
141
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
142
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
143
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
144
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
145
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
146
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
147
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
148
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
149
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
150
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
151
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
152
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
153
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
154
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
155
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
156
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
157
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
158
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
159
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
160
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
215
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
224
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
235
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
245
+ "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
246
+ "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
247
+ "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
250
+ "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
251
+ "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
252
+ "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
253
+ "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
254
+ "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
255
+ "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
256
+ "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
257
+ "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
258
+ "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
259
+ "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
260
+ "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
261
+ "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
262
+ "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
263
+ "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
264
+ "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
265
+ "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
266
+ "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
267
+ "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
268
+ "model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
269
+ "model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
270
+ "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
271
+ "model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
272
+ "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
273
+ "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
274
+ "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
275
+ "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
276
+ "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
277
+ "model.layers.36.input_layernorm.weight": "model-00004-of-00004.safetensors",
278
+ "model.layers.36.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
279
+ "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
280
+ "model.layers.36.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
281
+ "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
282
+ "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
283
+ "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
284
+ "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
285
+ "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
286
+ "model.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors",
287
+ "model.layers.37.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
288
+ "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
289
+ "model.layers.37.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
290
+ "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
291
+ "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
292
+ "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
293
+ "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
294
+ "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
295
+ "model.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors",
296
+ "model.layers.38.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
297
+ "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
298
+ "model.layers.38.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
299
+ "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
300
+ "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
301
+ "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
302
+ "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
303
+ "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
304
+ "model.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors",
305
+ "model.layers.39.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
306
+ "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
307
+ "model.layers.39.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
308
+ "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
309
+ "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
310
+ "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
311
+ "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
312
+ "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
313
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
314
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
315
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
316
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
317
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
318
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
319
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
320
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
321
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
322
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
323
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
324
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
325
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
326
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
327
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
328
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
329
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
330
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
331
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
332
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
333
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
334
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
335
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
336
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
337
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
338
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
339
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
340
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
341
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
342
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
343
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
344
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
345
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
346
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
347
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
348
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
349
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
350
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
351
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
352
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
353
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
354
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
355
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
356
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
357
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
358
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
359
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
360
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
361
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
362
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
363
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
364
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
365
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
366
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
367
+ "model.norm.weight": "model-00004-of-00004.safetensors"
368
+ }
369
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|start_of_role|>",
4
+ "<|end_of_role|>",
5
+ "<|tool_call|>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<|end_of_text|>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "<|end_of_text|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "<|end_of_text|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<|end_of_text|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,198 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<|end_of_text|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<fim_prefix>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<fim_middle>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<fim_suffix>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<fim_pad>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "5": {
46
+ "content": "<filename>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "6": {
54
+ "content": "<gh_stars>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "7": {
62
+ "content": "<issue_start>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "8": {
70
+ "content": "<issue_comment>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "9": {
78
+ "content": "<issue_closed>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "10": {
86
+ "content": "<jupyter_start>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "11": {
94
+ "content": "<jupyter_text>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "12": {
102
+ "content": "<jupyter_code>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "13": {
110
+ "content": "<jupyter_output>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "14": {
118
+ "content": "<empty_output>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "15": {
126
+ "content": "<commit_before>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "16": {
134
+ "content": "<commit_msg>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "17": {
142
+ "content": "<commit_after>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "18": {
150
+ "content": "<reponame>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "49152": {
158
+ "content": "<|start_of_role|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "49153": {
166
+ "content": "<|end_of_role|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "49154": {
174
+ "content": "<|tool_call|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|start_of_role|>",
184
+ "<|end_of_role|>",
185
+ "<|tool_call|>"
186
+ ],
187
+ "bos_token": "<|end_of_text|>",
188
+ "chat_template": "{%- if tools %}\n {{- '<|start_of_role|>available_tools<|end_of_role|>\n' }}\n {%- for tool in tools %}\n {{- tool | tojson(indent=4) }}\n {%- if not loop.last %}\n {{- '\n\n' }}\n {%- endif %}\n {%- endfor %}\n {{- '<|end_of_text|>\n' }}\n{%- endif %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n {{- '<|start_of_role|>system<|end_of_role|>' + message['content'] + '<|end_of_text|>\n' }}\n {%- elif message['role'] == 'user' %}\n {{- '<|start_of_role|>user<|end_of_role|>' + message['content'] + '<|end_of_text|>\n' }}\n {%- elif message['role'] == 'assistant' %}\n {{- '<|start_of_role|>assistant<|end_of_role|>' + message['content'] + '<|end_of_text|>\n' }}\n {%- elif message['role'] == 'assistant_tool_call' %}\n {{- '<|start_of_role|>assistant<|end_of_role|><|tool_call|>' + message['content'] + '<|end_of_text|>\n' }}\n {%- elif message['role'] == 'tool_response' %}\n {{- '<|start_of_role|>tool_response<|end_of_role|>' + message['content'] + '<|end_of_text|>\n' }}\n {%- endif %}\n {%- if loop.last and add_generation_prompt %}\n {{- '<|start_of_role|>assistant<|end_of_role|>' }}\n {%- endif %}\n{%- endfor %}",
189
+ "clean_up_tokenization_spaces": true,
190
+ "eos_token": "<|end_of_text|>",
191
+ "errors": "replace",
192
+ "model_max_length": 9223372036854775807,
193
+ "pad_token": "<|end_of_text|>",
194
+ "padding_side": "left",
195
+ "tokenizer_class": "GPT2Tokenizer",
196
+ "unk_token": "<|end_of_text|>",
197
+ "vocab_size": 49152
198
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94e845deaff4e8c26c02f32d8df6053a1ce785df328cc3f26218829abf755ab1
3
+ size 6520
vocab.json ADDED
The diff for this file is too large to render. See raw diff