Theoistic commited on
Commit
bc9042e
·
verified ·
1 Parent(s): 9297cfd

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,243 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BantamForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attention_head_groups": [
8
+ {
9
+ "head_dim": 128,
10
+ "kv_heads": 1,
11
+ "query_heads": 3
12
+ },
13
+ {
14
+ "head_dim": 64,
15
+ "kv_heads": 2,
16
+ "query_heads": 6
17
+ }
18
+ ],
19
+ "attn_logit_softcapping": 0.0,
20
+ "bos_token_id": 1,
21
+ "dtype": "bfloat16",
22
+ "eos_token_id": 2,
23
+ "final_logit_softcapping": 0.0,
24
+ "head_dim": 85,
25
+ "hidden_size": 768,
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 2304,
28
+ "label_smoothing": 0.0,
29
+ "layer_configs": [
30
+ {
31
+ "attention_head_groups": [
32
+ {
33
+ "head_dim": 64,
34
+ "kv_heads": 3,
35
+ "query_heads": 12
36
+ }
37
+ ],
38
+ "intermediate_size": 2304,
39
+ "num_attention_heads": 12,
40
+ "num_key_value_heads": 3,
41
+ "window": 128
42
+ },
43
+ {
44
+ "attention_head_groups": [
45
+ {
46
+ "head_dim": 64,
47
+ "kv_heads": 3,
48
+ "query_heads": 12
49
+ }
50
+ ],
51
+ "intermediate_size": 2304,
52
+ "num_attention_heads": 12,
53
+ "num_key_value_heads": 3,
54
+ "window": 128
55
+ },
56
+ {
57
+ "attention_head_groups": [
58
+ {
59
+ "head_dim": 64,
60
+ "kv_heads": 3,
61
+ "query_heads": 12
62
+ }
63
+ ],
64
+ "intermediate_size": 2368,
65
+ "num_attention_heads": 12,
66
+ "num_key_value_heads": 3,
67
+ "window": 128
68
+ },
69
+ {
70
+ "attention_head_groups": [
71
+ {
72
+ "head_dim": 64,
73
+ "kv_heads": 3,
74
+ "query_heads": 12
75
+ }
76
+ ],
77
+ "intermediate_size": 2400,
78
+ "num_attention_heads": 12,
79
+ "num_key_value_heads": 3
80
+ },
81
+ {
82
+ "attention_head_groups": [
83
+ {
84
+ "head_dim": 80,
85
+ "kv_heads": 2,
86
+ "query_heads": 6
87
+ },
88
+ {
89
+ "head_dim": 96,
90
+ "kv_heads": 1,
91
+ "query_heads": 3
92
+ }
93
+ ],
94
+ "expert_type": "topk",
95
+ "intermediate_size": 2432,
96
+ "moe_aux_loss_weight": 0.01,
97
+ "moe_capacity_factor": 1.05,
98
+ "moe_drop_policy": "random",
99
+ "moe_intermediate_size": 2432,
100
+ "moe_router_jitter": 0.05,
101
+ "moe_top_k": 2,
102
+ "num_attention_heads": 9,
103
+ "num_experts": 6,
104
+ "num_key_value_heads": 3,
105
+ "window": 256
106
+ },
107
+ {
108
+ "attention_head_groups": [
109
+ {
110
+ "head_dim": 80,
111
+ "kv_heads": 2,
112
+ "query_heads": 6
113
+ },
114
+ {
115
+ "head_dim": 96,
116
+ "kv_heads": 1,
117
+ "query_heads": 3
118
+ }
119
+ ],
120
+ "intermediate_size": 2368,
121
+ "num_attention_heads": 9,
122
+ "num_key_value_heads": 3,
123
+ "window": 256
124
+ },
125
+ {
126
+ "attention_head_groups": [
127
+ {
128
+ "head_dim": 80,
129
+ "kv_heads": 2,
130
+ "query_heads": 6
131
+ },
132
+ {
133
+ "head_dim": 96,
134
+ "kv_heads": 1,
135
+ "query_heads": 3
136
+ }
137
+ ],
138
+ "intermediate_size": 2432,
139
+ "num_attention_heads": 9,
140
+ "num_key_value_heads": 3,
141
+ "window": 256
142
+ },
143
+ {
144
+ "attention_head_groups": [
145
+ {
146
+ "head_dim": 80,
147
+ "kv_heads": 2,
148
+ "query_heads": 6
149
+ },
150
+ {
151
+ "head_dim": 96,
152
+ "kv_heads": 1,
153
+ "query_heads": 3
154
+ }
155
+ ],
156
+ "intermediate_size": 2368,
157
+ "num_attention_heads": 9,
158
+ "num_key_value_heads": 3
159
+ },
160
+ {
161
+ "intermediate_size": 2304,
162
+ "window": 256
163
+ },
164
+ {
165
+ "intermediate_size": 2368,
166
+ "window": 256
167
+ },
168
+ {
169
+ "intermediate_size": 2400,
170
+ "window": 256
171
+ },
172
+ {
173
+ "intermediate_size": 2432,
174
+ "window": 256
175
+ },
176
+ {
177
+ "intermediate_size": 2432
178
+ },
179
+ {
180
+ "intermediate_size": 2400,
181
+ "window": 512
182
+ },
183
+ {
184
+ "intermediate_size": 2432,
185
+ "window": 512
186
+ },
187
+ {
188
+ "intermediate_size": 2432,
189
+ "window": 512
190
+ },
191
+ {
192
+ "expert_type": "topk",
193
+ "intermediate_size": 2432,
194
+ "moe_aux_loss_weight": 0.01,
195
+ "moe_capacity_factor": 1.1,
196
+ "moe_drop_policy": "random",
197
+ "moe_intermediate_size": 2432,
198
+ "moe_router_jitter": 0.05,
199
+ "moe_top_k": 2,
200
+ "num_experts": 8,
201
+ "window": 512
202
+ },
203
+ {
204
+ "expert_type": "topk",
205
+ "intermediate_size": 2432,
206
+ "moe_aux_loss_weight": 0.01,
207
+ "moe_capacity_factor": 1.1,
208
+ "moe_drop_policy": "random",
209
+ "moe_intermediate_size": 2432,
210
+ "moe_router_jitter": 0.05,
211
+ "moe_top_k": 2,
212
+ "num_experts": 8
213
+ },
214
+ {
215
+ "intermediate_size": 2368,
216
+ "window": 512
217
+ },
218
+ {
219
+ "intermediate_size": 2400
220
+ }
221
+ ],
222
+ "max_head_dim": 128,
223
+ "max_position_embeddings": 2048,
224
+ "mlp_dropout": 0.0,
225
+ "model_type": "bantam",
226
+ "num_attention_heads": 9,
227
+ "num_attention_sinks": 4,
228
+ "num_hidden_layers": 20,
229
+ "num_key_value_heads": 3,
230
+ "pad_token_id": 1,
231
+ "qk_norm": true,
232
+ "qk_norm_eps": 1e-06,
233
+ "residual_dropout": 0.0,
234
+ "rms_norm_eps": 1e-06,
235
+ "rope_scaling": null,
236
+ "rope_theta": 10000.0,
237
+ "scaled_embeddings": false,
238
+ "sink_boost": 0.25,
239
+ "transformers_version": "4.57.1",
240
+ "use_cache": false,
241
+ "vocab_size": 49152,
242
+ "z_loss_weight": 0.0
243
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.57.1",
7
+ "use_cache": false
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52ead4b124ca1c257d50c36c9069bc037d1aec9d306140e65639c1e40d187823
3
+ size 571443364
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90c27a81f578097e56751319af5faec4071e83cf50a4762f304b6861d2c8f5ea
3
+ size 1143157881
rng_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c242972bd560f5561453fc36bfc2181272298527332acde570b9935d803e2cda
3
+ size 14709
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e73954c8722cc2d44a2f2092091e84e9a40c6fa62e10367758a1a6a3e172c6f
3
+ size 1465
special_tokens_map.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|SYSTEM_START|>",
4
+ "<|SYSTEM_END|>",
5
+ "<|USER_START|>",
6
+ "<|USER_END|>",
7
+ "<|AGENT_START|>",
8
+ "<|AGENT_END|>",
9
+ "<|THINK_START|>",
10
+ "<|THINK_END|>",
11
+ "<|COMPUTE_START|>",
12
+ "<|COMPUTE_END|>",
13
+ "<|IMAGE_START|>",
14
+ "<|IMAGE_END|>",
15
+ "<|AUDIO_START|>",
16
+ "<|AUDIO_END|>",
17
+ "<|VISION_START|>",
18
+ "<|VISION_END|>",
19
+ "<|OBJECT_REF_START|>",
20
+ "<|OBJECT_REF_END|>",
21
+ "<|BOX_START|>",
22
+ "<|BOX_END|>",
23
+ "<|QUAD_START|>",
24
+ "<|QUAD_END|>",
25
+ "<|VISION_PAD|>",
26
+ "<|IMAGE_PAD|>",
27
+ "<|VIDEO_PAD|>",
28
+ "<|AUDIO_TOKEN_START|>",
29
+ "<|AUDIO_TOKEN_END|>",
30
+ "<|JSON_START|>",
31
+ "<|JSON_END|>",
32
+ "<|TOOL_CALL_START|>",
33
+ "<|TOOL_CALL_END|>",
34
+ "<|TOOL_RESPONSE_START|>",
35
+ "<|TOOL_RESPONSE_END|>",
36
+ "<|OBJECTIVES_START|>",
37
+ "<|OBJECTIVES_END|>",
38
+ "<|TASKS_START|>",
39
+ "<|TASKS_END|>",
40
+ "<|ASSUMPTIONS_START|>",
41
+ "<|ASSUMPTIONS_END|>",
42
+ "<|CONSTRAINTS_START|>",
43
+ "<|CONSTRAINTS_END|>",
44
+ "<|CONTEXT_START|>",
45
+ "<|CONTEXT_END|>",
46
+ "<|CITATIONS_START|>",
47
+ "<|CITATIONS_END|>",
48
+ "<|PROVENANCE_START|>",
49
+ "<|PROVENANCE_END|>",
50
+ "<|REASON_START|>",
51
+ "<|REASON_END|>",
52
+ "<|VERIFY_START|>",
53
+ "<|VERIFY_END|>",
54
+ "<|ANSWER_DRAFT_START|>",
55
+ "<|ANSWER_DRAFT_END|>",
56
+ "<|SUMMARY_BULLETS_START|>",
57
+ "<|SUMMARY_BULLETS_END|>",
58
+ "<|ANSWER_FINAL_START|>",
59
+ "<|ANSWER_FINAL_END|>",
60
+ "<|REDACT_START|>",
61
+ "<|REDACT_END|>",
62
+ "<|EXT1_START|>",
63
+ "<|EXT1_END|>",
64
+ "<|EXT2_START|>",
65
+ "<|EXT2_END|>",
66
+ "<|EXT3_START|>",
67
+ "<|EXT3_END|>",
68
+ "<|EXT4_START|>",
69
+ "<|EXT4_END|>"
70
+ ],
71
+ "bos_token": "<|BOS|>",
72
+ "eos_token": "<|EOS|>",
73
+ "pad_token": "<|PAD|>",
74
+ "unk_token": {
75
+ "content": "<|UNK|>",
76
+ "lstrip": false,
77
+ "normalized": false,
78
+ "rstrip": false,
79
+ "single_word": false
80
+ }
81
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,649 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<|UNK|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<|PAD|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<|BOS|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<|EOS|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<|SYSTEM_START|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<|SYSTEM_END|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<|USER_START|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<|USER_END|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "8": {
68
+ "content": "<|AGENT_START|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "9": {
76
+ "content": "<|AGENT_END|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "10": {
84
+ "content": "<|THINK_START|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "11": {
92
+ "content": "<|THINK_END|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "12": {
100
+ "content": "<|COMPUTE_START|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "13": {
108
+ "content": "<|COMPUTE_END|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "14": {
116
+ "content": "<|IMAGE_START|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "15": {
124
+ "content": "<|IMAGE_END|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "16": {
132
+ "content": "<|AUDIO_START|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "17": {
140
+ "content": "<|AUDIO_END|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "18": {
148
+ "content": "<|VISION_START|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "19": {
156
+ "content": "<|VISION_END|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "20": {
164
+ "content": "<|OBJECT_REF_START|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "21": {
172
+ "content": "<|OBJECT_REF_END|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "22": {
180
+ "content": "<|BOX_START|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "23": {
188
+ "content": "<|BOX_END|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "24": {
196
+ "content": "<|QUAD_START|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "25": {
204
+ "content": "<|QUAD_END|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "26": {
212
+ "content": "<|VISION_PAD|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "27": {
220
+ "content": "<|IMAGE_PAD|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "28": {
228
+ "content": "<|VIDEO_PAD|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "29": {
236
+ "content": "<|AUDIO_TOKEN_START|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "30": {
244
+ "content": "<|AUDIO_TOKEN_END|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "31": {
252
+ "content": "<|JSON_START|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "32": {
260
+ "content": "<|JSON_END|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "33": {
268
+ "content": "<|TOOL_CALL_START|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "34": {
276
+ "content": "<|TOOL_CALL_END|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "35": {
284
+ "content": "<|TOOL_RESPONSE_START|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "36": {
292
+ "content": "<|TOOL_RESPONSE_END|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "37": {
300
+ "content": "<|OBJECTIVES_START|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "38": {
308
+ "content": "<|OBJECTIVES_END|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "39": {
316
+ "content": "<|TASKS_START|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "40": {
324
+ "content": "<|TASKS_END|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "41": {
332
+ "content": "<|ASSUMPTIONS_START|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "42": {
340
+ "content": "<|ASSUMPTIONS_END|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "43": {
348
+ "content": "<|CONSTRAINTS_START|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "44": {
356
+ "content": "<|CONSTRAINTS_END|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "45": {
364
+ "content": "<|CONTEXT_START|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "46": {
372
+ "content": "<|CONTEXT_END|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "47": {
380
+ "content": "<|CITATIONS_START|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "48": {
388
+ "content": "<|CITATIONS_END|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "49": {
396
+ "content": "<|PROVENANCE_START|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "50": {
404
+ "content": "<|PROVENANCE_END|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "51": {
412
+ "content": "<|REASON_START|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "52": {
420
+ "content": "<|REASON_END|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "53": {
428
+ "content": "<|VERIFY_START|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "54": {
436
+ "content": "<|VERIFY_END|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "55": {
444
+ "content": "<|ANSWER_DRAFT_START|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "56": {
452
+ "content": "<|ANSWER_DRAFT_END|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "57": {
460
+ "content": "<|SUMMARY_BULLETS_START|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "58": {
468
+ "content": "<|SUMMARY_BULLETS_END|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "59": {
476
+ "content": "<|ANSWER_FINAL_START|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "60": {
484
+ "content": "<|ANSWER_FINAL_END|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "61": {
492
+ "content": "<|REDACT_START|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "62": {
500
+ "content": "<|REDACT_END|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "63": {
508
+ "content": "<|EXT1_START|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "64": {
516
+ "content": "<|EXT1_END|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "65": {
524
+ "content": "<|EXT2_START|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "66": {
532
+ "content": "<|EXT2_END|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "67": {
540
+ "content": "<|EXT3_START|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "68": {
548
+ "content": "<|EXT3_END|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "69": {
556
+ "content": "<|EXT4_START|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "70": {
564
+ "content": "<|EXT4_END|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ }
571
+ },
572
+ "additional_special_tokens": [
573
+ "<|SYSTEM_START|>",
574
+ "<|SYSTEM_END|>",
575
+ "<|USER_START|>",
576
+ "<|USER_END|>",
577
+ "<|AGENT_START|>",
578
+ "<|AGENT_END|>",
579
+ "<|THINK_START|>",
580
+ "<|THINK_END|>",
581
+ "<|COMPUTE_START|>",
582
+ "<|COMPUTE_END|>",
583
+ "<|IMAGE_START|>",
584
+ "<|IMAGE_END|>",
585
+ "<|AUDIO_START|>",
586
+ "<|AUDIO_END|>",
587
+ "<|VISION_START|>",
588
+ "<|VISION_END|>",
589
+ "<|OBJECT_REF_START|>",
590
+ "<|OBJECT_REF_END|>",
591
+ "<|BOX_START|>",
592
+ "<|BOX_END|>",
593
+ "<|QUAD_START|>",
594
+ "<|QUAD_END|>",
595
+ "<|VISION_PAD|>",
596
+ "<|IMAGE_PAD|>",
597
+ "<|VIDEO_PAD|>",
598
+ "<|AUDIO_TOKEN_START|>",
599
+ "<|AUDIO_TOKEN_END|>",
600
+ "<|JSON_START|>",
601
+ "<|JSON_END|>",
602
+ "<|TOOL_CALL_START|>",
603
+ "<|TOOL_CALL_END|>",
604
+ "<|TOOL_RESPONSE_START|>",
605
+ "<|TOOL_RESPONSE_END|>",
606
+ "<|OBJECTIVES_START|>",
607
+ "<|OBJECTIVES_END|>",
608
+ "<|TASKS_START|>",
609
+ "<|TASKS_END|>",
610
+ "<|ASSUMPTIONS_START|>",
611
+ "<|ASSUMPTIONS_END|>",
612
+ "<|CONSTRAINTS_START|>",
613
+ "<|CONSTRAINTS_END|>",
614
+ "<|CONTEXT_START|>",
615
+ "<|CONTEXT_END|>",
616
+ "<|CITATIONS_START|>",
617
+ "<|CITATIONS_END|>",
618
+ "<|PROVENANCE_START|>",
619
+ "<|PROVENANCE_END|>",
620
+ "<|REASON_START|>",
621
+ "<|REASON_END|>",
622
+ "<|VERIFY_START|>",
623
+ "<|VERIFY_END|>",
624
+ "<|ANSWER_DRAFT_START|>",
625
+ "<|ANSWER_DRAFT_END|>",
626
+ "<|SUMMARY_BULLETS_START|>",
627
+ "<|SUMMARY_BULLETS_END|>",
628
+ "<|ANSWER_FINAL_START|>",
629
+ "<|ANSWER_FINAL_END|>",
630
+ "<|REDACT_START|>",
631
+ "<|REDACT_END|>",
632
+ "<|EXT1_START|>",
633
+ "<|EXT1_END|>",
634
+ "<|EXT2_START|>",
635
+ "<|EXT2_END|>",
636
+ "<|EXT3_START|>",
637
+ "<|EXT3_END|>",
638
+ "<|EXT4_START|>",
639
+ "<|EXT4_END|>"
640
+ ],
641
+ "bos_token": "<|BOS|>",
642
+ "clean_up_tokenization_spaces": false,
643
+ "eos_token": "<|EOS|>",
644
+ "extra_special_tokens": {},
645
+ "model_max_length": 16384,
646
+ "pad_token": "<|PAD|>",
647
+ "tokenizer_class": "PreTrainedTokenizerFast",
648
+ "unk_token": "<|UNK|>"
649
+ }
training_args.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset": "/root/lang_mix.jsonl",
3
+ "tokenizer": "/root/tokenizers",
4
+ "out_dir": "/root/models/run_cen_V",
5
+ "use_hf": false,
6
+ "hf_name": null,
7
+ "hf_subset": null,
8
+ "hf_split": "train",
9
+ "hf_streaming": true,
10
+ "hf_text_field": "text",
11
+ "hf_messages_field": "messages",
12
+ "shuffle_buffer_size": 10000,
13
+ "seed": 1337,
14
+ "init_from_checkpoint": null,
15
+ "finetune_from": null,
16
+ "strict_vocab_match": false,
17
+ "save_tag": null,
18
+ "save_every_n": 2000,
19
+ "keep_last_k": 3,
20
+ "save_on_improve": false,
21
+ "improve_delta": 0.0,
22
+ "resume_from_checkpoint": null,
23
+ "log_loss_to_csv": false,
24
+ "dataset_text_field": "text",
25
+ "min_sample_token_length": 8,
26
+ "stream_local_dataset": false,
27
+ "local_dataset_shuffle_buffer": 2048,
28
+ "block_count_sample_fraction": 0.02,
29
+ "block_count_min_sample_megabytes": 32,
30
+ "block_count_max_sample_megabytes": 512,
31
+ "precision": "bf16",
32
+ "optimizer": "adamw",
33
+ "lr": 0.0003,
34
+ "weight_decay": 0.06,
35
+ "beta2": 0.98,
36
+ "adam_eps": 1e-08,
37
+ "grad_clip": 0.8,
38
+ "optim_eps": 1e-08,
39
+ "lr_scheduler": "cosine",
40
+ "min_lr_ratio": 0.05,
41
+ "muon_lr": null,
42
+ "muon_momentum": 0.95,
43
+ "muon_exclude_embeddings": true,
44
+ "muon_beta1": null,
45
+ "muon_beta2": null,
46
+ "muon_eps": null,
47
+ "muon_bias_correction": true,
48
+ "muon_clip_by_layer": false,
49
+ "muon_lr_correction": true,
50
+ "batch_size": 4,
51
+ "accum_steps": 16,
52
+ "epochs": 2,
53
+ "warmup_frac": 0.05,
54
+ "log_every_n": 10,
55
+ "overfit_subset": null,
56
+ "use_gradient_checkpoint": false,
57
+ "num_workers": 2,
58
+ "pin_memory": true,
59
+ "persistent_workers": true,
60
+ "sft_mode": "lora",
61
+ "lora_r": 64,
62
+ "lora_alpha": 96,
63
+ "lora_dropout": 0.05,
64
+ "include_agent_end": true,
65
+ "include_eos": false,
66
+ "mask_user_queries": true
67
+ }
training_state.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "step": 44536,
3
+ "epoch": 2,
4
+ "time": 1761438748.4434173,
5
+ "best_loss": 0.9493680596351624
6
+ }