yuyuzhang commited on
Commit
083ad84
·
verified ·
1 Parent(s): d1acfb4

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.009882118,
12
+ "intermediate_size": 14336,
13
+ "layer_norm_eps": null,
14
+ "max_position_embeddings": 32768,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "resid_pdrop": 0.1,
21
+ "rms_norm_eps": 1e-06,
22
+ "rope_theta": 500000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.46.2",
26
+ "use_cache": true,
27
+ "vocab_size": 155136
28
+ }
cruise_cli.yaml ADDED
@@ -0,0 +1,444 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ trainer:
2
+ default_root_dir: null
3
+ default_hdfs_dir: hdfs://haruna/home/byte_data_seed/hdd_hldy/user/yuyu.zhang/seekpath/P61_D6_8B_8M_tp2_stage2_H800_code
4
+ logger:
5
+ - tracking
6
+ - console
7
+ log_every_n_steps: 50
8
+ benchmark: false
9
+ enable_speedmonitor: true
10
+ stats_speedmonitor: false
11
+ enable_versions: false
12
+ detect_anomaly: false
13
+ deterministic: false
14
+ accelerator: gpu
15
+ accelerator_kwargs:
16
+ mega_config: null
17
+ precision: bf16
18
+ max_epochs: 1
19
+ max_steps: -1
20
+ limit_train_batches: null
21
+ limit_val_batches: null
22
+ limit_test_batches: null
23
+ static_sync_limit_val: false
24
+ sync_batchnorm: false
25
+ sync_fit_metrics: null
26
+ val_check_interval:
27
+ - 20000000
28
+ save_before_val: false
29
+ accumulate_grad_batches: null
30
+ gradient_clip_val: 1.0
31
+ max_grad_clip: 0.0
32
+ seed: null
33
+ summarize_model_depth: 0
34
+ resume_ckpt_path: auto
35
+ frozen_ckpt_path: null
36
+ resume_strict: true
37
+ resume_optimizer: true
38
+ resume_metadata: true
39
+ resume_loader_state: false
40
+ callbacks: null
41
+ enable_checkpoint:
42
+ - 1
43
+ - 10000
44
+ checkpoint_monitor: step
45
+ checkpoint_mode: max
46
+ dataloader_timeout: -1
47
+ dataloader_retry_limit: 100
48
+ dataloader_retry_persistent_limit: 5
49
+ find_unused_parameters: false
50
+ project_name: seekpath_v3
51
+ experiment_name: P61_D6_8B_npu_8M_tp2_H800stage1_code
52
+ enable_trace: false
53
+ reload_dataloaders_every_n_epochs: -1
54
+ strategy: megatron
55
+ enable_qat: false
56
+ no_quant_module: []
57
+ enable_ptq: true
58
+ qat_kwargs: {}
59
+ optimizer_kwargs:
60
+ optimizer:
61
+ type: adam
62
+ params:
63
+ lr: 3.0e-05
64
+ betas:
65
+ - 0.9
66
+ - 0.95
67
+ eps: 1.0e-08
68
+ weight_decay: 0.1
69
+ bias_correction: true
70
+ adam_w_mode: true
71
+ momentum: 0.9
72
+ lr_mult_keys: []
73
+ no_weight_decay_keys: []
74
+ weight_decay_keys: []
75
+ lr_mult_start_epoch: 0
76
+ lr_mult: 1.0
77
+ scheduler:
78
+ type: megatron.optimizer_param_schedule.OptimizerParamScheduler
79
+ total_steps_param_name: num_training_steps
80
+ warmup_steps_param_name: num_warmup_steps
81
+ interval: step
82
+ params:
83
+ warmup_step_rate: 0.002
84
+ lr_end: 0.1
85
+ lr_decay_style: constant
86
+ lr_decay_rate: 1.0
87
+ grad_norm_layers: []
88
+ checkpoint_kwargs:
89
+ verbose: false
90
+ save_last: false
91
+ save_weights_only: false
92
+ every_n_train_steps: -1
93
+ every_n_seconds: -1
94
+ save_best: false
95
+ storage:
96
+ enable_shm_download: false
97
+ enable_shm_upload: false
98
+ download_thread_num: 16
99
+ upload_thread_num: 1
100
+ enable_save_checkpoint_async: true
101
+ enable_profiler: false
102
+ profiler_schedule_kwargs:
103
+ wait: 50
104
+ warmup: 3
105
+ active: 3
106
+ repeat: 1
107
+ profile_all_ranks: false
108
+ enable_bsdp: false
109
+ bsdp_num_prefetch: 64
110
+ keep_frozen_weights: true
111
+ val_reduce_fn: {}
112
+ experiment_id: null
113
+ enable_omnistore: false
114
+ model:
115
+ network:
116
+ hidden_size: 4096
117
+ n_embed: 4096
118
+ n_inner: 14336
119
+ n_head: 32
120
+ n_layer: 32
121
+ vocab_size: 155136
122
+ max_position_embeddings: 32768
123
+ cross_entropy_spilt_num: 1
124
+ layer_norm_epsilon: 1.0e-05
125
+ activation_function: gelu_new
126
+ resid_pdrop: 0.1
127
+ embd_pdrop: 0.0
128
+ attn_pdrop: 0.1
129
+ scale_attn_weights: true
130
+ scale_attn_by_inverse_layer_idx: false
131
+ reorder_and_upcast_attn: false
132
+ initializer_range: 0.009882118
133
+ gradient_checkpointing: false
134
+ gradient_checkpointing_ln: false
135
+ gradient_checkpointing_mlp: false
136
+ gradient_checkpointing_start_layers: 0
137
+ tie_weight: false
138
+ pad_idx: 1
139
+ use_ft_flash_attn: false
140
+ use_ft_linear: false
141
+ use_ft_layernorm: false
142
+ use_xperf_rotary: false
143
+ use_rmpad: true
144
+ fuse_gelu_gemm: false
145
+ pad_output: false
146
+ position_embeddings_type: rope
147
+ skip_n_iters: -1
148
+ n_shared_qhead: 4
149
+ num_q_heads: -1
150
+ num_kv_heads: -1
151
+ head_dim: -1
152
+ kv_mirror_layers: []
153
+ kv_mirror_imitated_layers: []
154
+ residual_post_ln_layers: []
155
+ hyperconnection_rate: -1
156
+ repeat_kv_heads: true
157
+ sparse_attention_window_size:
158
+ - -1
159
+ use_query_swiglu: false
160
+ query_swiglu_inner_dim: 8192
161
+ force_mem_efficient_layers:
162
+ - -1
163
+ noop_transformer_layers: []
164
+ dense_ffn_layers: []
165
+ dense_ffn_type: swiglu
166
+ dense_ffn_inner_dim: -1
167
+ moe_expert_type: exp-xelego
168
+ moe_gate_type: caplog-lego
169
+ moe_gate_metric_type: lego
170
+ moe_expert_exp_level: 4
171
+ moe_expert_exp_first_dim_factor: 1.0
172
+ moe_expert_exp_first_num: 2
173
+ moe_topk: 5
174
+ moe_num_expert: 0
175
+ moe_expert_eq_dim_factor: 0.25
176
+ moe_backend: default
177
+ moe_overlap_recomp_grad_comm: false
178
+ moe_expert_op_version: V1
179
+ moe_aux_loss_weight: 0.001
180
+ moe_gate_dropout: 0.0
181
+ moe_use_balance: false
182
+ moe_expert_group_capacity: 1.0
183
+ moe_expert_group_balance_loss_weight: 0.0
184
+ moe_expert_groups_in_ep_rank: 1
185
+ moe_enable_warmup: false
186
+ moe_swiglu_fc1_2_init_scale: 1.0
187
+ janus_use_big_op: false
188
+ janus_big_op_version: V1
189
+ janus_big_op_attn_grad_accum_fusion: true
190
+ convert_gate_to_fp32: false
191
+ moe_enable_ema_update: 1
192
+ query_head_scale_factor: 1
193
+ value_moe_num_expert: 0
194
+ value_moe_qkv_topk: 4
195
+ value_moe_qkv_times: 1
196
+ value_moe_is_repeat: true
197
+ value_moe_expert_type: linear-lego
198
+ moe_pr_scale_factor: 1.0
199
+ moe_pr_expert_type: disabled
200
+ value_moe_gate_type: default-lego
201
+ value_moe_gate_metric_type: default
202
+ lora_rank: 0
203
+ save_mixed_ckpt_in_shards: false
204
+ save_mixed_model_states_freq: final
205
+ cont_train_mode: default
206
+ fuse_lora_weight: true
207
+ rope_mode: default
208
+ rope_scale: 1
209
+ rope_base: 500000.0
210
+ rope_cut: false
211
+ rope_cut_head_dim: 0
212
+ rope_force_fp32: false
213
+ sparse_attention_window_scale: 1
214
+ sparse_attention_global_window_size:
215
+ - 0
216
+ use_attention_bias: false
217
+ layer_norm_type: rmsnorm_torch
218
+ exact_token_as_loss_denominator: false
219
+ use_key_layernorm: false
220
+ key_norm_after_rope: false
221
+ use_query_layernorm: false
222
+ use_context_groupnorm: false
223
+ use_mariana_gqa_pattern: false
224
+ use_sequence_parallel_attention: false
225
+ use_sequence_parallel_attention_a2a: false
226
+ context_parallel_use_all_gather: false
227
+ fp8_use_bf16_layers: ''
228
+ deterministic_mode: false
229
+ megatron_tensor_parallel_size: 8
230
+ megatron_pipeline_parallel_size: 1
231
+ megatron_context_parallel_size: 1
232
+ megatron_expert_parallel_size: 1
233
+ megatron_expert_parallel_size_in_dp: 1
234
+ megatron_context_parallel_query_only: false
235
+ megatron_num_layers_per_virtual_pipeline_stage: 0
236
+ megatron_micro_batch_size: 1
237
+ megatron_global_batch_size: 256
238
+ megatron_sequence_parallel: true
239
+ megatron_recompute_granularity: ''
240
+ megatron_use_flash_attention: true
241
+ megatron_recompute_method: uniform
242
+ megatron_recompute_num_layers: 1
243
+ megatron_distribute_saved_activations: false
244
+ megatron_enable_distributed_optimizer: true
245
+ megatron_use_multi_precision_ddp: false
246
+ megatron_sequence_parallel_as_data_parallel_in_optimizer: false
247
+ megatron_gather_params_use_alltoall: false
248
+ megatron_enable_initial_jit_warmup: true
249
+ megatron_accumulate_allreduce_grads_in_fp32: true
250
+ megatron_bf16_use_bf16_allreduce_grads: false
251
+ megatron_grad_comm_type: ''
252
+ megatron_reduce_grads_use_alltoall: false
253
+ megatron_scale_loss_in_gradient: false
254
+ megatron_scale_gradient_after_allreduce: false
255
+ megatron_ddp_impl: local
256
+ megatron_bf16_qt: false
257
+ megatron_empty_cache_level: 0
258
+ megatron_force_fp32_embed: false
259
+ megatron_deterministic_flash_attn: false
260
+ megatron_switch_pp_and_dp: false
261
+ megatron_timing_log_level: 2
262
+ megatron_no_load_rng: false
263
+ megatron_no_save_rng: false
264
+ megatron_no_load_optim: false
265
+ megatron_mem_efficient_column_parallel: true
266
+ megatron_masked_softmax_fusion: true
267
+ megatron_bias_gelu_fusion: false
268
+ megatron_bias_dropout_fusion: false
269
+ megatron_gradient_accumulation_fusion: true
270
+ megatron_overlap_p2p_comm: false
271
+ megatron_deallocate_pipeline_outputs: true
272
+ megatron_timing_log_option: local
273
+ megatron_barrier_with_L1_time: false
274
+ megatron_strict_align_diff_with_ds: false
275
+ megatron_parallel_linear_force_weight_contiguous: false
276
+ megatron_use_mariana_softmax: false
277
+ megatron_use_mariana_activation: false
278
+ megatron_overlap_data_parallel_communication: false
279
+ megatron_overlap_dp_grad_comm: false
280
+ megatron_overlap_dp_param_comm: false
281
+ megatron_early_prefetch_dp_allgather: true
282
+ megatron_use_non_sequential_block: false
283
+ megatron_overlap_attn_grad_input_comm: true
284
+ megatron_sequence_data_parallel_size: -1
285
+ megatron_distributed_sequence_parallel_size: -1
286
+ megatron_num_layers_for_pipeline_stages: []
287
+ megatron_vocab_parallel_embedding_fusion: false
288
+ megatron_embedding_reduce_scatter_for_sp: true
289
+ megatron_print_args: true
290
+ megatron_grad_norm_skip: -1.0
291
+ megatron_reorder_wgrad: false
292
+ megatron_offload_activations: false
293
+ megatron_offload_ratio: 1.0
294
+ megatron_offload_launch_ratio: 1.0
295
+ megatron_optimizer_offload_main_param: false
296
+ megatron_data_parallel_random_init: false
297
+ megatron_pipeline_strategy: ''
298
+ megatron_pipeline_wgrad_strategy: ''
299
+ megatron_pipeline_warmup_overlap: false
300
+ megatron_allow_transformer_engine: false
301
+ megatron_fp8_e4m3: false
302
+ megatron_fp8_hybrid: false
303
+ megatron_fp8_wgrad: true
304
+ megatron_fp8_dgrad: true
305
+ megatron_fp8_margin: 0
306
+ megatron_fp8_interval: 1
307
+ megatron_transformer_impl: local
308
+ megatron_fp8_amax_history_len: 1024
309
+ megatron_fp8_amax_compute_algo: max
310
+ megatron_use_qlora: false
311
+ megatron_qlora_quant_weight_dtype: null
312
+ megatron_qlora_quant_real_store: false
313
+ megatron_qlora_quant_groupsize: -1
314
+ megatron_qlora_quant_input_dtype: ''
315
+ megatron_qlora_quant_aware_lora: false
316
+ megatron_qlora_quant_aware_L4Q: false
317
+ megatron_terapipe_nano_batch_size: -1
318
+ lora_config:
319
+ default:
320
+ lora_dropout: 0.0
321
+ lora_rank: 64
322
+ layers:
323
+ - all
324
+ init_method: normal
325
+ init_mode: nonzero_parallel_init
326
+ init_kwargs: {}
327
+ lora_alpha: 2.0
328
+ use_rslora: true
329
+ lora_experts_appr: full
330
+ use_qlora: false
331
+ qlora_quant_weight_dtype: null
332
+ qlora_quant_real_store: false
333
+ qlora_quant_aware_L4Q: false
334
+ qlora_quant_groupsize: -1
335
+ qlora_quant_input_dtype: None
336
+ qlora_quant_aware_lora: false
337
+ post_training_quant: false
338
+ fully_sharded: false
339
+ emb_trainable: true
340
+ target_modules:
341
+ - query_key_value
342
+ - experts
343
+ - dense
344
+ query_key_value:
345
+ lora_rank: -1
346
+ lora_alpha: -1.0
347
+ experts:
348
+ lora_rank: -1
349
+ lora_alpha: -1.0
350
+ dense:
351
+ lora_rank: -1
352
+ lora_alpha: -1.0
353
+ dense_h_to_4h:
354
+ lora_rank: -1
355
+ lora_alpha: -1.0
356
+ dense_4h_to_h:
357
+ lora_rank: -1
358
+ lora_alpha: -1.0
359
+ freeze_prefix: null
360
+ partial_pretrain: null
361
+ partial_pretrain_rename: null
362
+ reset_global_step: -1
363
+ override_lr_scheduler: true
364
+ start_debug_server: false
365
+ clip_token_ids: false
366
+ data:
367
+ train_path: hdfs://haruna/home/byte_data_seed/hdd_hldy/seed_code_seekpath/pretrained_yaml_new/V1_longct_datacard_hdfs_new_stage2_code_ct_fim_2.yaml
368
+ val_path:
369
+ - hdfs://haruna/home/byte_data_seed/ssd_hldy/p0/D73_release/val/D73_val_20240507_2_200M_token_plain_source_v2_1_part
370
+ - hdfs://haruna/home/byte_data_seed/ssd_hldy/p0/D73_release/val/human_all_lite
371
+ - hdfs://haruna/home/byte_data_seed/ssd_hldy/p0/D73_release/val/autoeval_code_val_lite
372
+ - hdfs://haruna/home/byte_data_seed/ssd_hldy/p0/D73_release/val/pretrain_auto_eval_merged_all_20240412_ceval_1_part
373
+ - hdfs://haruna/home/byte_data_seed/ssd_hldy/p0/D73_release/val/merged_few_benchmark_datasets_20240705_1_part
374
+ - hdfs://haruna/home/byte_data_seed/ssd_hldy/p0/D73_release/val/pretrain_auto_eval_merged_all_v0.3_1_part
375
+ - hdfs://haruna/home/byte_data_seed/ssd_hldy/p0/D73_release/val/D74_val_20240621_200M_token_tok643_sa8192_plain_source_v2_1_part_dir
376
+ train_size: 5000000000000
377
+ val_size: -1
378
+ train_batch_size: 32
379
+ train_num_workers: 4
380
+ val_batch_size: -1
381
+ val_num_workers: 1
382
+ max_seq_len: 32768
383
+ val_max_seq_len: -1
384
+ text_keys:
385
+ - content_split
386
+ tokenizer: hdfs://haruna/home/byte_data_seed/hl_lq/seed_code/liuyongfei/tokenizers/bbpe155k-v6.4.3-ml.pret
387
+ gpu_prefetch: false
388
+ cpu_prefetch: false
389
+ dyn_bsz: true
390
+ dyn_bsz_margin: 0.0
391
+ stride: -1
392
+ warmup_step_rate: -1.0
393
+ tokenizer_type: bbpe
394
+ bsz_warmup: false
395
+ bsz_warmup_rate: 0.016
396
+ return_source: true
397
+ synthetic_sample: false
398
+ synthetic_batch: false
399
+ seq_lens: null
400
+ seq_probs: null
401
+ enable_sampling_ratios: false
402
+ train_path_with_ratio: null
403
+ src_weights: null
404
+ parse_aug_data: false
405
+ loader_accumulate: -1
406
+ bsz_warmup_warmup_step_rate: 0.002
407
+ max_epochs: 1
408
+ pad_idx: 1
409
+ strategy: megatron
410
+ megatron_micro_batch_size: 1
411
+ use_rmpad: true
412
+ hidden_size: -1
413
+ megatron_sequence_parallel: false
414
+ max_position_embeddings: 2048
415
+ position_embeddings_type: absolute
416
+ use_sequence_parallel_attention: false
417
+ use_sequence_parallel_attention_a2a: false
418
+ resume_ckpt_path: ''
419
+ val_override_est_steps: false
420
+ init_without_cli: true
421
+ rope_mode: default
422
+ rope_scale: 1
423
+ rope_base: 500000.0
424
+ rope_cut: false
425
+ rope_cut_head_dim: 0
426
+ init_val_loader_worker_beforehand: false
427
+ megatron_global_batch_size: 1
428
+ megatron_tensor_parallel_size: 1
429
+ megatron_pipeline_parallel_size: 1
430
+ n_head: 1
431
+ log_level: INFO
432
+ val_only: false
433
+ merge_model_states: false
434
+ merge_ckpt_dtype: bf16
435
+ merge_cache_dir: ./
436
+ download_ckpt_in_shards: true
437
+ gc_interval: 50
438
+ profiler_at_iter: -1
439
+ timer_at_iter: -1
440
+ profile_all_ranks: false
441
+ profile_ranks: []
442
+ profile_every_n_steps: -1
443
+ profiler_memory_at_iter: null
444
+ profile_max_preview_rank: 0
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.46.2"
6
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e936d8a183cc516c3e7bc12ba683640c6389d437fddd7a7ada1dc14b55e22320
3
+ size 4962001760
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2fabf094dcada2d9595bf7ff769b995d9d08b4a8a32035587be4653c9ab126b
3
+ size 4915916160
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b97958c5cda4cd08ca6b59ba32e2d613158805bb5c4172b4cdf207af624a5e62
3
+ size 4999819336
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfe5acfac5ac5231ce100c6a690d2d164693b91fe3d753d39aacc9e89ebbd663
3
+ size 1623221024
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16500924416
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.norm.weight": "model-00004-of-00004.safetensors"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<[BOS_never_used_51bce0c785ca2f68081bfa7d91973934]>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<[EOS_never_used_51bce0c785ca2f68081bfa7d91973934]>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<[PAD_never_used_51bce0c785ca2f68081bfa7d91973934]>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "<[SEP_never_used_51bce0c785ca2f68081bfa7d91973934]>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f5a7581f9bd555b11181c8fd69e9c7e6f6f5904d958f7c8771393aec7de1da9
3
+ size 11892194
tokenizer_config.json ADDED
@@ -0,0 +1,1036 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<[BOS_never_used_51bce0c785ca2f68081bfa7d91973934]>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<[PAD_never_used_51bce0c785ca2f68081bfa7d91973934]>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<[EOS_never_used_51bce0c785ca2f68081bfa7d91973934]>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<[UNK_never_used_51bce0c785ca2f68081bfa7d91973934]>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<[CLS_never_used_51bce0c785ca2f68081bfa7d91973934]>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<[MASK_never_used_51bce0c785ca2f68081bfa7d91973934]>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<[SEP_never_used_51bce0c785ca2f68081bfa7d91973934]>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<[PLHD7_never_used_51bce0c785ca2f68081bfa7d91973934]>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "8": {
68
+ "content": "<[PLHD8_never_used_51bce0c785ca2f68081bfa7d91973934]>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "9": {
76
+ "content": "<[PLHD9_never_used_51bce0c785ca2f68081bfa7d91973934]>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "10": {
84
+ "content": "<[PLHD10_never_used_51bce0c785ca2f68081bfa7d91973934]>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "11": {
92
+ "content": "<[PLHD11_never_used_51bce0c785ca2f68081bfa7d91973934]>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "12": {
100
+ "content": "<[PLHD12_never_used_51bce0c785ca2f68081bfa7d91973934]>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "13": {
108
+ "content": "<[PLHD13_never_used_51bce0c785ca2f68081bfa7d91973934]>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "14": {
116
+ "content": "<[PLHD14_never_used_51bce0c785ca2f68081bfa7d91973934]>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "15": {
124
+ "content": "<[PLHD15_never_used_51bce0c785ca2f68081bfa7d91973934]>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "16": {
132
+ "content": "<[PLHD16_never_used_51bce0c785ca2f68081bfa7d91973934]>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "17": {
140
+ "content": "<[PLHD17_never_used_51bce0c785ca2f68081bfa7d91973934]>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "18": {
148
+ "content": "<[PLHD18_never_used_51bce0c785ca2f68081bfa7d91973934]>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "19": {
156
+ "content": "<[PLHD19_never_used_51bce0c785ca2f68081bfa7d91973934]>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "20": {
164
+ "content": "<[PLHD20_never_used_51bce0c785ca2f68081bfa7d91973934]>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "21": {
172
+ "content": "<[PLHD21_never_used_51bce0c785ca2f68081bfa7d91973934]>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "22": {
180
+ "content": "<[PLHD22_never_used_51bce0c785ca2f68081bfa7d91973934]>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "23": {
188
+ "content": "<[PLHD23_never_used_51bce0c785ca2f68081bfa7d91973934]>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "24": {
196
+ "content": "<[PLHD24_never_used_51bce0c785ca2f68081bfa7d91973934]>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "25": {
204
+ "content": "<[PLHD25_never_used_51bce0c785ca2f68081bfa7d91973934]>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "26": {
212
+ "content": "<[PLHD26_never_used_51bce0c785ca2f68081bfa7d91973934]>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "27": {
220
+ "content": "<[PLHD27_never_used_51bce0c785ca2f68081bfa7d91973934]>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "28": {
228
+ "content": "<[PLHD28_never_used_51bce0c785ca2f68081bfa7d91973934]>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "29": {
236
+ "content": "<[PLHD29_never_used_51bce0c785ca2f68081bfa7d91973934]>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "30": {
244
+ "content": "<[PLHD30_never_used_51bce0c785ca2f68081bfa7d91973934]>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "31": {
252
+ "content": "<[PLHD31_never_used_51bce0c785ca2f68081bfa7d91973934]>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "32": {
260
+ "content": "<[PLHD32_never_used_51bce0c785ca2f68081bfa7d91973934]>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "33": {
268
+ "content": "<[PLHD33_never_used_51bce0c785ca2f68081bfa7d91973934]>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "34": {
276
+ "content": "<[PLHD34_never_used_51bce0c785ca2f68081bfa7d91973934]>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "35": {
284
+ "content": "<[PLHD35_never_used_51bce0c785ca2f68081bfa7d91973934]>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "36": {
292
+ "content": "<[PLHD36_never_used_51bce0c785ca2f68081bfa7d91973934]>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "37": {
300
+ "content": "<[PLHD37_never_used_51bce0c785ca2f68081bfa7d91973934]>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "38": {
308
+ "content": "<[PLHD38_never_used_51bce0c785ca2f68081bfa7d91973934]>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "39": {
316
+ "content": "<[PLHD39_never_used_51bce0c785ca2f68081bfa7d91973934]>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "40": {
324
+ "content": "<[PLHD40_never_used_51bce0c785ca2f68081bfa7d91973934]>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "41": {
332
+ "content": "<[PLHD41_never_used_51bce0c785ca2f68081bfa7d91973934]>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "42": {
340
+ "content": "<[PLHD42_never_used_51bce0c785ca2f68081bfa7d91973934]>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "43": {
348
+ "content": "<[PLHD43_never_used_51bce0c785ca2f68081bfa7d91973934]>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "44": {
356
+ "content": "<[PLHD44_never_used_51bce0c785ca2f68081bfa7d91973934]>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "45": {
364
+ "content": "<[PLHD45_never_used_51bce0c785ca2f68081bfa7d91973934]>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "46": {
372
+ "content": "<[PLHD46_never_used_51bce0c785ca2f68081bfa7d91973934]>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "47": {
380
+ "content": "<[PLHD47_never_used_51bce0c785ca2f68081bfa7d91973934]>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "48": {
388
+ "content": "<[PLHD48_never_used_51bce0c785ca2f68081bfa7d91973934]>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "49": {
396
+ "content": "<[PLHD49_never_used_51bce0c785ca2f68081bfa7d91973934]>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "50": {
404
+ "content": "<[PLHD50_never_used_51bce0c785ca2f68081bfa7d91973934]>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "51": {
412
+ "content": "<[PLHD51_never_used_51bce0c785ca2f68081bfa7d91973934]>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "52": {
420
+ "content": "<[PLHD52_never_used_51bce0c785ca2f68081bfa7d91973934]>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "53": {
428
+ "content": "<[PLHD53_never_used_51bce0c785ca2f68081bfa7d91973934]>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "54": {
436
+ "content": "<[PLHD54_never_used_51bce0c785ca2f68081bfa7d91973934]>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "55": {
444
+ "content": "<[PLHD55_never_used_51bce0c785ca2f68081bfa7d91973934]>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "56": {
452
+ "content": "<[PLHD56_never_used_51bce0c785ca2f68081bfa7d91973934]>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "57": {
460
+ "content": "<[PLHD57_never_used_51bce0c785ca2f68081bfa7d91973934]>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "58": {
468
+ "content": "<[PLHD58_never_used_51bce0c785ca2f68081bfa7d91973934]>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "59": {
476
+ "content": "<[PLHD59_never_used_51bce0c785ca2f68081bfa7d91973934]>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "60": {
484
+ "content": "<[PLHD60_never_used_51bce0c785ca2f68081bfa7d91973934]>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "61": {
492
+ "content": "<[PLHD61_never_used_51bce0c785ca2f68081bfa7d91973934]>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "62": {
500
+ "content": "<[PLHD62_never_used_51bce0c785ca2f68081bfa7d91973934]>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "63": {
508
+ "content": "<[PLHD63_never_used_51bce0c785ca2f68081bfa7d91973934]>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "64": {
516
+ "content": "<[PLHD64_never_used_51bce0c785ca2f68081bfa7d91973934]>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "65": {
524
+ "content": "<[PLHD65_never_used_51bce0c785ca2f68081bfa7d91973934]>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "66": {
532
+ "content": "<[PLHD66_never_used_51bce0c785ca2f68081bfa7d91973934]>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "67": {
540
+ "content": "<[PLHD67_never_used_51bce0c785ca2f68081bfa7d91973934]>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "68": {
548
+ "content": "<[PLHD68_never_used_51bce0c785ca2f68081bfa7d91973934]>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "69": {
556
+ "content": "<[PLHD69_never_used_51bce0c785ca2f68081bfa7d91973934]>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "70": {
564
+ "content": "<[PLHD70_never_used_51bce0c785ca2f68081bfa7d91973934]>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "71": {
572
+ "content": "<[PLHD71_never_used_51bce0c785ca2f68081bfa7d91973934]>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "72": {
580
+ "content": "<[PLHD72_never_used_51bce0c785ca2f68081bfa7d91973934]>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "73": {
588
+ "content": "<[PLHD73_never_used_51bce0c785ca2f68081bfa7d91973934]>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "74": {
596
+ "content": "<[PLHD74_never_used_51bce0c785ca2f68081bfa7d91973934]>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "75": {
604
+ "content": "<[PLHD75_never_used_51bce0c785ca2f68081bfa7d91973934]>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "76": {
612
+ "content": "<[PLHD76_never_used_51bce0c785ca2f68081bfa7d91973934]>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "77": {
620
+ "content": "<[PLHD77_never_used_51bce0c785ca2f68081bfa7d91973934]>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "78": {
628
+ "content": "<[PLHD78_never_used_51bce0c785ca2f68081bfa7d91973934]>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "79": {
636
+ "content": "<[PLHD79_never_used_51bce0c785ca2f68081bfa7d91973934]>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "80": {
644
+ "content": "<[PLHD80_never_used_51bce0c785ca2f68081bfa7d91973934]>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "81": {
652
+ "content": "<[PLHD81_never_used_51bce0c785ca2f68081bfa7d91973934]>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "82": {
660
+ "content": "<[PLHD82_never_used_51bce0c785ca2f68081bfa7d91973934]>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "83": {
668
+ "content": "<[PLHD83_never_used_51bce0c785ca2f68081bfa7d91973934]>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "84": {
676
+ "content": "<[PLHD84_never_used_51bce0c785ca2f68081bfa7d91973934]>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "85": {
684
+ "content": "<[PLHD85_never_used_51bce0c785ca2f68081bfa7d91973934]>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "86": {
692
+ "content": "<[PLHD86_never_used_51bce0c785ca2f68081bfa7d91973934]>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "87": {
700
+ "content": "<[PLHD87_never_used_51bce0c785ca2f68081bfa7d91973934]>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "88": {
708
+ "content": "<[PLHD88_never_used_51bce0c785ca2f68081bfa7d91973934]>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "89": {
716
+ "content": "<[PLHD89_never_used_51bce0c785ca2f68081bfa7d91973934]>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "90": {
724
+ "content": "<[PLHD90_never_used_51bce0c785ca2f68081bfa7d91973934]>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "91": {
732
+ "content": "<[PLHD91_never_used_51bce0c785ca2f68081bfa7d91973934]>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "92": {
740
+ "content": "<[PLHD92_never_used_51bce0c785ca2f68081bfa7d91973934]>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "93": {
748
+ "content": "<[PLHD93_never_used_51bce0c785ca2f68081bfa7d91973934]>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "94": {
756
+ "content": "<[PLHD94_never_used_51bce0c785ca2f68081bfa7d91973934]>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "95": {
764
+ "content": "<[PLHD95_never_used_51bce0c785ca2f68081bfa7d91973934]>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "96": {
772
+ "content": "<[PLHD96_never_used_51bce0c785ca2f68081bfa7d91973934]>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "97": {
780
+ "content": "<[PLHD97_never_used_51bce0c785ca2f68081bfa7d91973934]>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "98": {
788
+ "content": "<[PLHD98_never_used_51bce0c785ca2f68081bfa7d91973934]>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "99": {
796
+ "content": "<[PLHD99_never_used_51bce0c785ca2f68081bfa7d91973934]>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "100": {
804
+ "content": "<[PLHD100_never_used_51bce0c785ca2f68081bfa7d91973934]>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "101": {
812
+ "content": "<[PLHD101_never_used_51bce0c785ca2f68081bfa7d91973934]>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "102": {
820
+ "content": "<[PLHD102_never_used_51bce0c785ca2f68081bfa7d91973934]>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "103": {
828
+ "content": "<[PLHD103_never_used_51bce0c785ca2f68081bfa7d91973934]>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "104": {
836
+ "content": "<[PLHD104_never_used_51bce0c785ca2f68081bfa7d91973934]>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "105": {
844
+ "content": "<[PLHD105_never_used_51bce0c785ca2f68081bfa7d91973934]>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "106": {
852
+ "content": "<[PLHD106_never_used_51bce0c785ca2f68081bfa7d91973934]>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "107": {
860
+ "content": "<[PLHD107_never_used_51bce0c785ca2f68081bfa7d91973934]>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "108": {
868
+ "content": "<[PLHD108_never_used_51bce0c785ca2f68081bfa7d91973934]>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "109": {
876
+ "content": "<[PLHD109_never_used_51bce0c785ca2f68081bfa7d91973934]>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "110": {
884
+ "content": "<[PLHD110_never_used_51bce0c785ca2f68081bfa7d91973934]>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "111": {
892
+ "content": "<[PLHD111_never_used_51bce0c785ca2f68081bfa7d91973934]>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "112": {
900
+ "content": "<[PLHD112_never_used_51bce0c785ca2f68081bfa7d91973934]>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "113": {
908
+ "content": "<[PLHD113_never_used_51bce0c785ca2f68081bfa7d91973934]>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "114": {
916
+ "content": "<[PLHD114_never_used_51bce0c785ca2f68081bfa7d91973934]>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "115": {
924
+ "content": "<[PLHD115_never_used_51bce0c785ca2f68081bfa7d91973934]>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "116": {
932
+ "content": "<[PLHD116_never_used_51bce0c785ca2f68081bfa7d91973934]>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "117": {
940
+ "content": "<[PLHD117_never_used_51bce0c785ca2f68081bfa7d91973934]>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "118": {
948
+ "content": "<[PLHD118_never_used_51bce0c785ca2f68081bfa7d91973934]>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "119": {
956
+ "content": "<[PLHD119_never_used_51bce0c785ca2f68081bfa7d91973934]>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "120": {
964
+ "content": "<[PLHD120_never_used_51bce0c785ca2f68081bfa7d91973934]>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "121": {
972
+ "content": "<[PLHD121_never_used_51bce0c785ca2f68081bfa7d91973934]>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "122": {
980
+ "content": "<[PLHD122_never_used_51bce0c785ca2f68081bfa7d91973934]>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "123": {
988
+ "content": "<[PLHD123_never_used_51bce0c785ca2f68081bfa7d91973934]>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "124": {
996
+ "content": "<[PLHD124_never_used_51bce0c785ca2f68081bfa7d91973934]>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "125": {
1004
+ "content": "<[PLHD125_never_used_51bce0c785ca2f68081bfa7d91973934]>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "126": {
1012
+ "content": "<[PLHD126_never_used_51bce0c785ca2f68081bfa7d91973934]>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "127": {
1020
+ "content": "<[PLHD127_never_used_51bce0c785ca2f68081bfa7d91973934]>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ }
1027
+ },
1028
+ "bos_token": "<[BOS_never_used_51bce0c785ca2f68081bfa7d91973934]>",
1029
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% set role = message['role'] %}{{ bos_token + role + '\n' + message['content'] | trim + eos_token }}{% endfor %}{% if add_generation_prompt %}{{ bos_token + 'assistant\n'}}{% endif %}",
1030
+ "clean_up_tokenization_spaces": false,
1031
+ "eos_token": "<[EOS_never_used_51bce0c785ca2f68081bfa7d91973934]>",
1032
+ "model_max_length": 1000000000000000019884624838656,
1033
+ "pad_token": "<[PAD_never_used_51bce0c785ca2f68081bfa7d91973934]>",
1034
+ "sep_token": "<[SEP_never_used_51bce0c785ca2f68081bfa7d91973934]>",
1035
+ "tokenizer_class": "PreTrainedTokenizerFast"
1036
+ }