Dan-Carter commited on
Commit
8509fc6
·
verified ·
1 Parent(s): 819beec

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
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
args.json ADDED
@@ -0,0 +1,465 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "Qwen3-32B",
3
+ "model_type": "qwen3",
4
+ "model_revision": null,
5
+ "task_type": "causal_lm",
6
+ "torch_dtype": "bfloat16",
7
+ "attn_impl": null,
8
+ "new_special_tokens": [],
9
+ "num_labels": null,
10
+ "problem_type": null,
11
+ "rope_scaling": null,
12
+ "device_map": null,
13
+ "max_memory": {},
14
+ "max_model_len": null,
15
+ "local_repo_path": null,
16
+ "init_strategy": null,
17
+ "template": "qwen3_thinking",
18
+ "system": null,
19
+ "max_length": 8192,
20
+ "truncation_strategy": "delete",
21
+ "max_pixels": null,
22
+ "agent_template": null,
23
+ "norm_bbox": null,
24
+ "use_chat_template": true,
25
+ "padding_free": true,
26
+ "padding_side": "right",
27
+ "loss_scale": "default",
28
+ "sequence_parallel_size": 1,
29
+ "response_prefix": null,
30
+ "template_backend": "swift",
31
+ "dataset": [
32
+ "my_data/total_mixed_loss.jsonl"
33
+ ],
34
+ "val_dataset": [
35
+ "my_data/100.jsonl"
36
+ ],
37
+ "split_dataset_ratio": 0.0,
38
+ "data_seed": 42,
39
+ "dataset_num_proc": 8,
40
+ "load_from_cache_file": false,
41
+ "dataset_shuffle": true,
42
+ "val_dataset_shuffle": false,
43
+ "streaming": false,
44
+ "interleave_prob": null,
45
+ "stopping_strategy": "first_exhausted",
46
+ "shuffle_buffer_size": 1000,
47
+ "download_mode": "reuse_dataset_if_exists",
48
+ "columns": {},
49
+ "strict": false,
50
+ "remove_unused_columns": true,
51
+ "model_name": null,
52
+ "model_author": null,
53
+ "custom_dataset_info": [],
54
+ "quant_method": null,
55
+ "quant_bits": null,
56
+ "hqq_axis": null,
57
+ "bnb_4bit_compute_dtype": "bfloat16",
58
+ "bnb_4bit_quant_type": "nf4",
59
+ "bnb_4bit_use_double_quant": true,
60
+ "bnb_4bit_quant_storage": null,
61
+ "max_new_tokens": null,
62
+ "temperature": null,
63
+ "top_k": null,
64
+ "top_p": null,
65
+ "repetition_penalty": null,
66
+ "num_beams": 1,
67
+ "stream": false,
68
+ "stop_words": [],
69
+ "logprobs": false,
70
+ "top_logprobs": null,
71
+ "ckpt_dir": "/workspace/Qwen3-32B-mcore",
72
+ "lora_modules": [],
73
+ "tuner_backend": "peft",
74
+ "train_type": "full",
75
+ "adapters": [],
76
+ "external_plugins": [],
77
+ "seed": 42,
78
+ "model_kwargs": {},
79
+ "load_args": false,
80
+ "load_data_args": false,
81
+ "packing": false,
82
+ "packing_length": null,
83
+ "lazy_tokenize": false,
84
+ "cached_dataset": [],
85
+ "custom_register_path": [],
86
+ "use_hf": false,
87
+ "hub_token": null,
88
+ "ddp_timeout": 18000000,
89
+ "ddp_backend": null,
90
+ "ignore_args_error": false,
91
+ "use_swift_lora": false,
92
+ "freeze_llm": false,
93
+ "freeze_vit": true,
94
+ "freeze_aligner": true,
95
+ "freeze_parameters": [],
96
+ "freeze_parameters_regex": null,
97
+ "freeze_parameters_ratio": 0.0,
98
+ "trainable_parameters": [],
99
+ "trainable_parameters_regex": null,
100
+ "adapter_load": null,
101
+ "target_modules": [
102
+ "all-linear"
103
+ ],
104
+ "target_regex": null,
105
+ "modules_to_save": [],
106
+ "lora_rank": 8,
107
+ "lora_alpha": 32,
108
+ "lora_dropout": 0.05,
109
+ "lora_bias": "none",
110
+ "lora_dtype": null,
111
+ "use_rslora": false,
112
+ "rlhf_type": null,
113
+ "ref_load": null,
114
+ "ref_adapter_load": null,
115
+ "beta": 0.1,
116
+ "rpo_alpha": null,
117
+ "reference_free": false,
118
+ "label_smoothing": 0.0,
119
+ "f_divergence_type": "reverse_kl",
120
+ "loss_type": null,
121
+ "desirable_weight": 1.0,
122
+ "undesirable_weight": 1.0,
123
+ "calculate_KL": null,
124
+ "center_rewards_coefficient": null,
125
+ "padded_vocab_size": 151936,
126
+ "initialize_embedding": false,
127
+ "mlp_padding_free": false,
128
+ "dataloader_persistent_workers": true,
129
+ "dataloader_prefetch_factor": 10,
130
+ "architectures": "Qwen3ForCausalLM",
131
+ "llm_architectures": null,
132
+ "max_epochs": 4,
133
+ "enable_dft_loss": false,
134
+ "enable_channel_loss": false,
135
+ "original_max_position_embeddings": null,
136
+ "partial_rotary_factor": null,
137
+ "use_shared_expert_gate": false,
138
+ "vit_gradient_checkpointing": true,
139
+ "gradient_checkpointing_kwargs": null,
140
+ "linear_num_value_heads": null,
141
+ "linear_num_key_heads": null,
142
+ "linear_key_head_dim": null,
143
+ "linear_value_head_dim": null,
144
+ "linear_conv_kernel_dim": null,
145
+ "layer_types": null,
146
+ "mrope_interleaved": false,
147
+ "micro_batch_size": 8,
148
+ "global_batch_size": 256,
149
+ "recompute_granularity": "full",
150
+ "recompute_method": "block",
151
+ "recompute_num_layers": 36,
152
+ "recompute_modules": [
153
+ "core_attn"
154
+ ],
155
+ "use_cpu_initialization": false,
156
+ "deterministic_mode": false,
157
+ "train_iters": null,
158
+ "log_interval": 1,
159
+ "tensorboard_dir": "/workspace/my_model/v0-20251109-230125/runs",
160
+ "no_masked_softmax_fusion": false,
161
+ "no_bias_dropout_fusion": false,
162
+ "no_bias_swiglu_fusion": false,
163
+ "no_rope_fusion": false,
164
+ "no_gradient_accumulation_fusion": false,
165
+ "cross_entropy_loss_fusion": true,
166
+ "cross_entropy_fusion_impl": "native",
167
+ "calculate_per_token_loss": true,
168
+ "use_flash_attn": false,
169
+ "attention_backend": "flash",
170
+ "optimizer": "adam",
171
+ "optimizer_cpu_offload": false,
172
+ "optimizer_offload_fraction": 1.0,
173
+ "use_precision_aware_optimizer": true,
174
+ "main_grads_dtype": "bf16",
175
+ "main_params_dtype": "fp32",
176
+ "exp_avg_dtype": "bf16",
177
+ "exp_avg_sq_dtype": "bf16",
178
+ "dataloader_type": "cyclic",
179
+ "manual_gc": false,
180
+ "manual_gc_interval": 0,
181
+ "lr": 1e-05,
182
+ "lr_decay_style": "cosine",
183
+ "lr_decay_iters": null,
184
+ "lr_warmup_iters": 0,
185
+ "lr_warmup_fraction": 0.01,
186
+ "min_lr": 2e-06,
187
+ "weight_decay": 0.1,
188
+ "clip_grad": 1.0,
189
+ "adam_beta1": 0.9,
190
+ "adam_beta2": 0.95,
191
+ "adam_eps": 1e-08,
192
+ "sgd_momentum": 0.9,
193
+ "save": "/workspace/my_model/v0-20251109-230125",
194
+ "save_interval": 2070,
195
+ "save_retain_interval": null,
196
+ "no_save_optim": true,
197
+ "no_save_rng": true,
198
+ "load": "/workspace/Qwen3-32B-mcore",
199
+ "no_load_optim": false,
200
+ "no_load_rng": false,
201
+ "finetune": true,
202
+ "ckpt_format": "torch_dist",
203
+ "no_initialization": true,
204
+ "auto_detect_ckpt_format": true,
205
+ "exit_on_missing_checkpoint": true,
206
+ "async_save": false,
207
+ "use_persistent_ckpt_worker": false,
208
+ "ckpt_fully_parallel_load": false,
209
+ "ckpt_assume_constant_structure": false,
210
+ "distributed_backend": "nccl",
211
+ "local_rank": 0,
212
+ "use_distributed_optimizer": true,
213
+ "tensor_model_parallel_size": 8,
214
+ "pipeline_model_parallel_size": 1,
215
+ "decoder_first_pipeline_num_layers": null,
216
+ "decoder_last_pipeline_num_layers": null,
217
+ "sequence_parallel": true,
218
+ "context_parallel_size": 1,
219
+ "tp_comm_overlap": false,
220
+ "overlap_grad_reduce": false,
221
+ "overlap_param_gather": false,
222
+ "distributed_timeout_minutes": 300000,
223
+ "num_layers_per_virtual_pipeline_stage": null,
224
+ "num_virtual_stages_per_pipeline_rank": null,
225
+ "microbatch_group_size_per_virtual_pipeline_stage": null,
226
+ "pipeline_model_parallel_layout": null,
227
+ "num_layers": 64,
228
+ "hidden_size": 5120,
229
+ "ffn_hidden_size": 25600,
230
+ "num_attention_heads": 64,
231
+ "group_query_attention": true,
232
+ "num_query_groups": 8,
233
+ "max_position_embeddings": 40960,
234
+ "position_embedding_type": "rope",
235
+ "mrope_section": null,
236
+ "rotary_base": 1000000,
237
+ "rotary_percent": 1.0,
238
+ "rotary_interleaved": false,
239
+ "normalization": "RMSNorm",
240
+ "norm_epsilon": 1e-06,
241
+ "swiglu": true,
242
+ "untie_embeddings_and_output_weights": true,
243
+ "disable_bias_linear": true,
244
+ "add_qkv_bias": false,
245
+ "attention_dropout": 0.0,
246
+ "hidden_dropout": 0.0,
247
+ "kv_channels": 128,
248
+ "qk_layernorm": true,
249
+ "transformer_impl": "transformer_engine",
250
+ "num_experts": null,
251
+ "moe_layer_freq": "1",
252
+ "moe_ffn_hidden_size": null,
253
+ "moe_shared_expert_intermediate_size": null,
254
+ "moe_router_topk": 2,
255
+ "moe_router_pre_softmax": false,
256
+ "moe_router_dtype": "fp32",
257
+ "moe_router_score_function": "softmax",
258
+ "moe_router_bias_update_rate": 0.001,
259
+ "moe_router_enable_expert_bias": false,
260
+ "moe_router_topk_scaling_factor": null,
261
+ "moe_router_load_balancing_type": "aux_loss",
262
+ "expert_model_parallel_size": 1,
263
+ "expert_tensor_parallel_size": 1,
264
+ "moe_token_dispatcher_type": null,
265
+ "moe_enable_deepep": false,
266
+ "moe_grouped_gemm": false,
267
+ "moe_permute_fusion": false,
268
+ "moe_aux_loss_coeff": 0.0,
269
+ "moe_z_loss_coeff": null,
270
+ "moe_shared_expert_overlap": false,
271
+ "moe_layer_recompute": false,
272
+ "moe_expert_capacity_factor": null,
273
+ "moe_pad_expert_input_to_capacity": false,
274
+ "moe_token_drop_policy": null,
275
+ "multi_latent_attention": false,
276
+ "q_lora_rank": null,
277
+ "kv_lora_rank": 32,
278
+ "qk_head_dim": 128,
279
+ "qk_pos_emb_head_dim": 64,
280
+ "fp8_format": null,
281
+ "fp8_recipe": "delayed",
282
+ "fp8_amax_history_len": 1024,
283
+ "fp8_amax_compute_algo": "max",
284
+ "fp8_param_gather": false,
285
+ "fp16": false,
286
+ "bf16": true,
287
+ "apply_query_key_layer_scaling": false,
288
+ "attention_softmax_in_fp32": true,
289
+ "log_params_norm": false,
290
+ "log_throughput": false,
291
+ "tensorboard_log_interval": 1,
292
+ "tensorboard_queue_size": 50,
293
+ "log_timers_to_tensorboard": true,
294
+ "no_log_learning_rate_to_tensorboard": false,
295
+ "log_validation_ppl_to_tensorboard": true,
296
+ "log_memory_to_tensorboard": true,
297
+ "logging_level": null,
298
+ "wandb_project": "my_affine",
299
+ "wandb_exp_name": "qwen_32b_mixed",
300
+ "wandb_save_dir": null,
301
+ "eval_iters": -1,
302
+ "eval_interval": 10000000,
303
+ "seq_length": 8192,
304
+ "num_workers": 8,
305
+ "extra_megatron_kwargs": {},
306
+ "add_version": true,
307
+ "rank": 0,
308
+ "global_world_size": 8,
309
+ "local_world_size": 8,
310
+ "model_suffix": "Qwen3-32B",
311
+ "model_info": "ModelInfo(model_type='qwen3', model_dir='/workspace/Qwen3-32B', torch_dtype=torch.bfloat16, max_model_len=40960, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, config=None, task_type='causal_lm', num_labels=None)",
312
+ "model_meta": "ModelMeta(model_type='qwen3', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-0.6B-Base', hf_model_id='Qwen/Qwen3-0.6B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B-Base', hf_model_id='Qwen/Qwen3-1.7B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-Base', hf_model_id='Qwen/Qwen3-4B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-Base', hf_model_id='Qwen/Qwen3-8B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-Base', hf_model_id='Qwen/Qwen3-14B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-0.6B', hf_model_id='Qwen/Qwen3-0.6B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B', hf_model_id='Qwen/Qwen3-1.7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B', hf_model_id='Qwen/Qwen3-4B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B', hf_model_id='Qwen/Qwen3-8B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B', hf_model_id='Qwen/Qwen3-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B', hf_model_id='Qwen/Qwen3-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-0.6B-FP8', hf_model_id='Qwen/Qwen3-0.6B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B-FP8', hf_model_id='Qwen/Qwen3-1.7B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-FP8', hf_model_id='Qwen/Qwen3-4B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-FP8', hf_model_id='Qwen/Qwen3-8B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-FP8', hf_model_id='Qwen/Qwen3-14B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B-FP8', hf_model_id='Qwen/Qwen3-32B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-AWQ', hf_model_id='Qwen/Qwen3-4B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-AWQ', hf_model_id='Qwen/Qwen3-8B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-AWQ', hf_model_id='Qwen/Qwen3-14B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B-AWQ', hf_model_id='Qwen/Qwen3-32B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='swift/Qwen3-32B-AWQ', hf_model_id=None, model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen3', get_function=<function get_model_tokenizer_with_flash_attn at 0x70b3aa6eb880>, model_arch=ModelKeys(arch_name='llama', embedding='model.embed_tokens', module_list='model.layers', lm_head='lm_head', q_proj='model.layers.{}.self_attn.q_proj', k_proj='model.layers.{}.self_attn.k_proj', v_proj='model.layers.{}.self_attn.v_proj', o_proj='model.layers.{}.self_attn.o_proj', attention='model.layers.{}.self_attn', mlp='model.layers.{}.mlp', down_proj='model.layers.{}.mlp.down_proj', qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None), architectures=['Qwen3ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.51'], tags=[])",
313
+ "model_dir": "/workspace/Qwen3-32B",
314
+ "hub": "<class 'swift.hub.hub.MSHub'>",
315
+ "megatron_model_meta": "MegatronModelMeta(megatron_model_type='gpt', model_types=['qwen2', 'qwen2_5', 'qwq', 'qwq_preview', 'qwen2_5_math', 'llama', 'llama3', 'llama3_1', 'llama3_2', 'longwriter_llama3_1', 'codefuse_codellama', 'marco_o1', 'deepseek', 'deepseek_r1_distill', 'yi', 'yi_coder', 'sus', 'skywork_o1', 'openbuddy_llama', 'openbuddy_llama3', 'megrez', 'reflection', 'numina', 'ziya', 'mengzi3', 'qwen3', 'qwen3_thinking', 'qwen3_nothinking', 'qwen2_moe', 'qwen3_moe', 'qwen3_moe_thinking', 'qwen3_coder', 'internlm3', 'mimo', 'mimo_rl', 'moonlight', 'deepseek_moe', 'deepseek_v2', 'deepseek_v2_5', 'deepseek_r1', 'dots1', 'ernie', 'glm4_5', 'deepseek_v3_1', 'ernie_thinking'], convert_mcore2hf=<function convert_mcore2hf at 0x70b313552de0>, convert_hf2mcore=<function convert_hf2mcore at 0x70b3135528e0>, model_cls=<class 'swift.megatron.model.gpt_model.GPTModel'>, convert_hf_config=<function convert_gpt_hf_config at 0x70b31372e660>, get_transformer_layer_spec=None, model_provider=<function model_provider at 0x70b31372d300>, visual_cls=None, extra_args_provider=None)",
316
+ "extra_args": {
317
+ "model": "Qwen3-32B",
318
+ "model_type": "qwen3",
319
+ "model_revision": null,
320
+ "task_type": "causal_lm",
321
+ "torch_dtype": "bfloat16",
322
+ "attn_impl": null,
323
+ "new_special_tokens": [],
324
+ "num_labels": null,
325
+ "problem_type": null,
326
+ "rope_scaling": null,
327
+ "device_map": null,
328
+ "max_memory": {},
329
+ "max_model_len": null,
330
+ "local_repo_path": null,
331
+ "init_strategy": null,
332
+ "template": "qwen3_thinking",
333
+ "system": null,
334
+ "max_length": 8192,
335
+ "truncation_strategy": "delete",
336
+ "max_pixels": null,
337
+ "agent_template": null,
338
+ "norm_bbox": null,
339
+ "use_chat_template": true,
340
+ "padding_free": true,
341
+ "padding_side": "right",
342
+ "sequence_parallel_size": 1,
343
+ "response_prefix": null,
344
+ "template_backend": "swift",
345
+ "dataset": [
346
+ "my_data/total_mixed_loss.jsonl"
347
+ ],
348
+ "val_dataset": [
349
+ "my_data/100.jsonl"
350
+ ],
351
+ "split_dataset_ratio": 0.0,
352
+ "data_seed": 42,
353
+ "dataset_num_proc": 8,
354
+ "load_from_cache_file": false,
355
+ "dataset_shuffle": true,
356
+ "val_dataset_shuffle": false,
357
+ "streaming": false,
358
+ "interleave_prob": null,
359
+ "stopping_strategy": "first_exhausted",
360
+ "shuffle_buffer_size": 1000,
361
+ "download_mode": "reuse_dataset_if_exists",
362
+ "columns": {},
363
+ "strict": false,
364
+ "remove_unused_columns": true,
365
+ "model_name": null,
366
+ "model_author": null,
367
+ "custom_dataset_info": [],
368
+ "quant_method": null,
369
+ "quant_bits": null,
370
+ "hqq_axis": null,
371
+ "bnb_4bit_compute_dtype": "bfloat16",
372
+ "bnb_4bit_quant_type": "nf4",
373
+ "bnb_4bit_use_double_quant": true,
374
+ "bnb_4bit_quant_storage": null,
375
+ "max_new_tokens": null,
376
+ "temperature": null,
377
+ "top_k": null,
378
+ "top_p": null,
379
+ "repetition_penalty": null,
380
+ "num_beams": 1,
381
+ "stream": false,
382
+ "stop_words": [],
383
+ "logprobs": false,
384
+ "top_logprobs": null,
385
+ "ckpt_dir": "/workspace/Qwen3-32B-mcore",
386
+ "lora_modules": [],
387
+ "tuner_backend": "peft",
388
+ "train_type": "full",
389
+ "adapters": [],
390
+ "external_plugins": [],
391
+ "model_kwargs": {},
392
+ "load_args": false,
393
+ "load_data_args": false,
394
+ "packing": false,
395
+ "packing_length": null,
396
+ "lazy_tokenize": false,
397
+ "cached_dataset": [],
398
+ "custom_register_path": [],
399
+ "use_hf": false,
400
+ "hub_token": null,
401
+ "ddp_timeout": 18000000,
402
+ "ddp_backend": null,
403
+ "ignore_args_error": false,
404
+ "use_swift_lora": false,
405
+ "freeze_llm": false,
406
+ "freeze_vit": true,
407
+ "freeze_aligner": true,
408
+ "freeze_parameters": [],
409
+ "freeze_parameters_regex": null,
410
+ "freeze_parameters_ratio": 0.0,
411
+ "trainable_parameters": [],
412
+ "trainable_parameters_regex": null,
413
+ "adapter_load": null,
414
+ "target_modules": [
415
+ "all-linear"
416
+ ],
417
+ "target_regex": null,
418
+ "modules_to_save": [],
419
+ "lora_rank": 8,
420
+ "lora_alpha": 32,
421
+ "lora_dropout": 0.05,
422
+ "lora_bias": "none",
423
+ "lora_dtype": null,
424
+ "use_rslora": false,
425
+ "rlhf_type": null,
426
+ "ref_load": null,
427
+ "ref_adapter_load": null,
428
+ "beta": 0.1,
429
+ "rpo_alpha": null,
430
+ "reference_free": false,
431
+ "label_smoothing": 0.0,
432
+ "f_divergence_type": "reverse_kl",
433
+ "loss_type": null,
434
+ "desirable_weight": 1.0,
435
+ "undesirable_weight": 1.0,
436
+ "calculate_KL": null,
437
+ "center_rewards_coefficient": null,
438
+ "padded_vocab_size": 151936,
439
+ "initialize_embedding": false,
440
+ "mlp_padding_free": false,
441
+ "dataloader_persistent_workers": true,
442
+ "dataloader_prefetch_factor": 10,
443
+ "architectures": "Qwen3ForCausalLM",
444
+ "llm_architectures": null,
445
+ "max_epochs": 4,
446
+ "enable_dft_loss": false,
447
+ "enable_channel_loss": false,
448
+ "original_max_position_embeddings": null,
449
+ "partial_rotary_factor": null,
450
+ "use_shared_expert_gate": false,
451
+ "vit_gradient_checkpointing": true,
452
+ "gradient_checkpointing_kwargs": null,
453
+ "linear_num_value_heads": null,
454
+ "linear_num_key_heads": null,
455
+ "linear_key_head_dim": null,
456
+ "linear_value_head_dim": null,
457
+ "linear_conv_kernel_dim": null,
458
+ "layer_types": null,
459
+ "mrope_interleaved": false,
460
+ "add_version": true,
461
+ "model_info": "ModelInfo(model_type='qwen3', model_dir='/workspace/Qwen3-32B', torch_dtype=torch.bfloat16, max_model_len=40960, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, config=None, task_type='causal_lm', num_labels=None)",
462
+ "model_meta": "ModelMeta(model_type='qwen3', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-0.6B-Base', hf_model_id='Qwen/Qwen3-0.6B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B-Base', hf_model_id='Qwen/Qwen3-1.7B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-Base', hf_model_id='Qwen/Qwen3-4B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-Base', hf_model_id='Qwen/Qwen3-8B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-Base', hf_model_id='Qwen/Qwen3-14B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-0.6B', hf_model_id='Qwen/Qwen3-0.6B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B', hf_model_id='Qwen/Qwen3-1.7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B', hf_model_id='Qwen/Qwen3-4B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B', hf_model_id='Qwen/Qwen3-8B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B', hf_model_id='Qwen/Qwen3-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B', hf_model_id='Qwen/Qwen3-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-0.6B-FP8', hf_model_id='Qwen/Qwen3-0.6B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-1.7B-FP8', hf_model_id='Qwen/Qwen3-1.7B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-FP8', hf_model_id='Qwen/Qwen3-4B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-FP8', hf_model_id='Qwen/Qwen3-8B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-FP8', hf_model_id='Qwen/Qwen3-14B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B-FP8', hf_model_id='Qwen/Qwen3-32B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-AWQ', hf_model_id='Qwen/Qwen3-4B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-8B-AWQ', hf_model_id='Qwen/Qwen3-8B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-14B-AWQ', hf_model_id='Qwen/Qwen3-14B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-32B-AWQ', hf_model_id='Qwen/Qwen3-32B-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='swift/Qwen3-32B-AWQ', hf_model_id=None, model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen3', get_function=<function get_model_tokenizer_with_flash_attn at 0x70b3aa6eb880>, model_arch=ModelKeys(arch_name='llama', embedding='model.embed_tokens', module_list='model.layers', lm_head='lm_head', q_proj='model.layers.{}.self_attn.q_proj', k_proj='model.layers.{}.self_attn.k_proj', v_proj='model.layers.{}.self_attn.v_proj', o_proj='model.layers.{}.self_attn.o_proj', attention='model.layers.{}.self_attn', mlp='model.layers.{}.mlp', down_proj='model.layers.{}.mlp.down_proj', qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None), architectures=['Qwen3ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.51'], tags=[])",
463
+ "megatron_model_meta": "MegatronModelMeta(megatron_model_type='gpt', model_types=['qwen2', 'qwen2_5', 'qwq', 'qwq_preview', 'qwen2_5_math', 'llama', 'llama3', 'llama3_1', 'llama3_2', 'longwriter_llama3_1', 'codefuse_codellama', 'marco_o1', 'deepseek', 'deepseek_r1_distill', 'yi', 'yi_coder', 'sus', 'skywork_o1', 'openbuddy_llama', 'openbuddy_llama3', 'megrez', 'reflection', 'numina', 'ziya', 'mengzi3', 'qwen3', 'qwen3_thinking', 'qwen3_nothinking', 'qwen2_moe', 'qwen3_moe', 'qwen3_moe_thinking', 'qwen3_coder', 'internlm3', 'mimo', 'mimo_rl', 'moonlight', 'deepseek_moe', 'deepseek_v2', 'deepseek_v2_5', 'deepseek_r1', 'dots1', 'ernie', 'glm4_5', 'deepseek_v3_1', 'ernie_thinking'], convert_mcore2hf=<function convert_mcore2hf at 0x70b313552de0>, convert_hf2mcore=<function convert_hf2mcore at 0x70b3135528e0>, model_cls=<class 'swift.megatron.model.gpt_model.GPTModel'>, convert_hf_config=<function convert_gpt_hf_config at 0x70b31372e660>, get_transformer_layer_spec=None, model_provider=<function model_provider at 0x70b31372d300>, visual_cls=None, extra_args_provider=None)"
464
+ }
465
+ }
chat_template.jinja ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if message.content is string %}
27
+ {%- set content = message.content %}
28
+ {%- else %}
29
+ {%- set content = '' %}
30
+ {%- endif %}
31
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
+ {%- elif message.role == "assistant" %}
34
+ {%- set reasoning_content = '' %}
35
+ {%- if message.reasoning_content is string %}
36
+ {%- set reasoning_content = message.reasoning_content %}
37
+ {%- else %}
38
+ {%- if '</think>' in content %}
39
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
+ {%- endif %}
42
+ {%- endif %}
43
+ {%- if loop.index0 > ns.last_query_index %}
44
+ {%- if loop.last or (not loop.last and reasoning_content) %}
45
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
+ {%- else %}
47
+ {{- '<|im_start|>' + message.role + '\n' + content }}
48
+ {%- endif %}
49
+ {%- else %}
50
+ {{- '<|im_start|>' + message.role + '\n' + content }}
51
+ {%- endif %}
52
+ {%- if message.tool_calls %}
53
+ {%- for tool_call in message.tool_calls %}
54
+ {%- if (loop.first and content) or (not loop.first) %}
55
+ {{- '\n' }}
56
+ {%- endif %}
57
+ {%- if tool_call.function %}
58
+ {%- set tool_call = tool_call.function %}
59
+ {%- endif %}
60
+ {{- '<tool_call>\n{"name": "' }}
61
+ {{- tool_call.name }}
62
+ {{- '", "arguments": ' }}
63
+ {%- if tool_call.arguments is string %}
64
+ {{- tool_call.arguments }}
65
+ {%- else %}
66
+ {{- tool_call.arguments | tojson }}
67
+ {%- endif %}
68
+ {{- '}\n</tool_call>' }}
69
+ {%- endfor %}
70
+ {%- endif %}
71
+ {{- '<|im_end|>\n' }}
72
+ {%- elif message.role == "tool" %}
73
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
+ {{- '<|im_start|>user' }}
75
+ {%- endif %}
76
+ {{- '\n<tool_response>\n' }}
77
+ {{- content }}
78
+ {{- '\n</tool_response>' }}
79
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
+ {{- '<|im_end|>\n' }}
81
+ {%- endif %}
82
+ {%- endif %}
83
+ {%- endfor %}
84
+ {%- if add_generation_prompt %}
85
+ {{- '<|im_start|>assistant\n' }}
86
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 151645,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 5120,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 25600,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention",
73
+ "full_attention",
74
+ "full_attention",
75
+ "full_attention",
76
+ "full_attention",
77
+ "full_attention",
78
+ "full_attention",
79
+ "full_attention"
80
+ ],
81
+ "max_position_embeddings": 40960,
82
+ "max_window_layers": 64,
83
+ "model_type": "qwen3",
84
+ "num_attention_heads": 64,
85
+ "num_hidden_layers": 64,
86
+ "num_key_value_heads": 8,
87
+ "pad_token_id": 151643,
88
+ "rms_norm_eps": 1e-06,
89
+ "rope_scaling": null,
90
+ "rope_theta": 1000000,
91
+ "sliding_window": null,
92
+ "tie_word_embeddings": false,
93
+ "transformers_version": "4.57.1",
94
+ "use_cache": true,
95
+ "use_sliding_window": false,
96
+ "vocab_size": 151936
97
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.57.1"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aa50005016356d05fb0e37cfab70cddc64134a1b5ef2757a5703d2aed190770
3
+ size 7305955360
model-00002-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:214ed06c5de2c76433b66657e03f355b28ce8718987d8eb53013d8abb167b501
3
+ size 7340035248
model-00003-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f84b8ecd41f4eab3bf01ef061b7f7056a99a48b571c319d58599175b9032c93f
3
+ size 7340035256
model-00004-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83841c9997aeb4cfcb9366e86a42d0a8a8edcca589790303d1449b0ae9fbc1f5
3
+ size 7340035256
model-00005-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c45af8f82a87901560f12502453a83e0c0758d90c610d9bb97e6e1856524a74
3
+ size 7340035248
model-00006-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e08da3e6d28a8c3852c757c427e08894ee1fb3f37e161913669e8b2128217438
3
+ size 7340035240
model-00007-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc3ce11c1d46526f62496a7dad99a7ea777cf9bdbfd7f23b54a3180304f38abe
3
+ size 7340035256
model-00008-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cdbaeb5dda4ff7dea0c05d317dc7e2ba28df8edd88becf39a5195e76c498f2b
3
+ size 7465869608
model-00009-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cb558f9c88fac32e76dccae0f548f3c8695194fe0fe68c14673efa4acd1ecfa
3
+ size 6712291928
model.safetensors.index.json ADDED
@@ -0,0 +1,715 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 32762123264,
4
+ "total_size": 65524246528
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00001-of-00009.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00009-of-00009.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
14
+ "model.layers.0.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
17
+ "model.layers.0.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00009-of-00009.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
25
+ "model.layers.1.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
28
+ "model.layers.1.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
30
+ "model.layers.1.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
31
+ "model.layers.10.input_layernorm.weight": "model-00009-of-00009.safetensors",
32
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
33
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
34
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
35
+ "model.layers.10.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
36
+ "model.layers.10.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
37
+ "model.layers.10.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
38
+ "model.layers.10.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
39
+ "model.layers.10.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
40
+ "model.layers.10.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
41
+ "model.layers.10.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
42
+ "model.layers.11.input_layernorm.weight": "model-00009-of-00009.safetensors",
43
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
44
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
45
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
46
+ "model.layers.11.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
47
+ "model.layers.11.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
48
+ "model.layers.11.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
49
+ "model.layers.11.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
50
+ "model.layers.11.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
51
+ "model.layers.11.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
52
+ "model.layers.11.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
53
+ "model.layers.12.input_layernorm.weight": "model-00009-of-00009.safetensors",
54
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
55
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
56
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
57
+ "model.layers.12.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
58
+ "model.layers.12.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
59
+ "model.layers.12.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
60
+ "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
61
+ "model.layers.12.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
62
+ "model.layers.12.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
63
+ "model.layers.12.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
64
+ "model.layers.13.input_layernorm.weight": "model-00009-of-00009.safetensors",
65
+ "model.layers.13.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
66
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
67
+ "model.layers.13.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
68
+ "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
69
+ "model.layers.13.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
70
+ "model.layers.13.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
71
+ "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
72
+ "model.layers.13.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
73
+ "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
74
+ "model.layers.13.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
75
+ "model.layers.14.input_layernorm.weight": "model-00009-of-00009.safetensors",
76
+ "model.layers.14.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
77
+ "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
78
+ "model.layers.14.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
79
+ "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
80
+ "model.layers.14.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
81
+ "model.layers.14.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
82
+ "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
83
+ "model.layers.14.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
84
+ "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
85
+ "model.layers.14.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
86
+ "model.layers.15.input_layernorm.weight": "model-00009-of-00009.safetensors",
87
+ "model.layers.15.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
88
+ "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
89
+ "model.layers.15.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
90
+ "model.layers.15.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
91
+ "model.layers.15.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
92
+ "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
93
+ "model.layers.15.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
94
+ "model.layers.15.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
95
+ "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
96
+ "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
97
+ "model.layers.16.input_layernorm.weight": "model-00009-of-00009.safetensors",
98
+ "model.layers.16.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
99
+ "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
100
+ "model.layers.16.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
101
+ "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
102
+ "model.layers.16.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
103
+ "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
104
+ "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
105
+ "model.layers.16.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
106
+ "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
107
+ "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
108
+ "model.layers.17.input_layernorm.weight": "model-00009-of-00009.safetensors",
109
+ "model.layers.17.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
110
+ "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
111
+ "model.layers.17.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
112
+ "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
113
+ "model.layers.17.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
114
+ "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
115
+ "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
116
+ "model.layers.17.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
117
+ "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
118
+ "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
119
+ "model.layers.18.input_layernorm.weight": "model-00009-of-00009.safetensors",
120
+ "model.layers.18.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
121
+ "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
122
+ "model.layers.18.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
123
+ "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
124
+ "model.layers.18.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
125
+ "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
126
+ "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
127
+ "model.layers.18.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
128
+ "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
129
+ "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
130
+ "model.layers.19.input_layernorm.weight": "model-00009-of-00009.safetensors",
131
+ "model.layers.19.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
132
+ "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
133
+ "model.layers.19.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
134
+ "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
135
+ "model.layers.19.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
136
+ "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
137
+ "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
138
+ "model.layers.19.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
139
+ "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
140
+ "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
141
+ "model.layers.2.input_layernorm.weight": "model-00009-of-00009.safetensors",
142
+ "model.layers.2.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
143
+ "model.layers.2.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
144
+ "model.layers.2.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
145
+ "model.layers.2.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
146
+ "model.layers.2.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
147
+ "model.layers.2.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
148
+ "model.layers.2.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
149
+ "model.layers.2.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
150
+ "model.layers.2.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
151
+ "model.layers.2.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
152
+ "model.layers.20.input_layernorm.weight": "model-00009-of-00009.safetensors",
153
+ "model.layers.20.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
154
+ "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
155
+ "model.layers.20.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
156
+ "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
157
+ "model.layers.20.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
158
+ "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
159
+ "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
160
+ "model.layers.20.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
161
+ "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
162
+ "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
163
+ "model.layers.21.input_layernorm.weight": "model-00009-of-00009.safetensors",
164
+ "model.layers.21.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
165
+ "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
166
+ "model.layers.21.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
167
+ "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
168
+ "model.layers.21.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
169
+ "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
170
+ "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
171
+ "model.layers.21.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
172
+ "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
173
+ "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
174
+ "model.layers.22.input_layernorm.weight": "model-00009-of-00009.safetensors",
175
+ "model.layers.22.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
176
+ "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
177
+ "model.layers.22.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
178
+ "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
179
+ "model.layers.22.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
180
+ "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
181
+ "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
182
+ "model.layers.22.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
183
+ "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
184
+ "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
185
+ "model.layers.23.input_layernorm.weight": "model-00009-of-00009.safetensors",
186
+ "model.layers.23.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
187
+ "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
188
+ "model.layers.23.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
189
+ "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
190
+ "model.layers.23.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
191
+ "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
192
+ "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
193
+ "model.layers.23.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
194
+ "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
195
+ "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
196
+ "model.layers.24.input_layernorm.weight": "model-00009-of-00009.safetensors",
197
+ "model.layers.24.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
198
+ "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
199
+ "model.layers.24.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
200
+ "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
201
+ "model.layers.24.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
202
+ "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
203
+ "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
204
+ "model.layers.24.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
205
+ "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
206
+ "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
207
+ "model.layers.25.input_layernorm.weight": "model-00009-of-00009.safetensors",
208
+ "model.layers.25.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
209
+ "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
210
+ "model.layers.25.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
211
+ "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
212
+ "model.layers.25.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
213
+ "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
214
+ "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
215
+ "model.layers.25.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
216
+ "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
217
+ "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
218
+ "model.layers.26.input_layernorm.weight": "model-00009-of-00009.safetensors",
219
+ "model.layers.26.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
220
+ "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
221
+ "model.layers.26.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
222
+ "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
223
+ "model.layers.26.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
224
+ "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
225
+ "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
226
+ "model.layers.26.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
227
+ "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
228
+ "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
229
+ "model.layers.27.input_layernorm.weight": "model-00009-of-00009.safetensors",
230
+ "model.layers.27.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
231
+ "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
232
+ "model.layers.27.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
233
+ "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
234
+ "model.layers.27.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
235
+ "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
236
+ "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
237
+ "model.layers.27.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
238
+ "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
239
+ "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
240
+ "model.layers.28.input_layernorm.weight": "model-00009-of-00009.safetensors",
241
+ "model.layers.28.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
242
+ "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
243
+ "model.layers.28.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
244
+ "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
245
+ "model.layers.28.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
246
+ "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
247
+ "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
248
+ "model.layers.28.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
249
+ "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
250
+ "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
251
+ "model.layers.29.input_layernorm.weight": "model-00009-of-00009.safetensors",
252
+ "model.layers.29.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
253
+ "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
254
+ "model.layers.29.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
255
+ "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
256
+ "model.layers.29.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
257
+ "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
258
+ "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
259
+ "model.layers.29.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
260
+ "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
261
+ "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
262
+ "model.layers.3.input_layernorm.weight": "model-00009-of-00009.safetensors",
263
+ "model.layers.3.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
264
+ "model.layers.3.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
265
+ "model.layers.3.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
266
+ "model.layers.3.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
267
+ "model.layers.3.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
268
+ "model.layers.3.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
269
+ "model.layers.3.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
270
+ "model.layers.3.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
271
+ "model.layers.3.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
273
+ "model.layers.30.input_layernorm.weight": "model-00009-of-00009.safetensors",
274
+ "model.layers.30.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
275
+ "model.layers.30.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
276
+ "model.layers.30.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
277
+ "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
278
+ "model.layers.30.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
279
+ "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
280
+ "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
281
+ "model.layers.30.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
282
+ "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
283
+ "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
284
+ "model.layers.31.input_layernorm.weight": "model-00009-of-00009.safetensors",
285
+ "model.layers.31.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
286
+ "model.layers.31.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
287
+ "model.layers.31.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
288
+ "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
289
+ "model.layers.31.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
290
+ "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
291
+ "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
292
+ "model.layers.31.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
293
+ "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
294
+ "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
295
+ "model.layers.32.input_layernorm.weight": "model-00009-of-00009.safetensors",
296
+ "model.layers.32.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
297
+ "model.layers.32.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
298
+ "model.layers.32.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
299
+ "model.layers.32.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
300
+ "model.layers.32.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
301
+ "model.layers.32.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
302
+ "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
303
+ "model.layers.32.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
304
+ "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
305
+ "model.layers.32.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
306
+ "model.layers.33.input_layernorm.weight": "model-00009-of-00009.safetensors",
307
+ "model.layers.33.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
308
+ "model.layers.33.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
309
+ "model.layers.33.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
310
+ "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
311
+ "model.layers.33.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
312
+ "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
313
+ "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
314
+ "model.layers.33.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
315
+ "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
316
+ "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
317
+ "model.layers.34.input_layernorm.weight": "model-00009-of-00009.safetensors",
318
+ "model.layers.34.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
319
+ "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
320
+ "model.layers.34.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
321
+ "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
322
+ "model.layers.34.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
323
+ "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
324
+ "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
325
+ "model.layers.34.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
326
+ "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
327
+ "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
328
+ "model.layers.35.input_layernorm.weight": "model-00009-of-00009.safetensors",
329
+ "model.layers.35.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
330
+ "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
331
+ "model.layers.35.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
332
+ "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
333
+ "model.layers.35.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
334
+ "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
335
+ "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
336
+ "model.layers.35.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
337
+ "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
338
+ "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
339
+ "model.layers.36.input_layernorm.weight": "model-00009-of-00009.safetensors",
340
+ "model.layers.36.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
341
+ "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
342
+ "model.layers.36.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
343
+ "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
344
+ "model.layers.36.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
345
+ "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
346
+ "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
347
+ "model.layers.36.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
348
+ "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
349
+ "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
350
+ "model.layers.37.input_layernorm.weight": "model-00009-of-00009.safetensors",
351
+ "model.layers.37.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
352
+ "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
353
+ "model.layers.37.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
354
+ "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
355
+ "model.layers.37.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
356
+ "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
357
+ "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
358
+ "model.layers.37.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
359
+ "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
360
+ "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
361
+ "model.layers.38.input_layernorm.weight": "model-00009-of-00009.safetensors",
362
+ "model.layers.38.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
363
+ "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
364
+ "model.layers.38.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
365
+ "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
366
+ "model.layers.38.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
367
+ "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
368
+ "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
369
+ "model.layers.38.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
370
+ "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
371
+ "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
372
+ "model.layers.39.input_layernorm.weight": "model-00009-of-00009.safetensors",
373
+ "model.layers.39.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
374
+ "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
375
+ "model.layers.39.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
376
+ "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
377
+ "model.layers.39.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
378
+ "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
379
+ "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
380
+ "model.layers.39.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
381
+ "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
382
+ "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
383
+ "model.layers.4.input_layernorm.weight": "model-00009-of-00009.safetensors",
384
+ "model.layers.4.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
385
+ "model.layers.4.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
386
+ "model.layers.4.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
387
+ "model.layers.4.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
388
+ "model.layers.4.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
389
+ "model.layers.4.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
390
+ "model.layers.4.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
391
+ "model.layers.4.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
392
+ "model.layers.4.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
393
+ "model.layers.4.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
394
+ "model.layers.40.input_layernorm.weight": "model-00009-of-00009.safetensors",
395
+ "model.layers.40.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
396
+ "model.layers.40.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
397
+ "model.layers.40.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
398
+ "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
399
+ "model.layers.40.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
400
+ "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
401
+ "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
402
+ "model.layers.40.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
403
+ "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
404
+ "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
405
+ "model.layers.41.input_layernorm.weight": "model-00009-of-00009.safetensors",
406
+ "model.layers.41.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
407
+ "model.layers.41.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
408
+ "model.layers.41.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
409
+ "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
410
+ "model.layers.41.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
411
+ "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
412
+ "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
413
+ "model.layers.41.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
414
+ "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
415
+ "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
416
+ "model.layers.42.input_layernorm.weight": "model-00009-of-00009.safetensors",
417
+ "model.layers.42.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
418
+ "model.layers.42.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
419
+ "model.layers.42.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
420
+ "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
421
+ "model.layers.42.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
422
+ "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
423
+ "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
424
+ "model.layers.42.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
425
+ "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
426
+ "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
427
+ "model.layers.43.input_layernorm.weight": "model-00009-of-00009.safetensors",
428
+ "model.layers.43.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
429
+ "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
430
+ "model.layers.43.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
431
+ "model.layers.43.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
432
+ "model.layers.43.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
433
+ "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
434
+ "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
435
+ "model.layers.43.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
436
+ "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
437
+ "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
438
+ "model.layers.44.input_layernorm.weight": "model-00009-of-00009.safetensors",
439
+ "model.layers.44.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
440
+ "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
441
+ "model.layers.44.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
442
+ "model.layers.44.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
443
+ "model.layers.44.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
444
+ "model.layers.44.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
445
+ "model.layers.44.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
446
+ "model.layers.44.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
447
+ "model.layers.44.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
448
+ "model.layers.44.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
449
+ "model.layers.45.input_layernorm.weight": "model-00009-of-00009.safetensors",
450
+ "model.layers.45.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
451
+ "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
452
+ "model.layers.45.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
453
+ "model.layers.45.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
454
+ "model.layers.45.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
455
+ "model.layers.45.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
456
+ "model.layers.45.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
457
+ "model.layers.45.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
458
+ "model.layers.45.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
459
+ "model.layers.45.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
460
+ "model.layers.46.input_layernorm.weight": "model-00009-of-00009.safetensors",
461
+ "model.layers.46.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
462
+ "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
463
+ "model.layers.46.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
464
+ "model.layers.46.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
465
+ "model.layers.46.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
466
+ "model.layers.46.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
467
+ "model.layers.46.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
468
+ "model.layers.46.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
469
+ "model.layers.46.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
470
+ "model.layers.46.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
471
+ "model.layers.47.input_layernorm.weight": "model-00009-of-00009.safetensors",
472
+ "model.layers.47.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
473
+ "model.layers.47.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
474
+ "model.layers.47.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
475
+ "model.layers.47.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
476
+ "model.layers.47.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
477
+ "model.layers.47.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
478
+ "model.layers.47.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
479
+ "model.layers.47.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
480
+ "model.layers.47.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
481
+ "model.layers.47.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
482
+ "model.layers.48.input_layernorm.weight": "model-00009-of-00009.safetensors",
483
+ "model.layers.48.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
484
+ "model.layers.48.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
485
+ "model.layers.48.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
486
+ "model.layers.48.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
487
+ "model.layers.48.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
488
+ "model.layers.48.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
489
+ "model.layers.48.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
490
+ "model.layers.48.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
491
+ "model.layers.48.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
492
+ "model.layers.48.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
493
+ "model.layers.49.input_layernorm.weight": "model-00009-of-00009.safetensors",
494
+ "model.layers.49.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
495
+ "model.layers.49.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
496
+ "model.layers.49.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
497
+ "model.layers.49.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
498
+ "model.layers.49.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
499
+ "model.layers.49.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
500
+ "model.layers.49.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
501
+ "model.layers.49.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
502
+ "model.layers.49.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
503
+ "model.layers.49.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
504
+ "model.layers.5.input_layernorm.weight": "model-00009-of-00009.safetensors",
505
+ "model.layers.5.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
506
+ "model.layers.5.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
507
+ "model.layers.5.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
508
+ "model.layers.5.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
509
+ "model.layers.5.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
510
+ "model.layers.5.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
511
+ "model.layers.5.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
512
+ "model.layers.5.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
513
+ "model.layers.5.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
514
+ "model.layers.5.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
515
+ "model.layers.50.input_layernorm.weight": "model-00009-of-00009.safetensors",
516
+ "model.layers.50.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
517
+ "model.layers.50.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
518
+ "model.layers.50.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
519
+ "model.layers.50.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
520
+ "model.layers.50.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
521
+ "model.layers.50.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
522
+ "model.layers.50.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
523
+ "model.layers.50.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
524
+ "model.layers.50.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
525
+ "model.layers.50.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
526
+ "model.layers.51.input_layernorm.weight": "model-00009-of-00009.safetensors",
527
+ "model.layers.51.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
528
+ "model.layers.51.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
529
+ "model.layers.51.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
530
+ "model.layers.51.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
531
+ "model.layers.51.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
532
+ "model.layers.51.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
533
+ "model.layers.51.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
534
+ "model.layers.51.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
535
+ "model.layers.51.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
536
+ "model.layers.51.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
537
+ "model.layers.52.input_layernorm.weight": "model-00009-of-00009.safetensors",
538
+ "model.layers.52.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
539
+ "model.layers.52.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
540
+ "model.layers.52.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
541
+ "model.layers.52.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
542
+ "model.layers.52.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
543
+ "model.layers.52.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
544
+ "model.layers.52.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
545
+ "model.layers.52.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
546
+ "model.layers.52.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
547
+ "model.layers.52.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
548
+ "model.layers.53.input_layernorm.weight": "model-00009-of-00009.safetensors",
549
+ "model.layers.53.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
550
+ "model.layers.53.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
551
+ "model.layers.53.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
552
+ "model.layers.53.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
553
+ "model.layers.53.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
554
+ "model.layers.53.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
555
+ "model.layers.53.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
556
+ "model.layers.53.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
557
+ "model.layers.53.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
558
+ "model.layers.53.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
559
+ "model.layers.54.input_layernorm.weight": "model-00009-of-00009.safetensors",
560
+ "model.layers.54.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
561
+ "model.layers.54.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
562
+ "model.layers.54.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
563
+ "model.layers.54.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
564
+ "model.layers.54.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
565
+ "model.layers.54.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
566
+ "model.layers.54.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
567
+ "model.layers.54.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
568
+ "model.layers.54.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
569
+ "model.layers.54.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
570
+ "model.layers.55.input_layernorm.weight": "model-00009-of-00009.safetensors",
571
+ "model.layers.55.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
572
+ "model.layers.55.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
573
+ "model.layers.55.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
574
+ "model.layers.55.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
575
+ "model.layers.55.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
576
+ "model.layers.55.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
577
+ "model.layers.55.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
578
+ "model.layers.55.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
579
+ "model.layers.55.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
580
+ "model.layers.55.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
581
+ "model.layers.56.input_layernorm.weight": "model-00009-of-00009.safetensors",
582
+ "model.layers.56.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
583
+ "model.layers.56.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
584
+ "model.layers.56.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
585
+ "model.layers.56.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
586
+ "model.layers.56.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
587
+ "model.layers.56.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
588
+ "model.layers.56.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
589
+ "model.layers.56.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
590
+ "model.layers.56.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
591
+ "model.layers.56.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
592
+ "model.layers.57.input_layernorm.weight": "model-00009-of-00009.safetensors",
593
+ "model.layers.57.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
594
+ "model.layers.57.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
595
+ "model.layers.57.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
596
+ "model.layers.57.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
597
+ "model.layers.57.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
598
+ "model.layers.57.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
599
+ "model.layers.57.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
600
+ "model.layers.57.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
601
+ "model.layers.57.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
602
+ "model.layers.57.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
603
+ "model.layers.58.input_layernorm.weight": "model-00009-of-00009.safetensors",
604
+ "model.layers.58.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
605
+ "model.layers.58.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
606
+ "model.layers.58.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
607
+ "model.layers.58.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
608
+ "model.layers.58.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
609
+ "model.layers.58.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
610
+ "model.layers.58.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
611
+ "model.layers.58.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
612
+ "model.layers.58.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
613
+ "model.layers.58.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
614
+ "model.layers.59.input_layernorm.weight": "model-00009-of-00009.safetensors",
615
+ "model.layers.59.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
616
+ "model.layers.59.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
617
+ "model.layers.59.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
618
+ "model.layers.59.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
619
+ "model.layers.59.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
620
+ "model.layers.59.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
621
+ "model.layers.59.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
622
+ "model.layers.59.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
623
+ "model.layers.59.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
624
+ "model.layers.59.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
625
+ "model.layers.6.input_layernorm.weight": "model-00009-of-00009.safetensors",
626
+ "model.layers.6.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
627
+ "model.layers.6.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
628
+ "model.layers.6.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
629
+ "model.layers.6.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
630
+ "model.layers.6.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
631
+ "model.layers.6.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
632
+ "model.layers.6.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
633
+ "model.layers.6.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
634
+ "model.layers.6.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
635
+ "model.layers.6.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
636
+ "model.layers.60.input_layernorm.weight": "model-00009-of-00009.safetensors",
637
+ "model.layers.60.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
638
+ "model.layers.60.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
639
+ "model.layers.60.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
640
+ "model.layers.60.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
641
+ "model.layers.60.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
642
+ "model.layers.60.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
643
+ "model.layers.60.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
644
+ "model.layers.60.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
645
+ "model.layers.60.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
646
+ "model.layers.60.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
647
+ "model.layers.61.input_layernorm.weight": "model-00009-of-00009.safetensors",
648
+ "model.layers.61.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
649
+ "model.layers.61.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
650
+ "model.layers.61.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
651
+ "model.layers.61.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
652
+ "model.layers.61.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
653
+ "model.layers.61.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
654
+ "model.layers.61.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
655
+ "model.layers.61.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
656
+ "model.layers.61.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
657
+ "model.layers.61.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
658
+ "model.layers.62.input_layernorm.weight": "model-00009-of-00009.safetensors",
659
+ "model.layers.62.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
660
+ "model.layers.62.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
661
+ "model.layers.62.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
662
+ "model.layers.62.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
663
+ "model.layers.62.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
664
+ "model.layers.62.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
665
+ "model.layers.62.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
666
+ "model.layers.62.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
667
+ "model.layers.62.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
668
+ "model.layers.62.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
669
+ "model.layers.63.input_layernorm.weight": "model-00009-of-00009.safetensors",
670
+ "model.layers.63.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
671
+ "model.layers.63.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
672
+ "model.layers.63.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
673
+ "model.layers.63.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
674
+ "model.layers.63.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
675
+ "model.layers.63.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
676
+ "model.layers.63.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
677
+ "model.layers.63.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
678
+ "model.layers.63.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
679
+ "model.layers.63.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
680
+ "model.layers.7.input_layernorm.weight": "model-00009-of-00009.safetensors",
681
+ "model.layers.7.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
682
+ "model.layers.7.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
683
+ "model.layers.7.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
684
+ "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
685
+ "model.layers.7.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
686
+ "model.layers.7.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
687
+ "model.layers.7.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
688
+ "model.layers.7.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
689
+ "model.layers.7.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
690
+ "model.layers.7.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
691
+ "model.layers.8.input_layernorm.weight": "model-00009-of-00009.safetensors",
692
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
693
+ "model.layers.8.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
694
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
695
+ "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
696
+ "model.layers.8.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
697
+ "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
698
+ "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
699
+ "model.layers.8.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
700
+ "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
701
+ "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
702
+ "model.layers.9.input_layernorm.weight": "model-00009-of-00009.safetensors",
703
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
704
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
705
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
706
+ "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
707
+ "model.layers.9.self_attn.k_norm.weight": "model-00009-of-00009.safetensors",
708
+ "model.layers.9.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
709
+ "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
710
+ "model.layers.9.self_attn.q_norm.weight": "model-00009-of-00009.safetensors",
711
+ "model.layers.9.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
712
+ "model.layers.9.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
713
+ "model.norm.weight": "model-00009-of-00009.safetensors"
714
+ }
715
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff