sealofyou/InternLM3-8B-Lora-SFT
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: sealofyou/InternLM3-8B-Lora-SFT
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-17 10:45:02 +08:00
commit fc8314fb36
18 changed files with 2873 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
.gitattributes vendored Normal file
View File

@@ -0,0 +1,47 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.gguf* filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text

2
.gitignore vendored Normal file
View File

@@ -0,0 +1,2 @@
runs/
images/

333
args.json Normal file
View File

@@ -0,0 +1,333 @@
{
"output_dir": "/root/L1G4/swift_output/InternLM3-8B-Lora-SFT/v0-20250628-153753",
"overwrite_output_dir": false,
"do_train": false,
"do_eval": false,
"do_predict": false,
"eval_strategy": "steps",
"prediction_loss_only": false,
"per_device_train_batch_size": 1,
"per_device_eval_batch_size": 1,
"per_gpu_train_batch_size": null,
"per_gpu_eval_batch_size": null,
"gradient_accumulation_steps": 2,
"eval_accumulation_steps": null,
"eval_delay": 0,
"torch_empty_cache_steps": null,
"learning_rate": 0.0001,
"weight_decay": 0.1,
"adam_beta1": 0.9,
"adam_beta2": 0.95,
"adam_epsilon": 1e-08,
"max_grad_norm": 1.0,
"num_train_epochs": 60.0,
"max_steps": -1,
"lr_scheduler_type": "cosine",
"lr_scheduler_kwargs": null,
"warmup_ratio": 0.1,
"warmup_steps": 0,
"log_level": "passive",
"log_level_replica": "warning",
"log_on_each_node": true,
"logging_dir": "/root/L1G4/swift_output/InternLM3-8B-Lora-SFT/v0-20250628-153753/runs",
"logging_strategy": "steps",
"logging_first_step": true,
"logging_steps": 5,
"logging_nan_inf_filter": true,
"save_strategy": "steps",
"save_steps": 2000.0,
"save_total_limit": 5,
"save_safetensors": true,
"save_on_each_node": false,
"save_only_model": false,
"restore_callback_states_from_checkpoint": false,
"no_cuda": false,
"use_cpu": false,
"use_mps_device": false,
"seed": 42,
"data_seed": 42,
"jit_mode_eval": false,
"use_ipex": false,
"bf16": true,
"fp16": false,
"fp16_opt_level": "O1",
"half_precision_backend": "auto",
"bf16_full_eval": false,
"fp16_full_eval": false,
"tf32": null,
"local_rank": 0,
"ddp_backend": null,
"tpu_num_cores": null,
"tpu_metrics_debug": false,
"debug": null,
"dataloader_drop_last": false,
"eval_steps": 2000.0,
"dataloader_num_workers": 1,
"dataloader_prefetch_factor": null,
"past_index": -1,
"run_name": "/root/L1G4/swift_output/InternLM3-8B-Lora-SFT/v0-20250628-153753",
"disable_tqdm": null,
"remove_unused_columns": true,
"label_names": null,
"load_best_model_at_end": false,
"metric_for_best_model": "loss",
"greater_is_better": false,
"ignore_data_skip": false,
"fsdp": "",
"fsdp_min_num_params": 0,
"fsdp_config": null,
"fsdp_transformer_layer_cls_to_wrap": null,
"accelerator_config": {
"dispatch_batches": false
},
"deepspeed": null,
"label_smoothing_factor": 0.0,
"optim": "adamw_torch",
"optim_args": null,
"adafactor": false,
"group_by_length": false,
"length_column_name": "length",
"report_to": [
"swanlab"
],
"ddp_find_unused_parameters": null,
"ddp_bucket_cap_mb": null,
"ddp_broadcast_buffers": null,
"dataloader_pin_memory": true,
"dataloader_persistent_workers": false,
"skip_memory_metrics": true,
"use_legacy_prediction_loop": false,
"push_to_hub": false,
"resume_from_checkpoint": null,
"hub_model_id": null,
"hub_strategy": "every_save",
"hub_token": null,
"hub_private_repo": null,
"hub_always_push": false,
"gradient_checkpointing": true,
"gradient_checkpointing_kwargs": "{\"use_reentrant\": false}",
"include_inputs_for_metrics": false,
"include_for_metrics": [],
"eval_do_concat_batches": true,
"fp16_backend": "auto",
"push_to_hub_model_id": null,
"push_to_hub_organization": null,
"push_to_hub_token": null,
"mp_parameters": "",
"auto_find_batch_size": false,
"full_determinism": false,
"torchdynamo": null,
"ray_scope": "last",
"ddp_timeout": 18000000,
"torch_compile": false,
"torch_compile_backend": null,
"torch_compile_mode": null,
"include_tokens_per_second": false,
"include_num_input_tokens_seen": false,
"neftune_noise_alpha": null,
"optim_target_modules": null,
"batch_eval_metrics": false,
"eval_on_start": false,
"use_liger_kernel": false,
"eval_use_gather_object": false,
"average_tokens_across_devices": false,
"sortish_sampler": false,
"predict_with_generate": false,
"generation_max_length": null,
"generation_num_beams": null,
"generation_config": null,
"vit_gradient_checkpointing": null,
"check_model": true,
"acc_strategy": "token",
"train_dataloader_shuffle": true,
"max_epochs": null,
"aligner_lr": null,
"vit_lr": null,
"optimizer": null,
"use_logits_to_keep": null,
"channels": null,
"metric_warmup_step": 0,
"fsdp_num": 1,
"acc_steps": 1,
"eval_use_evalscope": false,
"eval_datasets": [],
"eval_limit": null,
"eval_datasets_args": null,
"eval_generation_config": null,
"model": "/root/L1G4/swift_output/InternLM3-8B-Lora/v0-20250628-003035/checkpoint-14400-merged",
"model_type": "internlm3",
"model_revision": null,
"task_type": "causal_lm",
"torch_dtype": "bfloat16",
"attn_impl": null,
"num_labels": null,
"problem_type": null,
"rope_scaling": null,
"device_map": null,
"max_memory": {},
"local_repo_path": null,
"init_strategy": null,
"template": "internlm2",
"system": null,
"max_length": 4096,
"truncation_strategy": "delete",
"max_pixels": null,
"agent_template": null,
"norm_bbox": null,
"use_chat_template": true,
"padding_free": false,
"padding_side": "right",
"loss_scale": "default",
"sequence_parallel_size": 1,
"response_prefix": null,
"template_backend": "swift",
"dataset": [
"/root/L1G4/datasets/train/swift_formatted_sft_train_data.jsonl"
],
"val_dataset": [],
"split_dataset_ratio": 0.0,
"dataset_num_proc": 1,
"load_from_cache_file": true,
"dataset_shuffle": true,
"val_dataset_shuffle": false,
"streaming": false,
"interleave_prob": null,
"stopping_strategy": "first_exhausted",
"shuffle_buffer_size": 1000,
"download_mode": "reuse_dataset_if_exists",
"columns": {},
"strict": false,
"model_name": [
"InternLM3-8B-Lora-SFT"
],
"model_author": [
"Seal"
],
"custom_dataset_info": [],
"quant_method": null,
"quant_bits": null,
"hqq_axis": null,
"bnb_4bit_compute_dtype": "bfloat16",
"bnb_4bit_quant_type": "nf4",
"bnb_4bit_use_double_quant": true,
"bnb_4bit_quant_storage": null,
"max_new_tokens": 64,
"temperature": 0.0,
"top_k": null,
"top_p": null,
"repetition_penalty": null,
"num_beams": 1,
"stream": false,
"stop_words": [],
"logprobs": false,
"top_logprobs": null,
"ckpt_dir": "/root/L1G4/swift_output/InternLM3-8B-Lora/v0-20250628-003035/checkpoint-14400-merged",
"lora_modules": [],
"tuner_backend": "peft",
"train_type": "lora",
"adapters": [],
"external_plugins": [],
"model_kwargs": {},
"load_args": false,
"load_data_args": false,
"packing": false,
"packing_cache": null,
"custom_register_path": [],
"use_hf": false,
"ignore_args_error": false,
"use_swift_lora": false,
"freeze_parameters": [],
"freeze_parameters_regex": null,
"freeze_parameters_ratio": 0.0,
"trainable_parameters": [],
"trainable_parameters_regex": null,
"freeze_llm": false,
"freeze_vit": true,
"freeze_aligner": true,
"target_modules": [
"all-linear"
],
"target_regex": null,
"modules_to_save": [],
"lora_rank": 8,
"lora_alpha": 32,
"lora_dropout": 0.05,
"lora_bias": "none",
"lora_dtype": null,
"lorap_lr_ratio": null,
"use_rslora": false,
"use_dora": false,
"lora_ga_batch_size": 2,
"lora_ga_iters": 2,
"lora_ga_max_length": 1024,
"lora_ga_direction": "ArB2r",
"lora_ga_scale": "stable",
"lora_ga_stable_gamma": 16,
"init_weights": true,
"fourier_n_frequency": 2000,
"fourier_scaling": 300.0,
"boft_block_size": 4,
"boft_block_num": 0,
"boft_n_butterfly_factor": 1,
"boft_dropout": 0.0,
"vera_rank": 256,
"vera_projection_prng_key": 0,
"vera_dropout": 0.0,
"vera_d_initial": 0.1,
"adapter_act": "gelu",
"adapter_length": 128,
"use_galore": false,
"galore_target_modules": null,
"galore_rank": 128,
"galore_update_proj_gap": 50,
"galore_scale": 1.0,
"galore_proj_type": "std",
"galore_optim_per_parameter": false,
"galore_with_embedding": false,
"galore_quantization": false,
"galore_proj_quant": false,
"galore_proj_bits": 4,
"galore_proj_group_size": 256,
"galore_cos_threshold": 0.4,
"galore_gamma_proj": 2,
"galore_queue_size": 5,
"adalora_target_r": 8,
"adalora_init_r": 12,
"adalora_tinit": 0,
"adalora_tfinal": 0,
"adalora_deltaT": 1,
"adalora_beta1": 0.85,
"adalora_beta2": 0.85,
"adalora_orth_reg_weight": 0.5,
"llamapro_num_new_blocks": 4,
"llamapro_num_groups": null,
"lisa_activated_layers": 0,
"lisa_step_interval": 20,
"reft_layer_key": null,
"reft_layers": null,
"reft_rank": 4,
"reft_intervention_type": "LoreftIntervention",
"reft_args": null,
"swanlab_token": null,
"swanlab_project": "InternLM-SFT-L1G4",
"swanlab_workspace": null,
"swanlab_exp_name": "/root/L1G4/swift_output/InternLM3-8B-Lora-SFT/v0-20250628-153753",
"swanlab_mode": "cloud",
"add_version": true,
"resume_only_model": false,
"create_checkpoint_symlink": false,
"lazy_tokenize": false,
"loss_type": null,
"metric": null,
"zero_hpz_partition_size": null,
"rank": 0,
"global_world_size": 1,
"local_world_size": 1,
"model_suffix": "checkpoint-14400-merged",
"model_info": "ModelInfo(model_type='internlm3', model_dir='/root/L1G4/swift_output/InternLM3-8B-Lora/v0-20250628-003035/checkpoint-14400-merged', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=None, rope_scaling={'factor': 6.0, 'rope_type': 'dynamic'}, config=None, task_type='causal_lm', num_labels=None)",
"model_meta": "ModelMeta(model_type='internlm3', model_groups=[ModelGroup(models=[Model(ms_model_id='Shanghai_AI_Laboratory/internlm3-8b-instruct', hf_model_id='internlm/internlm3-8b-instruct', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='internlm2', get_function=<function get_model_tokenizer_with_flash_attn at 0x7fcff56da0e0>, model_arch='llama', architectures=['InternLM3ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.48'], tags=[])",
"model_dir": "/root/L1G4/swift_output/InternLM3-8B-Lora/v0-20250628-003035/checkpoint-14400-merged",
"hub": "<class 'swift.hub.hub.MSHub'>",
"evaluation_strategy": "steps",
"training_args": "Seq2SeqTrainingArguments(output_dir='/root/L1G4/swift_output/InternLM3-8B-Lora-SFT/v0-20250628-153753', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=2, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=60.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.1, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/root/L1G4/swift_output/InternLM3-8B-Lora-SFT/v0-20250628-153753/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=2000, save_total_limit=5, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=2000, dataloader_num_workers=1, dataloader_prefetch_factor=10, past_index=-1, run_name='/root/L1G4/swift_output/InternLM3-8B-Lora-SFT/v0-20250628-153753', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['swanlab'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs={'use_reentrant': False}, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, vit_gradient_checkpointing=True, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, optimizer=None, use_logits_to_keep=None, channels=None, metric_warmup_step=0, fsdp_num=1, acc_steps=1, eval_use_evalscope=False, eval_datasets=[], eval_limit=None, eval_datasets_args=None, eval_generation_config=None, train_type='lora', local_repo_path=None, galore_config=None)"
}

4
chat_template.jinja Normal file
View File

@@ -0,0 +1,4 @@
{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
' + message['content'] + '<|im_end|>' + '
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
' }}{% endif %}

37
config.json Normal file
View File

@@ -0,0 +1,37 @@
{
"architectures": [
"InternLM3ForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_internlm3.InternLM3Config",
"AutoModel": "modeling_internlm3.InternLM3Model",
"AutoModelForCausalLM": "modeling_internlm3.InternLM3ForCausalLM"
},
"bias": false,
"bos_token_id": 1,
"eos_token_id": 2,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 10240,
"max_position_embeddings": 32768,
"model_type": "internlm3",
"num_attention_heads": 32,
"num_hidden_layers": 48,
"num_key_value_heads": 2,
"pad_token_id": 2,
"qkv_bias": false,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 6.0,
"rope_type": "dynamic"
},
"rope_theta": 50000000,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.52.4",
"use_cache": true,
"vocab_size": 128512
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

197
configuration_internlm3.py Normal file
View File

@@ -0,0 +1,197 @@
# coding=utf-8
# Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
#
# This code is based on transformers/src/transformers/models/llama/configuration_llama.py
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
""" InternLM3 model configuration"""
from transformers.configuration_utils import PretrainedConfig
from transformers.modeling_rope_utils import rope_config_validation
from transformers.utils import logging
logger = logging.get_logger(__name__)
class InternLM3Config(PretrainedConfig):
r"""
This is the configuration class to store the configuration of a [`InternLM2Model`]. It is used to instantiate
an InternLM2 model according to the specified arguments, defining the model architecture. Instantiating a
configuration with the defaults will yield a similar configuration to that of the InternLM2-7B.
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
documentation from [`PretrainedConfig`] for more information.
Args:
vocab_size (`int`, *optional*, defaults to 151936):
Vocabulary size of the InternLM3 model. Defines the number of different tokens that can be represented by the
`inputs_ids` passed when calling [`InternLM3Model`]
hidden_size (`int`, *optional*, defaults to 4096):
Dimension of the hidden representations.
intermediate_size (`int`, *optional*, defaults to 22016):
Dimension of the MLP representations.
num_hidden_layers (`int`, *optional*, defaults to 32):
Number of hidden layers in the Transformer encoder.
num_attention_heads (`int`, *optional*, defaults to 32):
Number of attention heads for each attention layer in the Transformer encoder.
num_key_value_heads (`int`, *optional*, defaults to 32):
This is the number of key_value heads that should be used to implement Grouped Query Attention. If
`num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
`num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When
converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
by meanpooling all the original heads within that group. For more details checkout [this
paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to `32`.
hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
The non-linear activation function (function or string) in the decoder.
max_position_embeddings (`int`, *optional*, defaults to 32768):
The maximum sequence length that this model might ever be used with.
initializer_range (`float`, *optional*, defaults to 0.02):
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
rms_norm_eps (`float`, *optional*, defaults to 1e-06):
The epsilon used by the rms normalization layers.
use_cache (`bool`, *optional*, defaults to `True`):
Whether or not the model should return the last key/values attentions (not used by all models). Only
relevant if `config.is_decoder=True`.
tie_word_embeddings (`bool`, *optional*, defaults to `False`):
Whether the model's input and output word embeddings should be tied.
rope_theta (`float`, *optional*, defaults to 10000.0):
The base period of the RoPE embeddings.
rope_scaling (`Dict`, *optional*):
Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type
and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value
accordingly.
Expected contents:
`rope_type` (`str`):
The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope',
'llama3'], with 'default' being the original RoPE implementation.
`factor` (`float`, *optional*):
Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In
most scaling types, a `factor` of x will enable the model to handle sequences of length x *
original maximum pre-trained length.
`original_max_position_embeddings` (`int`, *optional*):
Used with 'dynamic', 'longrope' and 'llama3'. The original max position embeddings used during
pretraining.
`attention_factor` (`float`, *optional*):
Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention
computation. If unspecified, it defaults to value recommended by the implementation, using the
`factor` field to infer the suggested value.
`beta_fast` (`float`, *optional*):
Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear
ramp function. If unspecified, it defaults to 32.
`beta_slow` (`float`, *optional*):
Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear
ramp function. If unspecified, it defaults to 1.
`short_factor` (`List[float]`, *optional*):
Only used with 'longrope'. The scaling factor to be applied to short contexts (<
`original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
size divided by the number of attention heads divided by 2
`long_factor` (`List[float]`, *optional*):
Only used with 'longrope'. The scaling factor to be applied to long contexts (<
`original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
size divided by the number of attention heads divided by 2
`low_freq_factor` (`float`, *optional*):
Only used with 'llama3'. Scaling factor applied to low frequency components of the RoPE
`high_freq_factor` (`float`, *optional*):
Only used with 'llama3'. Scaling factor applied to high frequency components of the RoPE
qkv_bias (`bool`, *optional*, defaults to `False`):
Whether to use a bias in the query, key and value projection layers during self-attention.
attention_dropout (`float`, *optional*, defaults to 0.0):
The dropout ratio for the attention probabilities.
bias (`bool`, *optional*, defaults to `False`):
Whether to use a bias in o_proj, up_proj, down_proj and gate_proj layers.
head_dim (`int`, *optional*):
The attention head dimension. If None, it will default to hidden_size // num_heads
```python
>>> from transformers import InternLM3Model, InternLM3Config
>>> # Initializing a InternLM3 style configuration
>>> configuration = InternLM3Config()
>>> # Initializing a model from the InternLM3-8B style configuration
>>> model = InternLM3Model(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
```"""
model_type = "internlm3"
keys_to_ignore_at_inference = ["past_key_values"]
# Default tensor parallel plan for base model `InternLM3`
base_model_tp_plan = {
"layers.*.self_attn.q_proj": "colwise",
"layers.*.self_attn.k_proj": "colwise",
"layers.*.self_attn.v_proj": "colwise",
"layers.*.self_attn.o_proj": "rowwise",
"layers.*.mlp.gate_proj": "colwise",
"layers.*.mlp.up_proj": "colwise",
"layers.*.mlp.down_proj": "rowwise",
}
def __init__(
self,
vocab_size=128512,
hidden_size=4096,
intermediate_size=11008,
num_hidden_layers=32,
num_attention_heads=32,
num_key_value_heads=32,
hidden_act="silu",
max_position_embeddings=32768,
initializer_range=0.02,
rms_norm_eps=1e-6,
use_cache=True,
tie_word_embeddings=False,
rope_theta=10000.0,
rope_scaling=None,
qkv_bias=False,
attention_dropout=0.0,
bias=False,
head_dim=None,
**kwargs,
):
self.vocab_size = vocab_size
self.max_position_embeddings = max_position_embeddings
self.hidden_size = hidden_size
self.intermediate_size = intermediate_size
self.num_hidden_layers = num_hidden_layers
self.num_attention_heads = num_attention_heads
# for backward compatibility
if num_key_value_heads is None:
num_key_value_heads = num_attention_heads
self.num_key_value_heads = num_key_value_heads
self.hidden_act = hidden_act
self.initializer_range = initializer_range
self.rms_norm_eps = rms_norm_eps
self.use_cache = use_cache
self.rope_theta = rope_theta
self.rope_scaling = rope_scaling
self.qkv_bias = qkv_bias
self.attention_dropout = attention_dropout
self.bias = bias
self.head_dim = head_dim if head_dim is not None else self.hidden_size // self.num_attention_heads
# Validate the correctness of rotary position embeddings parameters
# BC: if there is a 'type' field, move it to 'rope_type'.
if self.rope_scaling is not None and "type" in self.rope_scaling:
self.rope_scaling["rope_type"] = self.rope_scaling["type"]
rope_config_validation(self)
super().__init__(
tie_word_embeddings=tie_word_embeddings,
**kwargs,
)

9
generation_config.json Normal file
View File

@@ -0,0 +1,9 @@
{
"bos_token_id": 1,
"eos_token_id": [
2,
128131
],
"pad_token_id": 2,
"transformers_version": "4.52.4"
}

3
model-00001-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3cc2ab11da053663f6986439c78f247e825a0bea4b1a8d84fe2b7ab90babfef6
size 4999820088

3
model-00002-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d7b9d188d6d9f08d22147ddda85b409b483d4fb26d7e3398a8361faf0dcaef43
size 4928568784

3
model-00003-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:94879f554676d9b7af91fedca319c1cdfa9d1ac6eb6b4a79833e6b3d0a914206
size 4928568784

3
model-00004-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e93fc9551ce0a3d04c734fc4d133310abc9ca9212fae4b0b49e57f4327e79867
size 2751575736

442
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,442 @@
{
"metadata": {
"total_size": 17608482816
},
"weight_map": {
"lm_head.weight": "model-00004-of-00004.safetensors",
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.36.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.36.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.36.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.36.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.36.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.36.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.36.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.36.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.36.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.37.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.37.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.37.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.37.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.37.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.37.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.37.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.37.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.37.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.38.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.38.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.38.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.38.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.38.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.38.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.38.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.38.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.38.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.39.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.39.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.39.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.39.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.39.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.39.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.39.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.39.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.39.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.40.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.40.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.40.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.40.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.40.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.40.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.40.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.40.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.40.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.41.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.41.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.41.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.41.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.41.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.41.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.41.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.41.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.41.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.42.input_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.42.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.42.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.42.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.42.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.42.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.42.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.42.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.42.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.43.input_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.43.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.43.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.43.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.43.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.43.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.43.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.43.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.43.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.44.input_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.44.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.44.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.44.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.44.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.44.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.44.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.44.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.44.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.45.input_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.45.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.45.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.45.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.45.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.45.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.45.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.45.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.45.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.46.input_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.46.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.46.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.46.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.46.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.46.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.46.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.46.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.46.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.47.input_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.47.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.47.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.47.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.47.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.47.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.47.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.47.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.47.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.norm.weight": "model-00004-of-00004.safetensors"
}
}

1190
modeling_internlm3.py Normal file
View File

File diff suppressed because it is too large Load Diff

54
special_tokens_map.json Normal file
View File

@@ -0,0 +1,54 @@
{
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|action_start|>",
"<|action_end|>",
"<|interpreter|>",
"<|plugin|>",
"<restate>",
"</restate>",
"<planning>",
"</planning>",
"<recollect>",
"</recollect>",
"<execution>",
"</execution>",
"<review>",
"</review>",
"<summarize>",
"</summarize>",
"<retry>",
"</retry>",
"<conclude>",
"</conclude>"
],
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

294
tokenization_internlm3.py Normal file
View File

@@ -0,0 +1,294 @@
import os
from shutil import copyfile
from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple
import sentencepiece as spm
from transformers.tokenization_utils import AddedToken, PreTrainedTokenizer
from transformers.utils import logging
if TYPE_CHECKING:
from transformers.tokenization_utils_base import TextInput
logger = logging.get_logger(__name__)
VOCAB_FILES_NAMES = {"vocab_file": "tokenizer.model"}
SPIECE_UNDERLINE = "▁"
class InternLM3Tokenizer(PreTrainedTokenizer):
"""
Construct a InternLM3 tokenizer. Based on byte-level Byte-Pair-Encoding. The default padding token is unset as there is
no padding token in the original model.
Args:
vocab_file (`str`):
Path to the vocabulary file.
unk_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `"<unk>"`):
The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
token instead.
bos_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `"<s>"`):
The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.
eos_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `"</s>"`):
The end of sequence token.
pad_token (`str` or `tokenizers.AddedToken`, *optional*):
A special token used to make arrays of tokens the same size for batching purpose. Will then be ignored by
attention mechanisms or loss computation.
sp_model_kwargs (`Dict[str, Any]`, `Optional`, *optional*):
Will be passed to the `SentencePieceProcessor.__init__()` method. The [Python wrapper for
SentencePiece](https://github.com/google/sentencepiece/tree/master/python) can be used, among other things,
to set:
- `enable_sampling`: Enable subword regularization.
- `nbest_size`: Sampling parameters for unigram. Invalid for BPE-Dropout.
- `nbest_size = {0,1}`: No sampling is performed.
- `nbest_size > 1`: samples from the nbest_size results.
- `nbest_size < 0`: assuming that nbest_size is infinite and samples from the all hypothesis (lattice)
using forward-filtering-and-backward-sampling algorithm.
- `alpha`: Smoothing parameter for unigram sampling, and dropout probability of merge operations for
BPE-dropout.
add_bos_token (`bool`, *optional*, defaults to `True`):
Whether or not to add an `bos_token` at the start of sequences.
add_eos_token (`bool`, *optional*, defaults to `False`):
Whether or not to add an `eos_token` at the end of sequences.
clean_up_tokenization_spaces (`bool`, *optional*, defaults to `False`):
Whether or not to cleanup spaces after decoding, cleanup consists in removing potential artifacts like
extra spaces.
use_default_system_prompt (`bool`, *optional*, defaults to `False`):
Whether or not the default system prompt for InternLM3 should be used.
spaces_between_special_tokens (`bool`, *optional*, defaults to `False`):
Whether or not to add spaces between special tokens.
spaces_for_interleaved_special_tokens (`bool`, *optional*, defaults to `False`):
Whether or not to add spaces between special tokens that are interleaved with normal tokens.
add_prefix_space (`bool`, *optional*, defaults to `True`):
Whether or not to add an initial space to the input. This allows to treat the leading word just as any
other word. Again, this should be set with `from_slow=True` to make sure it's taken into account.
"""
vocab_files_names = VOCAB_FILES_NAMES
model_input_names = ["input_ids", "attention_mask"]
def __init__(
self,
vocab_file,
unk_token="<unk>",
bos_token="<s>",
eos_token="</s>",
pad_token=None,
sp_model_kwargs: Optional[Dict[str, Any]] = None,
add_bos_token=True,
add_eos_token=False,
clean_up_tokenization_spaces=False,
use_default_system_prompt=False,
spaces_between_special_tokens=False,
spaces_for_interleaved_special_tokens=False,
add_prefix_space=True,
**kwargs,
):
self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
bos_token = AddedToken(bos_token, normalized=False, special=True) if isinstance(bos_token, str) else bos_token
eos_token = AddedToken(eos_token, normalized=False, special=True) if isinstance(eos_token, str) else eos_token
unk_token = AddedToken(unk_token, normalized=False, special=True) if isinstance(unk_token, str) else unk_token
pad_token = AddedToken(pad_token, normalized=False, special=True) if isinstance(pad_token, str) else pad_token
self.vocab_file = vocab_file
self.add_bos_token = add_bos_token
self.add_eos_token = add_eos_token
self.use_default_system_prompt = use_default_system_prompt
self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
self.sp_model.Load(vocab_file)
self.add_prefix_space = add_prefix_space
self.spaces_for_interleaved_special_tokens = spaces_for_interleaved_special_tokens
vocab_size = self.sp_model.get_piece_size()
self.decoder = {i: self.sp_model.id_to_piece(i) for i in range(vocab_size)}
super().__init__(
bos_token=bos_token,
eos_token=eos_token,
unk_token=unk_token,
pad_token=pad_token,
add_bos_token=add_bos_token,
add_eos_token=add_eos_token,
sp_model_kwargs=sp_model_kwargs,
clean_up_tokenization_spaces=clean_up_tokenization_spaces,
use_default_system_prompt=use_default_system_prompt,
spaces_between_special_tokens=spaces_between_special_tokens,
add_prefix_space=add_prefix_space,
**kwargs,
)
def __getstate__(self):
state = self.__dict__.copy()
state["sp_model"] = None
state["sp_model_proto"] = self.sp_model.serialized_model_proto()
return state
def __setstate__(self, d):
self.__dict__.update(d)
self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
self.sp_model.LoadFromSerializedProto(self.sp_model_proto)
@property
def vocab_size(self):
"""Returns vocab size"""
return self.sp_model.get_piece_size()
def get_vocab(self):
"""Returns vocab as a dict"""
vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
vocab.update(self.added_tokens_encoder)
return vocab
def tokenize(self, text: "TextInput", **kwargs) -> List[str]:
"""
Args:
text: TextInput
Simply calls PreTrainedTokenizer's method
"""
return super().tokenize(text, **kwargs)
def _tokenize(self, text, **kwargs):
"""
Args:
text: TextInput
Returns a tokenized string. The Gemma tokenizer never adds a prefix space.
"""
return self.sp_model.encode(text, out_type=str)
def _convert_token_to_id(self, token):
"""Converts a token (str) in an id using the vocab."""
return self.sp_model.piece_to_id(token)
def _convert_id_to_token(self, index):
"""Converts an index (integer) in a token (str) using the vocab."""
return self.decoder.get(index, "")
def convert_tokens_to_string(self, tokens):
"""Converts a sequence of tokens (string) in a single string."""
# since we manually add the prefix space, we have to remove it when decoding
if tokens[0].startswith(SPIECE_UNDERLINE) and self.add_prefix_space:
tokens[0] = tokens[0][1:]
current_sub_tokens = []
out_string = ""
prev_is_special = False
for i, token in enumerate(tokens):
# make sure that special tokens are not decoded using sentencepiece model
if token in self.all_special_tokens:
if not prev_is_special and i != 0 and self.spaces_for_interleaved_special_tokens:
out_string += " "
out_string += self.sp_model.decode(current_sub_tokens) + token
prev_is_special = True
current_sub_tokens = []
else:
if (
prev_is_special
and i == 1
and self.add_prefix_space
and not token.startswith(SPIECE_UNDERLINE)
and self.spaces_for_interleaved_special_tokens
):
out_string += " "
current_sub_tokens.append(token)
prev_is_special = False
out_string += self.sp_model.decode(current_sub_tokens)
return out_string
def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]:
"""
Save the vocabulary and special tokens file to a directory.
Args:
save_directory (`str`):
The directory in which to save the vocabulary.
Returns:
`Tuple(str)`: Paths to the files saved.
"""
if not os.path.isdir(save_directory):
logger.error(f"Vocabulary path ({save_directory}) should be a directory")
return
out_vocab_file = os.path.join(save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"])
if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
copyfile(self.vocab_file, out_vocab_file)
elif not os.path.isfile(self.vocab_file):
with open(out_vocab_file, "wb") as fi:
content_spiece_model = self.sp_model.serialized_model_proto()
fi.write(content_spiece_model)
return (out_vocab_file,)
def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
bos_token_id = [self.bos_token_id] if self.add_bos_token else []
eos_token_id = [self.eos_token_id] if self.add_eos_token else []
output = bos_token_id + token_ids_0 + eos_token_id
if token_ids_1 is not None:
output = output + bos_token_id + token_ids_1 + eos_token_id
return output
def get_special_tokens_mask(
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
) -> List[int]:
"""
Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
special tokens using the tokenizer `prepare_for_model` method.
Args:
token_ids_0 (`List[int]`):
List of IDs.
token_ids_1 (`List[int]`, *optional*):
Optional second list of IDs for sequence pairs.
already_has_special_tokens (`bool`, *optional*, defaults to `False`):
Whether or not the token list is already formatted with special tokens for the model.
Returns:
`List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
"""
if already_has_special_tokens:
return super().get_special_tokens_mask(token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True)
bos_token_id = [1] if self.add_bos_token else []
eos_token_id = [1] if self.add_eos_token else []
if token_ids_1 is None:
return bos_token_id + ([0] * len(token_ids_0)) + eos_token_id
return bos_token_id + ([0] * len(token_ids_0)) + eos_token_id + bos_token_id + ([0] * len(token_ids_1)) + eos_token_id
def create_token_type_ids_from_sequences(self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None) -> List[int]:
"""
Creates a mask from the two sequences passed to be used in a sequence-pair classification task. An ALBERT
sequence pair mask has the following format:
```
0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1
| first sequence | second sequence |
```
if token_ids_1 is None, only returns the first portion of the mask (0s).
Args:
token_ids_0 (`List[int]`):
List of ids.
token_ids_1 (`List[int]`, *optional*):
Optional second list of IDs for sequence pairs.
Returns:
`List[int]`: List of [token type IDs](../glossary#token-type-ids) according to the given sequence(s).
"""
bos_token_id = [self.bos_token_id] if self.add_bos_token else []
eos_token_id = [self.eos_token_id] if self.add_eos_token else []
output = [0] * len(bos_token_id + token_ids_0 + eos_token_id)
if token_ids_1 is not None:
output += [1] * len(bos_token_id + token_ids_1 + eos_token_id)
return output

3
tokenizer.model Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bcacff3229854f5103ee7a85473a30ca9a8b3a68f3aae9b7479574b23ac2256b
size 2475075

248
tokenizer_config.json Normal file
View File

@@ -0,0 +1,248 @@
{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": true,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128111": {
"content": "<restate>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128112": {
"content": "</restate>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128113": {
"content": "<planning>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128114": {
"content": "</planning>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128115": {
"content": "<recollect>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128116": {
"content": "</recollect>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128117": {
"content": "<execution>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128118": {
"content": "</execution>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128119": {
"content": "<review>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128120": {
"content": "</review>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128121": {
"content": "<summarize>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128122": {
"content": "</summarize>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128123": {
"content": "<retry>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128124": {
"content": "</retry>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128125": {
"content": "<conclude>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128126": {
"content": "</conclude>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128127": {
"content": "<|plugin|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128128": {
"content": "<|interpreter|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128129": {
"content": "<|action_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128130": {
"content": "<|action_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128131": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128132": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|action_start|>",
"<|action_end|>",
"<|interpreter|>",
"<|plugin|>",
"<restate>",
"</restate>",
"<planning>",
"</planning>",
"<recollect>",
"</recollect>",
"<execution>",
"</execution>",
"<review>",
"</review>",
"<summarize>",
"</summarize>",
"<retry>",
"</retry>",
"<conclude>",
"</conclude>"
],
"auto_map": {
"AutoTokenizer": [
"tokenization_internlm3.InternLM3Tokenizer",
null
]
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"extra_special_tokens": {},
"model_max_length": 1000000000000000019884624838656,
"pad_token": "</s>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "InternLM3Tokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}