Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/OpenSparseLLMs/Linear-MoE
/ functions
Functions
1,498 in github.com/OpenSparseLLMs/Linear-MoE
⨍
Functions
1,498
◇
Types & classes
227
↓ 1 callers
Function
_init_embedding_weights
(module)
toolkits/model_checkpoints_convertor/llama/hf2megatron.py:357
↓ 1 callers
Function
_init_embedding_weights
(module)
toolkits/model_checkpoints_convertor/mistral/hf2megatron.py:347
↓ 1 callers
Function
_init_embedding_weights
(module)
toolkits/model_checkpoints_convertor/baichuan/hf2te.py:208
↓ 1 callers
Function
_init_embedding_weights
(module)
toolkits/model_checkpoints_convertor/baichuan/checkpoint_reshaping_and_interoperability.py:341
↓ 1 callers
Function
_init_embedding_weights
(module)
toolkits/model_checkpoints_convertor/falcon/checkpoint_reshaping_and_interoperability.py:303
↓ 1 callers
Function
_init_embedding_weights
(module)
toolkits/model_checkpoints_convertor/yi/checkpoint_reshaping_and_interoperability.py:328
↓ 1 callers
Function
_init_embedding_weights
(module)
toolkits/model_checkpoints_convertor/galactica/checkpoint_reshaping_and_interoperability.py:330
↓ 1 callers
Function
_init_embedding_weights
(module)
toolkits/model_checkpoints_convertor/qwen/hf2megatron_qwen1.0.py:353
↓ 1 callers
Function
_init_embedding_weights
(module)
toolkits/model_checkpoints_convertor/qwen/hf2megatron_qwen1.5.py:376
↓ 1 callers
Function
_init_embedding_weights
(module)
toolkits/model_checkpoints_convertor/baichuan2/hf2te.py:192
↓ 1 callers
Function
_init_embedding_weights
(module)
toolkits/model_checkpoints_convertor/baichuan2/checkpoint_reshaping_and_interoperability.py:328
↓ 1 callers
Function
_initialize_distributed
Initialize torch.distributed and core model parallel.
linear_moe/initialize.py:87
↓ 1 callers
Function
_l2_norm_bwd
( x, dy, eps=1e-5, )
linear_moe/model/common_modules/l2norm.py:136
↓ 1 callers
Function
_l2_norm_fwd
( x, eps=1e-6 )
linear_moe/model/common_modules/l2norm.py:98
↓ 1 callers
Function
_layer_counts_match
(a: list, b: list)
linear_moe/sequence_modeling/mamba2/mamba_hybrid_layer_allocation.py:77
↓ 1 callers
Function
_load_tiktoken_bpe
(tiktoken_bpe_file: str)
linear_moe/tokenizer/tokenization_qwen_vl.py:45
↓ 1 callers
Method
_loglikelihood_tokens
(self, requests, disable_tqdm=False)
linear_moe/lm_evaluate.py:145
↓ 1 callers
Method
_make_r_io_base
(self, f, mode: str)
linear_moe/data/llama.py:98
↓ 1 callers
Method
_make_r_io_base
(self, f, mode: str)
linear_moe/data/starcoder.py:68
↓ 1 callers
Function
_mask_targets
(target, tokenized_lens, speakers)
linear_moe/data/llava/mm_pretrain_dataset.py:61
↓ 1 callers
Method
_model_call
(self, inps, attn_mask=None, labels=None)
linear_moe/lm_evaluate.py:93
↓ 1 callers
Function
_renest_sd
(sd)
toolkits/model_checkpoints_convertor/bloom/deepspeed_to_megatron_ori.py:90
↓ 1 callers
Function
_renest_sd
(sd)
toolkits/model_checkpoints_convertor/bloom/deepspeed_to_megatron.py:93
↓ 1 callers
Function
_save_checkpoint
(file_path, chkpt_sd)
toolkits/model_checkpoints_convertor/bloom/deepspeed_to_megatron_ori.py:84
↓ 1 callers
Function
_save_checkpoint
(file_path, chkpt_sd)
toolkits/model_checkpoints_convertor/bloom/deepspeed_to_megatron.py:87
↓ 1 callers
Method
_select_layers_for_pipeline_parallel
(self, layer_type_list)
linear_moe/sequence_modeling/ssm.py:177
↓ 1 callers
Method
_select_layers_for_pipeline_parallel
(self, layer_type_list)
linear_moe/sequence_modeling/mamba2/mamba_block.py:155
↓ 1 callers
Method
_setup_figure
(self, img)
linear_moe/tokenizer/tokenization_qwen_vl.py:455
↓ 1 callers
Method
_sharded_state_dict_for_glu
( self, module_name: str, module: torch.nn.Module, prefix: str, sharde
linear_moe/model/mixtral/transformer/mlp.py:171
↓ 1 callers
Method
_sharded_state_dict_for_glu
( self, module_name: str, module: torch.nn.Module, prefix: str, sharde
linear_moe/model/qwen2/transformer/mlp.py:171
↓ 1 callers
Method
_sharded_state_dict_for_glu
( self, module_name: str, module: torch.nn.Module, prefix: str, sharde
linear_moe/model/deepseek_v2/transformer/mlp.py:159
↓ 1 callers
Method
_sharded_state_dict_for_glu
( self, module_name: str, module: torch.nn.Module, prefix: str, sharde
linear_moe/model/llama3/transformer/mlp.py:152
↓ 1 callers
Function
_tokenize_prompts_and_batch
Given a set of prompts and number of tokens to generate: - tokenize prompts - set the sequence length to be the max of length of
linear_moe/generation/tokenization.py:123
↓ 1 callers
Function
_train
Train the model. Args: model (nn.Module): The model to train. optimizer (Optimizer): The optimizer to use for gradient updat
linear_moe/finetune_utils.py:159
↓ 1 callers
Function
add_args
(parser)
toolkits/model_checkpoints_convertor/llama/hf2mcore_70b.py:27
↓ 1 callers
Function
add_args
(parser)
toolkits/model_checkpoints_convertor/mistral/hf2mcore_mixtral.py:27
↓ 1 callers
Function
add_args
(parser)
toolkits/model_checkpoints_convertor/baichuan/hf2te.py:31
↓ 1 callers
Function
add_args
(parser)
toolkits/model_checkpoints_convertor/baichuan2/hf2te.py:30
↓ 1 callers
Function
add_checkpointing_args
(parser)
toolkits/model_checkpoints_convertor/falcon40b/checkpoint_reshaping_and_interoperability.py:33
↓ 1 callers
Function
add_checkpointing_args
(parser)
toolkits/model_checkpoints_convertor/llama/hf2megatron.py:34
↓ 1 callers
Function
add_checkpointing_args
(parser)
toolkits/model_checkpoints_convertor/llama/hf2mcore.py:35
↓ 1 callers
Function
add_checkpointing_args
(parser)
toolkits/model_checkpoints_convertor/mistral/hf2megatron.py:33
↓ 1 callers
Function
add_checkpointing_args
(parser)
toolkits/model_checkpoints_convertor/mistral/hf2mcore.py:29
↓ 1 callers
Function
add_checkpointing_args
(parser)
toolkits/model_checkpoints_convertor/baichuan/checkpoint_reshaping_and_interoperability.py:32
↓ 1 callers
Function
add_checkpointing_args
(parser)
toolkits/model_checkpoints_convertor/glm/checkpoint_reshaping_and_interoperability.py:25
↓ 1 callers
Function
add_checkpointing_args
(parser)
toolkits/model_checkpoints_convertor/falcon/checkpoint_reshaping_and_interoperability.py:33
↓ 1 callers
Function
add_checkpointing_args
(parser)
toolkits/model_checkpoints_convertor/glm130b/checkpoint_reshaping_and_interoperability.py:25
↓ 1 callers
Function
add_checkpointing_args
(parser)
toolkits/model_checkpoints_convertor/starcoder/checkpoint_reshaping_and_interoperability.py:28
↓ 1 callers
Function
add_checkpointing_args
(parser)
toolkits/model_checkpoints_convertor/chatglm/checkpoint_reshaping_and_interoperability.py:28
↓ 1 callers
Function
add_checkpointing_args
(parser)
toolkits/model_checkpoints_convertor/yi/checkpoint_reshaping_and_interoperability.py:33
↓ 1 callers
Function
add_checkpointing_args
(parser)
toolkits/model_checkpoints_convertor/galactica/checkpoint_reshaping_and_interoperability.py:32
↓ 1 callers
Function
add_checkpointing_args
(parser)
toolkits/model_checkpoints_convertor/qwen/hf2megatron_qwen1.0.py:37
↓ 1 callers
Function
add_checkpointing_args
(parser)
toolkits/model_checkpoints_convertor/qwen/hf2megablocks_qwen1.5.py:31
↓ 1 callers
Function
add_checkpointing_args
(parser)
toolkits/model_checkpoints_convertor/qwen/hf2megatron_qwen1.5.py:39
↓ 1 callers
Function
add_checkpointing_args
(parser)
toolkits/model_checkpoints_convertor/bloom/checkpoint_reshaping_and_interoperability.py:28
↓ 1 callers
Function
add_checkpointing_args
(parser)
toolkits/model_checkpoints_convertor/bloom/reward_model_to_megatron.py:28
↓ 1 callers
Function
add_checkpointing_args
(parser)
toolkits/model_checkpoints_convertor/baichuan2/checkpoint_reshaping_and_interoperability.py:32
↓ 1 callers
Function
add_extra_args
(parser)
toolkits/model_checkpoints_convertor/qwen/hf2mcore_qwen1.5_dense_gqa.py:27
↓ 1 callers
Function
add_megatron_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/falcon40b/checkpoint_reshaping_and_interoperability.py:65
↓ 1 callers
Function
add_megatron_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/llama/hf2megatron.py:66
↓ 1 callers
Function
add_megatron_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/llama/hf2mcore.py:74
↓ 1 callers
Function
add_megatron_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/mistral/hf2megatron.py:65
↓ 1 callers
Function
add_megatron_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/mistral/hf2mcore.py:68
↓ 1 callers
Function
add_megatron_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/baichuan/checkpoint_reshaping_and_interoperability.py:64
↓ 1 callers
Function
add_megatron_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/glm/checkpoint_reshaping_and_interoperability.py:54
↓ 1 callers
Function
add_megatron_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/falcon/checkpoint_reshaping_and_interoperability.py:65
↓ 1 callers
Function
add_megatron_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/glm130b/checkpoint_reshaping_and_interoperability.py:54
↓ 1 callers
Function
add_megatron_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/starcoder/checkpoint_reshaping_and_interoperability.py:57
↓ 1 callers
Function
add_megatron_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/chatglm/checkpoint_reshaping_and_interoperability.py:54
↓ 1 callers
Function
add_megatron_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/yi/checkpoint_reshaping_and_interoperability.py:65
↓ 1 callers
Function
add_megatron_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/galactica/checkpoint_reshaping_and_interoperability.py:64
↓ 1 callers
Function
add_megatron_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/qwen/hf2megatron_qwen1.0.py:69
↓ 1 callers
Function
add_megatron_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/qwen/hf2megablocks_qwen1.5.py:72
↓ 1 callers
Function
add_megatron_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/qwen/hf2megatron_qwen1.5.py:71
↓ 1 callers
Function
add_megatron_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/bloom/checkpoint_reshaping_and_interoperability.py:57
↓ 1 callers
Function
add_megatron_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/bloom/reward_model_to_megatron.py:57
↓ 1 callers
Function
add_megatron_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/baichuan2/checkpoint_reshaping_and_interoperability.py:64
↓ 1 callers
Function
add_model_args
(parser)
toolkits/model_checkpoints_convertor/deepseek/hf2mcore_deepseek_v2_moe.py:31
↓ 1 callers
Function
add_model_args
(parser)
toolkits/model_checkpoints_convertor/qwen/hf2mcore_qwen1.5_moe.py:29
↓ 1 callers
Function
add_model_args
(parser)
toolkits/model_checkpoints_convertor/qwen/hf2mcore_qwen1.5_dense_mha_to_moe.py:26
↓ 1 callers
Function
add_model_args
(parser)
toolkits/model_checkpoints_convertor/qwen/hf2mcore_qwen2_dense_and_moe_gqa.py:32
↓ 1 callers
Function
add_model_args
(parser)
toolkits/model_checkpoints_convertor/qwen/hf2mcore_qwen1.5_dense_mha.py:27
↓ 1 callers
Function
add_transformers_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/falcon40b/checkpoint_reshaping_and_interoperability.py:130
↓ 1 callers
Function
add_transformers_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/llama/hf2megatron.py:131
↓ 1 callers
Function
add_transformers_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/llama/hf2mcore.py:114
↓ 1 callers
Function
add_transformers_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/mistral/hf2megatron.py:130
↓ 1 callers
Function
add_transformers_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/mistral/hf2mcore.py:102
↓ 1 callers
Function
add_transformers_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/baichuan/checkpoint_reshaping_and_interoperability.py:129
↓ 1 callers
Function
add_transformers_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/falcon/checkpoint_reshaping_and_interoperability.py:130
↓ 1 callers
Function
add_transformers_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/starcoder/checkpoint_reshaping_and_interoperability.py:108
↓ 1 callers
Function
add_transformers_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/chatglm/checkpoint_reshaping_and_interoperability.py:112
↓ 1 callers
Function
add_transformers_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/yi/checkpoint_reshaping_and_interoperability.py:130
↓ 1 callers
Function
add_transformers_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/galactica/checkpoint_reshaping_and_interoperability.py:129
↓ 1 callers
Function
add_transformers_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/qwen/hf2megatron_qwen1.0.py:134
↓ 1 callers
Function
add_transformers_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/qwen/hf2megablocks_qwen1.5.py:107
↓ 1 callers
Function
add_transformers_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/qwen/hf2megatron_qwen1.5.py:136
↓ 1 callers
Function
add_transformers_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/bloom/checkpoint_reshaping_and_interoperability.py:108
↓ 1 callers
Function
add_transformers_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/bloom/reward_model_to_megatron.py:108
↓ 1 callers
Function
add_transformers_checkpoint_args
(parser)
toolkits/model_checkpoints_convertor/baichuan2/checkpoint_reshaping_and_interoperability.py:129
↓ 1 callers
Method
apply_aux_loss
Applies auxiliary loss to the MoE layer. Args: loss_func (callable): The loss function to be used. probs (torch.Tenso
linear_moe/model/mixtral/moe/router.py:166
← previous
next →
301–400 of 1,498, ranked by callers