Functions — github.com/Alpha-VLLM/LLaMA2-Accessory

hub / github.com/Alpha-VLLM/LLaMA2-Accessory / functions

Functions1,094 in github.com/Alpha-VLLM/LLaMA2-Accessory

⨍ Functions 1,094◇ Types & classes 182

↓ 1 callersMethod_allocate_kv_cache

(self, max_batch_size: int)

accessory/model/LLM/internlm.py:381

↓ 1 callersMethod_allocate_kv_cache

(self, max_batch_size: int)

accessory/model/LLM/llama_ens5_light.py:498

↓ 1 callersFunction_clean_numbers

Clean Numbers in the given string >>> _clean_numbers(None, "Hello 123") 'Hello 123' >>> _clean_numbers(None, "Hello 1234") 'Hell

light-eval/src/eval_utils/math_util.py:62

↓ 1 callersMethod_collect_annotations_and_save_to_cache

(self, cache_dir)

Large-DiT-T2I/data/dataset.py:114

↓ 1 callersMethod_destroy_kv_cache

(self)

accessory/model/LLM/mixtral_peft.py:501

↓ 1 callersMethod_destroy_kv_cache

(self)

accessory/model/LLM/llama_ens10.py:540

↓ 1 callersMethod_destroy_kv_cache

(self)

accessory/model/LLM/falcon.py:376

↓ 1 callersMethod_destroy_kv_cache

(self)

accessory/model/LLM/llama_ens5.py:537

↓ 1 callersMethod_destroy_kv_cache

(self)

accessory/model/LLM/llama.py:433

↓ 1 callersMethod_destroy_kv_cache

(self)

accessory/model/LLM/llama_qformerv2_peft.py:386

↓ 1 callersMethod_destroy_kv_cache

(self)

accessory/model/LLM/mixtral_sparse_ens5.py:833

↓ 1 callersMethod_destroy_kv_cache

(self)

accessory/model/LLM/llama_ens5p2.py:546

↓ 1 callersMethod_destroy_kv_cache

(self)

accessory/model/LLM/mixtral_sparse.py:673

↓ 1 callersMethod_destroy_kv_cache

(self)

accessory/model/LLM/llama_ens.py:519

↓ 1 callersMethod_destroy_kv_cache

(self)

accessory/model/LLM/llama_qformerv2.py:367

↓ 1 callersMethod_destroy_kv_cache

(self)

accessory/model/LLM/mixtral.py:480

↓ 1 callersMethod_destroy_kv_cache

(self)

accessory/model/LLM/llama_peft.py:406

↓ 1 callersMethod_destroy_kv_cache

(self)

accessory/model/LLM/llama_ens_light.py:479

↓ 1 callersMethod_destroy_kv_cache

(self)

accessory/model/LLM/llama_adapter.py:518

↓ 1 callersMethod_destroy_kv_cache

(self)

accessory/model/LLM/llama_ens_peft.py:533

↓ 1 callersMethod_destroy_kv_cache

(self)

accessory/model/LLM/mixtral_sparse_ens.py:796

↓ 1 callersMethod_destroy_kv_cache

(self)

accessory/model/LLM/internlm.py:385

↓ 1 callersMethod_destroy_kv_cache

(self)

accessory/model/LLM/llama_ens5_light.py:502

↓ 1 callersFunction_fix_a_slash_b

(string)

accessory/eval_mm/utils/math_utils.py:164

↓ 1 callersFunction_fix_fracs

(string)

accessory/eval_mm/utils/math_utils.py:131

↓ 1 callersFunction_fix_sqrt

(string)

accessory/eval_mm/utils/math_utils.py:189

↓ 1 callersMethod_forward_attention

(self, x, start_pos, freqs_cis, mask)

accessory/model/LLM/mixtral_peft.py:330

↓ 1 callersMethod_forward_attention

(self, x, start_pos, freqs_cis, mask)

accessory/model/LLM/llama_ens10.py:240

↓ 1 callersMethod_forward_attention

(self, x, start_pos, freqs_cis, mask)

accessory/model/LLM/llama_ens5.py:240

↓ 1 callersMethod_forward_attention

(self, x, start_pos, freqs_cis, mask)

accessory/model/LLM/llama.py:279

↓ 1 callersMethod_forward_attention

(self, x, start_pos, freqs_cis, mask)

accessory/model/LLM/llama_qformerv2_peft.py:248

↓ 1 callersMethod_forward_attention

(self, x, start_pos, freqs_cis, mask)

accessory/model/LLM/mixtral_sparse_ens5.py:518

↓ 1 callersMethod_forward_attention

(self, x, start_pos, freqs_cis, mask)

accessory/model/LLM/llama_ens5p2.py:240

↓ 1 callersMethod_forward_attention

(self, x, start_pos, freqs_cis, mask)

accessory/model/LLM/mixtral_sparse.py:512

↓ 1 callersMethod_forward_attention

(self, x, start_pos, freqs_cis, mask)

accessory/model/LLM/llama_ens.py:240

↓ 1 callersMethod_forward_attention

(self, x, start_pos, freqs_cis, mask)

accessory/model/LLM/llama_qformerv2.py:234

↓ 1 callersMethod_forward_attention

(self, x, start_pos, freqs_cis, mask)

accessory/model/LLM/mixtral.py:318

↓ 1 callersMethod_forward_attention

(self, x, start_pos, freqs_cis, mask)

accessory/model/LLM/llama_peft.py:249

↓ 1 callersMethod_forward_attention

(self, x, start_pos, freqs_cis, mask)

accessory/model/LLM/llama_ens_light.py:241

↓ 1 callersMethod_forward_attention

(self, x, start_pos, freqs_cis, mask, prefix, prefix_gate, prefix_new_gate)

accessory/model/LLM/llama_adapter.py:289

↓ 1 callersMethod_forward_attention

(self, x, start_pos, freqs_cis, mask)

accessory/model/LLM/llama_ens_peft.py:255

↓ 1 callersMethod_forward_attention

(self, x, start_pos, freqs_cis, mask)

accessory/model/LLM/mixtral_sparse_ens.py:516

↓ 1 callersMethod_forward_attention

(self, x, start_pos, freqs_cis, mask)

accessory/model/LLM/llama_ens5_light.py:241

↓ 1 callersMethod_forward_ffn

(self, h)

accessory/model/LLM/mixtral_peft.py:327

↓ 1 callersMethod_forward_ffn

(self, h)

accessory/model/LLM/llama_ens10.py:237

↓ 1 callersMethod_forward_ffn

(self, h)

accessory/model/LLM/llama_ens5.py:237

↓ 1 callersMethod_forward_ffn

(self, h)

accessory/model/LLM/llama.py:276

↓ 1 callersMethod_forward_ffn

(self, h)

accessory/model/LLM/llama_qformerv2_peft.py:245

↓ 1 callersMethod_forward_ffn

(self, h)

accessory/model/LLM/mixtral_sparse_ens5.py:515

↓ 1 callersMethod_forward_ffn

(self, h)

accessory/model/LLM/llama_ens5p2.py:237

↓ 1 callersMethod_forward_ffn

(self, h)

accessory/model/LLM/mixtral_sparse.py:509

↓ 1 callersMethod_forward_ffn

(self, h)

accessory/model/LLM/llama_ens.py:237

↓ 1 callersMethod_forward_ffn

(self, h)

accessory/model/LLM/llama_qformerv2.py:231

↓ 1 callersMethod_forward_ffn

(self, h)

accessory/model/LLM/mixtral.py:315

↓ 1 callersMethod_forward_ffn

(self, h)

accessory/model/LLM/llama_peft.py:246

↓ 1 callersMethod_forward_ffn

(self, h)

accessory/model/LLM/llama_ens_light.py:238

↓ 1 callersMethod_forward_ffn

(self, h)

accessory/model/LLM/llama_adapter.py:286

↓ 1 callersMethod_forward_ffn

(self, h)

accessory/model/LLM/llama_ens_peft.py:252

↓ 1 callersMethod_forward_ffn

(self, h)

accessory/model/LLM/mixtral_sparse_ens.py:513

↓ 1 callersMethod_forward_ffn

(self, h)

accessory/model/LLM/llama_ens5_light.py:238

↓ 1 callersMethod_forward_silu_gating

(self, x1, x3)

Large-DiT-ImageNet/models.py:348

↓ 1 callersMethod_forward_silu_gating

(self, x1, x3)

Large-DiT-T2I/models/model.py:382

↓ 1 callersMethod_get_cache_dir

(config_path)

Large-DiT-T2I/data/dataset.py:141

↓ 1 callersMethod_load_annotations_from_cache

(cache_dir)

Large-DiT-T2I/data/dataset.py:150

↓ 1 callersMethod_load_balancing_loss

Args: expert_scores: size(n_tokens, num_experts), last dim sum to 1 flat_expert_indices: size(n_tokens * num_experts

accessory/model/LLM/mixtral_peft.py:257

↓ 1 callersMethod_load_balancing_loss

Args: expert_scores: size(n_tokens, num_experts), last dim sum to 1 tokens_per_expert: (num_experts) Return

accessory/model/LLM/mixtral_sparse_ens5.py:288

↓ 1 callersMethod_load_balancing_loss

Args: expert_scores: size(n_tokens, num_experts), last dim sum to 1 tokens_per_expert: (num_experts) Return

accessory/model/LLM/mixtral_sparse.py:282

↓ 1 callersMethod_load_balancing_loss

Args: expert_scores: size(n_tokens, num_experts), last dim sum to 1 flat_expert_indices: size(n_tokens * num_experts

accessory/model/LLM/mixtral.py:246

↓ 1 callersMethod_load_balancing_loss

Args: expert_scores: size(n_tokens, num_experts), last dim sum to 1 tokens_per_expert: (num_experts) Return

accessory/model/LLM/mixtral_sparse_ens.py:286

↓ 1 callersFunction_load_checkpoint_and_merge_ranks

( model: nn.Module, ckpt_path: str, ckpt_mp_world_size: int, verbose: bool, format: str, )

accessory/util/tensor_parallel.py:83

↓ 1 callersFunction_load_checkpoint_and_redistribute_general

( model: nn.Module, ckpt_path: str, ckpt_mp_world_size: int, verbose: bool, format: str, )

accessory/util/tensor_parallel.py:164

↓ 1 callersFunction_load_checkpoint_and_split_rank

( model: nn.Module, ckpt_path: str, ckpt_mp_world_size: int, verbose: bool, format: str, )

accessory/util/tensor_parallel.py:133

↓ 1 callersFunction_load_optimizer

()

accessory/util/misc.py:474

↓ 1 callersFunction_load_other

()

accessory/util/misc.py:489

↓ 1 callersFunction_load_rank_specific

()

accessory/util/misc.py:510

↓ 1 callersMethod_make_causal_mask

(self, q_len: int, kv_len: int)

accessory/model/LLM/mixtral_peft.py:194

↓ 1 callersMethod_make_causal_mask

(self, q_len: int, kv_len: int)

accessory/model/LLM/llama_ens10.py:181

↓ 1 callersMethod_make_causal_mask

(self, q_len: int, kv_len: int)

accessory/model/LLM/falcon.py:201

↓ 1 callersMethod_make_causal_mask

(self, q_len: int, kv_len: int)

accessory/model/LLM/llama_ens5.py:181

↓ 1 callersMethod_make_causal_mask

(self, q_len: int, kv_len: int)

accessory/model/LLM/llama.py:220

↓ 1 callersMethod_make_causal_mask

(self, q_len: int, kv_len: int)

accessory/model/LLM/llama_qformerv2_peft.py:184

↓ 1 callersMethod_make_causal_mask

(self, q_len: int, kv_len: int)

accessory/model/LLM/mixtral_sparse_ens5.py:209

↓ 1 callersMethod_make_causal_mask

(self, q_len: int, kv_len: int)

accessory/model/LLM/llama_ens5p2.py:181

↓ 1 callersMethod_make_causal_mask

(self, q_len: int, kv_len: int)

accessory/model/LLM/mixtral_sparse.py:203

↓ 1 callersMethod_make_causal_mask

(self, q_len: int, kv_len: int)

accessory/model/LLM/llama_ens.py:181

↓ 1 callersMethod_make_causal_mask

(self, q_len: int, kv_len: int)

accessory/model/LLM/llama_qformerv2.py:175

↓ 1 callersMethod_make_causal_mask

(self, q_len: int, kv_len: int)

accessory/model/LLM/mixtral.py:185

↓ 1 callersMethod_make_causal_mask

(self, q_len: int, kv_len: int)

accessory/model/LLM/llama_peft.py:185

↓ 1 callersMethod_make_causal_mask

(self, q_len: int, kv_len: int)

accessory/model/LLM/llama_ens_light.py:182

↓ 1 callersMethod_make_causal_mask

(self, q_len: int, kv_len: int)

accessory/model/LLM/llama_adapter.py:225

↓ 1 callersMethod_make_causal_mask

(self, q_len: int, kv_len: int)

accessory/model/LLM/llama_ens_peft.py:191

↓ 1 callersMethod_make_causal_mask

(self, q_len: int, kv_len: int)

accessory/model/LLM/mixtral_sparse_ens.py:207

↓ 1 callersMethod_make_causal_mask

(self, q_len: int, kv_len: int)

accessory/model/LLM/internlm.py:166

↓ 1 callersMethod_make_causal_mask

(self, q_len: int, kv_len: int)

accessory/model/LLM/llama_ens5_light.py:182

↓ 1 callersMethod_norm

Apply the RMSNorm normalization to the input tensor. Args: x (torch.Tensor): The input tensor.

accessory/model/components.py:28

↓ 1 callersMethod_prior_bpd

Get the prior KL term for the variational lower-bound, measured in bits-per-dim. This term can't be optimized, as it only dep

Large-DiT-ImageNet/diffusion/gaussian_diffusion.py:790

↓ 1 callersMethod_prior_bpd

Get the prior KL term for the variational lower-bound, measured in bits-per-dim. This term can't be optimized, as it only dep

Large-DiT-T2I/diffusion/gaussian_diffusion.py:817

↓ 1 callersMethod_probe_tokenizer_style

Given a sentence, e.g. "Hi my darling", some tokenizers (e.g. LLaMA's) will pose the following behavior: >>> # leading characters wil

accessory/model/tokenizer.py:90

↓ 1 callersFunction_remove_right_units

(string)

accessory/eval_mm/utils/math_utils.py:179

↓ 1 callersFunction_reset_world

()

accessory/model/multi_gpu_wrapper.py:119

← previous next →201–300 of 1,094, ranked by callers