Functions — github.com/TencentARC/MindOmni

CodeHub MCPcopy Create free account

hub / github.com/TencentARC/MindOmni / functions

Functions516 in github.com/TencentARC/MindOmni

⨍ Functions 516◇ Types & classes 89 ↳ Endpoints 2

(self, hidden_states)

src/image_decoder/modeling_phi3.py:124

(self, x, position_ids, seq_len=None)

src/image_decoder/modeling_phi3.py:148

(self, x, position_ids, seq_len=None)

src/image_decoder/modeling_phi3.py:179

(self, x, position_ids, seq_len=None)

src/image_decoder/modeling_phi3.py:219

(self, x, position_ids, seq_len=None)

src/image_decoder/modeling_phi3.py:260

( self, hidden_states: torch.Tensor, attention_mask: Optional[torch.Tensor] = None,

src/image_decoder/modeling_phi3.py:411

( self, hidden_states: torch.Tensor, attention_mask: Optional[torch.LongTensor] = None

src/image_decoder/modeling_phi3.py:501

( self, hidden_states: torch.Tensor, attention_mask: Optional[torch.Tensor] = None,

src/image_decoder/modeling_phi3.py:646

Args: hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)`

src/image_decoder/modeling_phi3.py:751

( self, input_ids: torch.LongTensor = None, attention_mask: Optional[torch.Tensor] = N

src/image_decoder/modeling_phi3.py:974

r""" Args: labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*): Labels for computing

src/image_decoder/modeling_phi3.py:1204

r""" labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*): Labels for computing the sequence classification/regression

src/image_decoder/modeling_phi3.py:1433

r""" labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*): Labels for computing the sequence classification/regression

src/image_decoder/modeling_phi3.py:1556

( self, input_ids: torch.LongTensor = None, attention_mask: Optional[torch.Tensor] = N

src/image_decoder/transformer.py:48

(self, t, dtype=torch.float32)

src/image_decoder/model.py:53

src/image_decoder/model.py:72

src/image_decoder/model.py:144

(self, hidden_states)

pretrain/modeling_phi3.py:124

(self, x, position_ids, seq_len=None)

pretrain/modeling_phi3.py:148

(self, x, position_ids, seq_len=None)

pretrain/modeling_phi3.py:179

(self, x, position_ids, seq_len=None)

pretrain/modeling_phi3.py:219

(self, x, position_ids, seq_len=None)

pretrain/modeling_phi3.py:260

( self, hidden_states: torch.Tensor, attention_mask: Optional[torch.Tensor] = None,

pretrain/modeling_phi3.py:411

( self, hidden_states: torch.Tensor, attention_mask: Optional[torch.LongTensor] = None

pretrain/modeling_phi3.py:501

( self, hidden_states: torch.Tensor, attention_mask: Optional[torch.Tensor] = None,

pretrain/modeling_phi3.py:646

Args: hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)`

pretrain/modeling_phi3.py:751

( self, input_ids: torch.LongTensor = None, attention_mask: Optional[torch.Tensor] = N

pretrain/modeling_phi3.py:974

r""" Args: labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*): Labels for computing

pretrain/modeling_phi3.py:1204

r""" labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*): Labels for computing the sequence classification/regression

pretrain/modeling_phi3.py:1433

r""" labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*): Labels for computing the sequence classification/regression

pretrain/modeling_phi3.py:1556

( self, input_ids: torch.LongTensor = None, attention_mask: Optional[torch.Tensor] = N

pretrain/transformer.py:62

(self, t, dtype=torch.float32)

pretrain/model.py:58

pretrain/model.py:77

pretrain/model.py:141

pretrain/model.py:159

Methodforward_with_cfg

(self, x, timestep, input_ids, input_img_latents, input_image_sizes, attention_mask, position_ids, cfg_scale,

pretrain/model.py:456

Methodforward_with_separate_cfg

(self, x, timestep, cfg_scale, past_key_values, use_kv_cache, offload_model,

src/image_decoder/model.py:368

Methodforward_with_separate_cfg

(self, x, timestep, input_ids, input_img_latents, input_image_sizes, attention_mask, position_ids, cfg_scale,

pretrain/model.py:472

Methodfrom_pretrained

(cls, model_name)

src/image_decoder/processor.py:55

Methodfrom_pretrained

(cls, model_name)

src/image_decoder/model.py:188

Methodfrom_pretrained

(cls, model_name)

pretrain/processor.py:43

Functiongenerate_func

( text, use_cot, cascade_thinking, height, width, guidance_scale, inference_steps, seed, separate_cfg_

Methodgeneration_score_reward

(prompts, completions, gt_prompt, clip_score_fn, generate_fuc, **kwargs)

rl-postrain/src/open-r1-multimodal/src/open_r1/vlm_modules/qwen_module.py:202

Methodget_custom_multimodal_keywords

rl-postrain/src/open-r1-multimodal/src/open_r1/vlm_modules/internvl_module.py:60

Methodget_custom_multimodal_keywords

rl-postrain/src/open-r1-multimodal/src/open_r1/vlm_modules/qwen_module.py:46

Methodget_custom_processing_keywords

rl-postrain/src/open-r1-multimodal/src/open_r1/vlm_modules/internvl_module.py:66

Methodget_custom_processing_keywords

rl-postrain/src/open-r1-multimodal/src/open_r1/vlm_modules/qwen_module.py:52

Methodget_data_info

pretrain/train_helper/subdata.py:107

Methodget_decoder

src/image_decoder/modeling_phi3.py:1198

Methodget_decoder

pretrain/modeling_phi3.py:1198

Methodget_input_embeddings

src/image_decoder/modeling_phi3.py:967

Methodget_input_embeddings

src/image_decoder/modeling_phi3.py:1178

Methodget_input_embeddings

src/image_decoder/modeling_phi3.py:1426

Methodget_input_embeddings

pretrain/modeling_phi3.py:1178

Methodget_input_embeddings

pretrain/modeling_phi3.py:1426

Methodget_model_class

(self, model_id: str, model_init_kwargs: dict)

rl-postrain/src/open-r1-multimodal/src/open_r1/vlm_modules/internvl_module.py:26

Methodget_model_class

(self, model_id: str, model_init_kwargs: dict)

rl-postrain/src/open-r1-multimodal/src/open_r1/vlm_modules/qwen_module.py:26

Methodget_non_generate_params

rl-postrain/src/open-r1-multimodal/src/open_r1/vlm_modules/internvl_module.py:63

Methodget_non_generate_params

rl-postrain/src/open-r1-multimodal/src/open_r1/vlm_modules/qwen_module.py:49

Methodget_output_embeddings

src/image_decoder/modeling_phi3.py:1186

Methodget_output_embeddings

pretrain/modeling_phi3.py:1186

Methodget_processing_class

rl-postrain/src/open-r1-multimodal/src/open_r1/vlm_modules/internvl_module.py:50

Methodget_processing_class

rl-postrain/src/open-r1-multimodal/src/open_r1/vlm_modules/qwen_module.py:40

Methodget_question_template

(task_type: str)

rl-postrain/src/open-r1-multimodal/src/open_r1/vlm_modules/internvl_module.py:135

Methodget_vision_modules_keywords

rl-postrain/src/open-r1-multimodal/src/open_r1/vlm_modules/internvl_module.py:57

Methodget_vision_modules_keywords

rl-postrain/src/open-r1-multimodal/src/open_r1/vlm_modules/qwen_module.py:43

Methodget_vlm_key

rl-postrain/src/open-r1-multimodal/src/open_r1/vlm_modules/internvl_module.py:23

Methodget_vlm_key

rl-postrain/src/open-r1-multimodal/src/open_r1/vlm_modules/qwen_module.py:23

Methodget_vlm_key

rl-postrain/src/open-r1-multimodal/src/open_r1/vlm_modules/vlm_module.py:11

rl-postrain/src/open-r1-multimodal/src/open_r1/vlm_modules/internvl_module.py:167

Methodiou_reward

Calculate IoU reward between predicted bounding box from InternVL model and ground truth bounding box.

rl-postrain/src/open-r1-multimodal/src/open_r1/vlm_modules/internvl_module.py:160

Methodiou_reward

Calculate IoU reward between predicted bounding box from Qwen model and ground truth bounding box.

rl-postrain/src/open-r1-multimodal/src/open_r1/vlm_modules/qwen_module.py:145

Methodis_embeds_input

rl-postrain/src/open-r1-multimodal/src/open_r1/vlm_modules/internvl_module.py:47

Functionkl_diffusion_loss

(pred, target, temperature0=3.0)

pretrain/train_helper/loss.py:158

(input, target, reduction='batchmean')

pretrain/train_helper/loss.py:43

(self, logs: dict[str, float], start_time: Optional[float] = None)

rl-postrain/src/open-r1-multimodal/src/open_r1/trainer/vllm_grpo_trainer.py:812

Methodmake_conversation

rl-postrain/src/open-r1-multimodal/src/open_r1/grpo_rec.py:153

Functionmake_conversation_from_jsonl

rl-postrain/src/open-r1-multimodal/src/open_r1/grpo_jsonl.py:993

Functionmake_conversation_from_jsonl

rl-postrain/src/open-r1-multimodal/src/open_r1/grpo_ust.py:1001

Methodmake_conversation_image

rl-postrain/src/open-r1-multimodal/src/open_r1/sft.py:138

Methodmake_conversation_image

rl-postrain/src/open-r1-multimodal/src/open_r1/grpo_rec.py:161

Methodmerge_lora

(self, lora_path: str)

pretrain/pipeline.py:106

(self, args: TrainingArguments, state: TrainerState, control: TrainerControl, **kwargs)

rl-postrain/src/open-r1-multimodal/src/open_r1/utils/callbacks.py:47

Methodpacked_llm_vae

(self, hidden_state, llm_padded_input_ids)

pretrain/model.py:348

Methodpost_model_init

(self, model, processing_class)

rl-postrain/src/open-r1-multimodal/src/open_r1/vlm_modules/internvl_module.py:41

Methodpost_model_init

(self, model, processing_class)

rl-postrain/src/open-r1-multimodal/src/open_r1/vlm_modules/qwen_module.py:37

Methodprepare_inputs_for_generation

( self, input_ids, past_key_values=None, attention_mask=None, inputs_e

src/image_decoder/modeling_phi3.py:1314

Methodprepare_inputs_for_generation

( self, input_ids, past_key_values=None, attention_mask=None, inputs_e

pretrain/modeling_phi3.py:1314

Methodprepare_model_inputs

(self, processing_class, prompts_text, images, return_tensors="pt", padding=True, padding_side="left", add_spe

rl-postrain/src/open-r1-multimodal/src/open_r1/vlm_modules/internvl_module.py:90

Methodprepare_model_inputs

(self, processing_class, prompts_text, images, return_tensors="pt", padding=True, padding_side="left", add_spe

rl-postrain/src/open-r1-multimodal/src/open_r1/vlm_modules/qwen_module.py:59

Methodprepare_prompt

(self, processing_class, inputs: dict[str, Union[torch.Tensor, Any]])

rl-postrain/src/open-r1-multimodal/src/open_r1/vlm_modules/internvl_module.py:69

Methodprepare_prompt

(self, processing_class, inputs: dict[str, Union[torch.Tensor, Any]])

rl-postrain/src/open-r1-multimodal/src/open_r1/vlm_modules/qwen_module.py:55

Methodprocess_image

src/image_decoder/processor.py:65

Functionprocess_raw_data

rl-postrain/src/open-r1-multimodal/local_scripts/prepare_hf_data.py:67

Functionprocess_single_item

rl-postrain/src/open-r1-multimodal/local_scripts/create_vision_cot_data.py:120

Functionprompt_fn

Assumes the model is either prompted to emit \\boxed{answer} or does so automatically

rl-postrain/src/open-r1-multimodal/src/open_r1/evaluate.py:37

Functionqwen2_5vl_forward

( self, input_ids: torch.LongTensor = None, attention_mask: Optional[torch.Tensor] = N

rl-postrain/src/open-r1-multimodal/src/open_r1/qwen2_5vl_monkey_patch.py:52

Functionqwen2_5vl_vision_flash_attn_forward

( self, hidden_states: torch.Tensor, cu_seqlens: torch.Tensor, rotary_pos_emb:

rl-postrain/src/open-r1-multimodal/src/open_r1/qwen2_5vl_monkey_patch.py:6

Functionrepetition_rewards

(completions, solution, **kwargs)

rl-postrain/src/open-r1-multimodal/src/open_r1/grpo_jsonl.py:686

Functionrepetition_rewards

(completions, solution, **kwargs)

rl-postrain/src/open-r1-multimodal/src/open_r1/grpo_ust.py:698

← previous next →401–500 of 516, ranked by callers