pyiqa.archs.q_align.cmp_modelling_mplug_owl2

Module Contents

pyiqa.archs.q_align.cmp_modelling_mplug_owl2.IGNORE_INDEX = -100[source]
pyiqa.archs.q_align.cmp_modelling_mplug_owl2.IMAGE_TOKEN_INDEX = -200[source]
pyiqa.archs.q_align.cmp_modelling_mplug_owl2.DEFAULT_IMAGE_TOKEN = '<|image|>'[source]
pyiqa.archs.q_align.cmp_modelling_mplug_owl2.tokenizer_image_token(prompt, tokenizer, image_token_index=IMAGE_TOKEN_INDEX, return_tensors=None)[source]
pyiqa.archs.q_align.cmp_modelling_mplug_owl2.expand2square(pil_img, background_color)[source]
pyiqa.archs.q_align.cmp_modelling_mplug_owl2.norm_cdf(x)[source]
pyiqa.archs.q_align.cmp_modelling_mplug_owl2.optimize_score_map_pytorch_cuda(c, seed=0, original_seed=20020, num_iterations=100)[source]
pyiqa.archs.q_align.cmp_modelling_mplug_owl2.softmax(logits)[source]
pyiqa.archs.q_align.cmp_modelling_mplug_owl2.update_matrix(anchor_matrix, scores, indices)[source]
class pyiqa.archs.q_align.cmp_modelling_mplug_owl2.MPLUGOwl2MetaModel(config)[source]
get_vision_tower()[source]
get_visual_abstractor()[source]
class pyiqa.archs.q_align.cmp_modelling_mplug_owl2.MPLUGOwl2MetaForCausalLM[source]

Bases: abc.ABC

Helper class that provides a standard way to create an ABC using inheritance.

abstractmethod get_model()[source]
encode_images(images)[source]
prepare_inputs_labels_for_multimodal(input_ids, attention_mask, past_key_values, labels, images)[source]
class pyiqa.archs.q_align.cmp_modelling_mplug_owl2.MPLUGOwl2LlamaModel(config: pyiqa.archs.q_align.configuration_mplug_owl2.MPLUGOwl2Config)[source]

Bases: MPLUGOwl2MetaModel, pyiqa.archs.q_align.modeling_llama2.LlamaModel

class pyiqa.archs.q_align.cmp_modelling_mplug_owl2.MPLUGOwl2LlamaForCausalLM(config)[source]

Bases: pyiqa.archs.q_align.modeling_llama2.LlamaForCausalLM, MPLUGOwl2MetaForCausalLM

Helper class that provides a standard way to create an ABC using inheritance.

get_model()[source]
score(image)[source]
forward(input_ids: torch.LongTensor = None, attention_mask: torch.Tensor | None = None, past_key_values: List[torch.FloatTensor] | None = None, inputs_embeds: torch.FloatTensor | None = None, labels: torch.LongTensor | None = None, use_cache: bool | None = None, output_attentions: bool | None = None, output_hidden_states: bool | None = None, images: torch.FloatTensor | None = None, return_dict: bool | None = None) → Tuple | transformers.modeling_outputs.CausalLMOutputWithPast[source]
prepare_inputs_for_generation(input_ids, past_key_values=None, attention_mask=None, inputs_embeds=None, **kwargs)[source]