Delete .ipynb_checkpoints

.ipynb_checkpoints/config-checkpoint.json

@@ -1,209 +0,0 @@
-{
-  "_commit_hash": null,
-  "_name_or_path": "/mnt/datasets_vlm/tianxie/LLM_Quantization/Skywork-R1V3-38B",
-  "architectures": [
-    "SkyworkChatModel"
-  ],
-  "auto_map": {
-    "AutoConfig": "configuration_skywork_chat.SkyworkChatConfig",
-    "AutoModel": "modeling_skywork_chat.SkyworkChatModel",
-    "AutoModelForCausalLM": "modeling_skywork_chat.SkyworkChatModel"
-  },
-  "downsample_ratio": 0.5,
-  "dynamic_image_size": true,
-  "force_image_size": 448,
-  "freeze_adapter": false,
-  "freeze_llm": false,
-  "freeze_vision": false,
-  "hidden_size": 5120,
-  "llm_config": {
-    "_attn_implementation_autoset": true,
-    "_name_or_path": "",
-    "add_cross_attention": false,
-    "architectures": [
-      "Qwen2ForCausalLM"
-    ],
-    "attention_dropout": 0.0,
-    "attn_implementation": "eager",
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": 151643,
-    "chunk_size_feed_forward": 0,
-    "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "early_stopping": false,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": 151645,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "hidden_act": "silu",
-    "hidden_size": 5120,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "initializer_range": 0.02,
-    "intermediate_size": 27648,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "max_position_embeddings": 32768,
-    "max_window_layers": 70,
-    "min_length": 0,
-    "model_type": "qwen2",
-    "no_repeat_ngram_size": 0,
-    "num_attention_heads": 40,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_hidden_layers": 64,
-    "num_key_value_heads": 8,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": null,
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
-    "quantization_config": {
-      "bits": 4,
-      "group_size": 128,
-      "quant_method": "awq",
-      "version": "gemm",
-      "zero_point": true
-    },
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "rms_norm_eps": 1e-06,
-    "rope_scaling": null,
-    "rope_theta": 1000000.0,
-    "sep_token_id": null,
-    "sliding_window": null,
-    "suppress_tokens": null,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": false,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": "bfloat16",
-    "torchscript": false,
-    "transformers_version": "4.46.3",
-    "typical_p": 1.0,
-    "use_bfloat16": true,
-    "use_cache": false,
-    "use_sliding_window": false,
-    "vocab_size": 151674
-  },
-  "max_dynamic_patch": 6,
-  "min_dynamic_patch": 1,
-  "model_type": "skywork_chat",
-  "pad2square": false,
-  "ps_version": "v2",
-  "select_layer": -1,
-  "template": "skywork-r1v-chat",
-  "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": null,
-  "use_backbone_lora": 0,
-  "use_llm_lora": 0,
-  "use_thumbnail": true,
-  "vision_config": {
-    "_attn_implementation_autoset": true,
-    "_name_or_path": "",
-    "add_cross_attention": false,
-    "architectures": [
-      "InternVisionModel"
-    ],
-    "attention_dropout": 0.0,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": null,
-    "chunk_size_feed_forward": 0,
-    "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "drop_path_rate": 0.1,
-    "dropout": 0.0,
-    "early_stopping": false,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": null,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "hidden_act": "gelu",
-    "hidden_size": 3200,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "image_size": 448,
-    "initializer_factor": 0.1,
-    "initializer_range": 1e-10,
-    "intermediate_size": 12800,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "layer_norm_eps": 1e-06,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "min_length": 0,
-    "model_type": "",
-    "no_repeat_ngram_size": 0,
-    "norm_type": "rms_norm",
-    "num_attention_heads": 25,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_channels": 3,
-    "num_hidden_layers": 45,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": null,
-    "patch_size": 14,
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
-    "qk_normalization": true,
-    "qkv_bias": false,
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "sep_token_id": null,
-    "suppress_tokens": null,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": "bfloat16",
-    "torchscript": false,
-    "transformers_version": "4.46.3",
-    "typical_p": 1.0,
-    "use_bfloat16": true,
-    "use_flash_attn": false
-  }
-}

.ipynb_checkpoints/configuration_skywork_chat-checkpoint.py

@@ -1,91 +0,0 @@
-import copy
-
-from transformers import AutoConfig, LlamaConfig
-from transformers.configuration_utils import PretrainedConfig
-from transformers.utils import logging
-
-from .configuration_skywork_vit import SkyworkVisionConfig
-from .configuration_skywork_lm2 import SkyworkLM2Config
-from transformers import Qwen2Config, Qwen2ForCausalLM
-
-logger = logging.get_logger(__name__)
-
-
-class SkyworkChatConfig(PretrainedConfig):
-    model_type = 'skywork_chat'
-    is_composition = True
-
-    def __init__(
-            self,
-            vision_config=None,
-            llm_config=None,
-            use_backbone_lora=0,
-            use_llm_lora=0,
-            select_layer=-1,
-            force_image_size=None,
-            downsample_ratio=0.5,
-            template=None,
-            dynamic_image_size=False,
-            use_thumbnail=False,
-            ps_version='v1',
-            min_dynamic_patch=1,
-            max_dynamic_patch=6,
-            **kwargs):
-        super().__init__(**kwargs)
-        if vision_config is None:
-            vision_config = {'architectures': ['SkyworkVisionModel']}
-            logger.info('vision_config is None. Initializing the SkyworkVisionConfig with default values.')
-
-        if llm_config is None:
-            llm_config = {'architectures': ['Qwen2ForCausalLM']}
-            logger.info('llm_config is None. Initializing the LlamaConfig config with default values (`LlamaConfig`).')
-
-        self.vision_config = SkyworkVisionConfig(**vision_config)
-        if llm_config.get('architectures')[0] == 'LlamaForCausalLM':
-            self.llm_config = LlamaConfig(**llm_config)
-        elif llm_config.get('architectures')[0] == 'Qwen2ForCausalLM':
-            self.llm_config = Qwen2Config(**llm_config)
-        else:
-            raise ValueError('Unsupported architecture: {}'.format(llm_config.get('architectures')[0]))
-
-
-        self.use_backbone_lora = use_backbone_lora
-        self.use_llm_lora = use_llm_lora
-        self.select_layer = select_layer
-        self.force_image_size = force_image_size
-        self.downsample_ratio = downsample_ratio
-        self.template = template
-        self.dynamic_image_size = dynamic_image_size
-        self.use_thumbnail = use_thumbnail
-        self.ps_version = ps_version  # pixel shuffle version
-        self.min_dynamic_patch = min_dynamic_patch
-        self.max_dynamic_patch = max_dynamic_patch
-
-        logger.info(f'vision_select_layer: {self.select_layer}')
-        logger.info(f'ps_version: {self.ps_version}')
-        logger.info(f'min_dynamic_patch: {self.min_dynamic_patch}')
-        logger.info(f'max_dynamic_patch: {self.max_dynamic_patch}')
-
-    def to_dict(self):
-        """
-        Serializes this instance to a Python dictionary. Override the default [`~PretrainedConfig.to_dict`].
-        Returns:
-            `Dict[str, any]`: Dictionary of all the attributes that make up this configuration instance,
-        """
-        output = copy.deepcopy(self.__dict__)
-        output['vision_config'] = self.vision_config.to_dict()
-        output['llm_config'] = self.llm_config.to_dict()
-        output['model_type'] = self.__class__.model_type
-        output['use_backbone_lora'] = self.use_backbone_lora
-        output['use_llm_lora'] = self.use_llm_lora
-        output['select_layer'] = self.select_layer
-        output['force_image_size'] = self.force_image_size
-        output['downsample_ratio'] = self.downsample_ratio
-        output['template'] = self.template
-        output['dynamic_image_size'] = self.dynamic_image_size
-        output['use_thumbnail'] = self.use_thumbnail
-        output['ps_version'] = self.ps_version
-        output['min_dynamic_patch'] = self.min_dynamic_patch
-        output['max_dynamic_patch'] = self.max_dynamic_patch
-
-        return output