Init

README.md

@@ -23,7 +23,7 @@ from transformers import AutoTokenizer
 from mplug_owl.modeling_mplug_owl import MplugOwlForConditionalGeneration
 from mplug_owl.processing_mplug_owl import MplugOwlImageProcessor, MplugOwlProcessor
 
-pretrained_ckpt = 'MAGAer13/mplug-owl-llama-7b'
+pretrained_ckpt = 'MAGAer13/mplug-owl-bloomz-7b-multilingual'
 model = MplugOwlForConditionalGeneration.from_pretrained(
     pretrained_ckpt,
     torch_dtype=torch.bfloat16,
@@ -66,4 +66,4 @@ with torch.no_grad():
     res = model.generate(**inputs, **generate_kwargs)
 sentence = tokenizer.decode(res.tolist()[0], skip_special_tokens=True)
 print(sentence)
-```
+```

config.json

@@ -0,0 +1,253 @@
+{
+    "return_dict": true,
+    "output_hidden_states": false,
+    "output_attentions": false,
+    "torchscript": false,
+    "torch_dtype": null,
+    "use_bfloat16": false,
+    "tf_legacy_loss": false,
+    "pruned_heads": {},
+    "tie_word_embeddings": false,
+    "is_encoder_decoder": false,
+    "is_decoder": false,
+    "cross_attention_hidden_size": null,
+    "add_cross_attention": false,
+    "tie_encoder_decoder": false,
+    "max_length": 20,
+    "min_length": 0,
+    "do_sample": false,
+    "early_stopping": false,
+    "num_beams": 1,
+    "num_beam_groups": 1,
+    "diversity_penalty": 0.0,
+    "temperature": 1.0,
+    "top_k": 50,
+    "top_p": 1.0,
+    "typical_p": 1.0,
+    "repetition_penalty": 1.0,
+    "length_penalty": 1.0,
+    "no_repeat_ngram_size": 0,
+    "encoder_no_repeat_ngram_size": 0,
+    "bad_words_ids": null,
+    "num_return_sequences": 1,
+    "chunk_size_feed_forward": 0,
+    "output_scores": false,
+    "return_dict_in_generate": false,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "remove_invalid_values": false,
+    "exponential_decay_length_penalty": null,
+    "suppress_tokens": null,
+    "begin_suppress_tokens": null,
+    "architectures": null,
+    "finetuning_task": null,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "tokenizer_class": null,
+    "prefix": null,
+    "bos_token_id": null,
+    "pad_token_id": null,
+    "eos_token_id": null,
+    "sep_token_id": null,
+    "decoder_start_token_id": null,
+    "task_specific_params": null,
+    "problem_type": null,
+    "_name_or_path": "",
+    "_commit_hash": null,
+    "transformers_version": null,
+    "vision_config": {
+        "return_dict": true,
+        "output_hidden_states": false,
+        "output_attentions": false,
+        "torchscript": false,
+        "torch_dtype": null,
+        "use_bfloat16": false,
+        "tf_legacy_loss": false,
+        "pruned_heads": {},
+        "tie_word_embeddings": true,
+        "is_encoder_decoder": false,
+        "is_decoder": false,
+        "cross_attention_hidden_size": null,
+        "add_cross_attention": false,
+        "tie_encoder_decoder": false,
+        "max_length": 20,
+        "min_length": 0,
+        "do_sample": false,
+        "early_stopping": false,
+        "num_beams": 1,
+        "num_beam_groups": 1,
+        "diversity_penalty": 0.0,
+        "temperature": 1.0,
+        "top_k": 50,
+        "top_p": 1.0,
+        "typical_p": 1.0,
+        "repetition_penalty": 1.0,
+        "length_penalty": 1.0,
+        "no_repeat_ngram_size": 0,
+        "encoder_no_repeat_ngram_size": 0,
+        "bad_words_ids": null,
+        "num_return_sequences": 1,
+        "chunk_size_feed_forward": 0,
+        "output_scores": false,
+        "return_dict_in_generate": false,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "remove_invalid_values": false,
+        "exponential_decay_length_penalty": null,
+        "suppress_tokens": null,
+        "begin_suppress_tokens": null,
+        "architectures": null,
+        "finetuning_task": null,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "tokenizer_class": null,
+        "prefix": null,
+        "bos_token_id": null,
+        "pad_token_id": null,
+        "eos_token_id": null,
+        "sep_token_id": null,
+        "decoder_start_token_id": null,
+        "task_specific_params": null,
+        "problem_type": null,
+        "_name_or_path": "",
+        "transformers_version": "4.29.0.dev0",
+        "model_type": "mplug_owl_vision_model",
+        "hidden_size": 1024,
+        "intermediate_size": 4096,
+        "projection_dim": 768,
+        "num_hidden_layers": 24,
+        "num_attention_heads": 16,
+        "num_channels": 3,
+        "patch_size": 14,
+        "image_size": 224,
+        "initializer_range": 0.02,
+        "initializer_factor": 1.0,
+        "attention_dropout": 0.0,
+        "layer_norm_eps": 1e-06,
+        "hidden_act": "quick_gelu"
+    },
+    "visual_abstractor_config": {
+        "return_dict": true,
+        "output_hidden_states": false,
+        "output_attentions": false,
+        "torchscript": false,
+        "torch_dtype": null,
+        "use_bfloat16": false,
+        "tf_legacy_loss": false,
+        "pruned_heads": {},
+        "tie_word_embeddings": true,
+        "is_encoder_decoder": false,
+        "is_decoder": false,
+        "cross_attention_hidden_size": null,
+        "add_cross_attention": false,
+        "tie_encoder_decoder": false,
+        "max_length": 20,
+        "min_length": 0,
+        "do_sample": false,
+        "early_stopping": false,
+        "num_beams": 1,
+        "num_beam_groups": 1,
+        "diversity_penalty": 0.0,
+        "temperature": 1.0,
+        "top_k": 50,
+        "top_p": 1.0,
+        "typical_p": 1.0,
+        "repetition_penalty": 1.0,
+        "length_penalty": 1.0,
+        "no_repeat_ngram_size": 0,
+        "encoder_no_repeat_ngram_size": 0,
+        "bad_words_ids": null,
+        "num_return_sequences": 1,
+        "chunk_size_feed_forward": 0,
+        "output_scores": false,
+        "return_dict_in_generate": false,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "remove_invalid_values": false,
+        "exponential_decay_length_penalty": null,
+        "suppress_tokens": null,
+        "begin_suppress_tokens": null,
+        "architectures": null,
+        "finetuning_task": null,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "tokenizer_class": null,
+        "prefix": null,
+        "bos_token_id": null,
+        "pad_token_id": 0,
+        "eos_token_id": null,
+        "sep_token_id": null,
+        "decoder_start_token_id": null,
+        "task_specific_params": null,
+        "problem_type": null,
+        "_name_or_path": "",
+        "transformers_version": "4.29.0.dev0",
+        "vocab_size": 30522,
+        "hidden_size": 1024,
+        "num_hidden_layers": 6,
+        "num_attention_heads": 16,
+        "hidden_act": "gelu",
+        "intermediate_size": 4096,
+        "hidden_dropout_prob": 0.1,
+        "attention_probs_dropout_prob": 0.1,
+        "max_position_embeddings": 512,
+        "initializer_range": 0.02,
+        "layer_norm_eps": 1e-06,
+        "position_embedding_type": "absolute",
+        "classifier_dropout": null,
+        "cross_attention_frequency": 2,
+        "encoder_hidden_size": 1024,
+        "model_type": "MPlugOwlVisualAbstractor"
+    },
+    "text_config": {
+        "apply_residual_connection_post_layernorm": false,
+        "attention_dropout": 0.0,
+        "attention_softmax_in_fp32": true,
+        "bias_dropout_fusion": true,
+        "bos_token_id": 1,
+        "eos_token_id": 2,
+        "hidden_dropout": 0.0,
+        "initializer_range": 0.02,
+        "layer_norm_epsilon": 1e-05,
+        "masked_softmax_fusion": true,
+        "model_type": "bloom",
+        "n_embed": 4096,
+        "n_inner": null,
+        "n_layer": 30,
+        "num_attention_heads": 32,
+        "offset_alibi": 100,
+        "pad_token_id": 3,
+        "pretraining_tp": 4,
+        "seq_length": 2048,
+        "skip_bias_add": true,
+        "skip_bias_add_qkv": false,
+        "slow_but_exact": false,
+        "transformers_version": "4.21.0.dev0",
+        "unk_token_id": 0,
+        "use_cache": true,
+        "vocab_size": 250880
+    },
+    "num_query_tokens": 64,
+    "use_decoder_only_language_model": true,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "model_type": "mplug-owl"
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+    "bos_token_id": 1,
+    "do_sample": true,
+    "eos_token_id": 2,
+    "max_length": 512,
+    "pad_token_id": 0,
+    "top_k": 3,
+    "transformers_version": "4.29.0.dev0",
+    "unk_token_id": 0
+}
+  

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+    "resolution": 224,
+    "image_mean": [
+        0.48145466, 0.4578275, 0.40821073
+    ],
+    "image_std": [
+        0.26862954, 0.26130258, 0.27577711
+    ]
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02ddb80deb7427199ac967891cbe5c2ead3254f56fdea690d310249613547d00
+size 14907607673

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "eos_token": "</s>", "bos_token": "<s>", "pad_token": "<pad>", "name_or_path": "bigscience/tokenizer", "special_tokens_map_file": null, "tokenizer_class": "BloomTokenizerFast", "padding_side": "left"}