Upload folder using huggingface_hub

.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,192 @@
+{
+  "_name_or_path": "q-future/co-instruct-preview",
+  "model_type": "mplug_owl2",
+  "architectures": [
+    "MPLUGOwl2LlamaForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_mplug_owl2.MPLUGOwl2Config",
+    "AutoModel": "modeling_mplug_owl2.MPLUGOwl2LlamaForCausalLM",
+    "AutoModelForCausalLM": "modeling_mplug_owl2.MPLUGOwl2LlamaForCausalLM"
+  },
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_vision_model": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "pad",
+  "image_grid_pinpoints": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "model_type": "mplug_owl2",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0",
+  "tune_visual_abstractor": true,
+  "use_cache": true,
+  "visual_abstractor_lr": null,
+  "visual_config": {
+    "visual_abstractor": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_probs_dropout_prob": 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,
+      "early_stopping": false,
+      "encoder_hidden_size": 1024,
+      "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,
+      "grid_size": 32,
+      "hidden_size": 1024,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "initializer_range": 0.02,
+      "intermediate_size": 2816,
+      "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": "mplug_owl_visual_abstract",
+      "no_repeat_ngram_size": 0,
+      "num_attention_heads": 16,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_hidden_layers": 6,
+      "num_learnable_queries": 64,
+      "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": {},
+      "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": null,
+      "torchscript": false,
+      "transformers_version": "4.28.1",
+      "typical_p": 1.0,
+      "use_bfloat16": false
+    },
+    "visual_model": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "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,
+      "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": "quick_gelu",
+      "hidden_size": 1024,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "image_size": 448,
+      "initializer_factor": 1.0,
+      "initializer_range": 0.02,
+      "intermediate_size": 4096,
+      "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": "mplug_owl_vision_model",
+      "no_repeat_ngram_size": 0,
+      "num_attention_heads": 16,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_channels": 3,
+      "num_hidden_layers": 24,
+      "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,
+      "projection_dim": 768,
+      "pruned_heads": {},
+      "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": null,
+      "torchscript": false,
+      "transformers_version": "4.37.0",
+      "typical_p": 1.0,
+      "use_bfloat16": false,
+      "use_flash_attn": false
+    }
+  },
+  "vocab_size": 32000
+}

config.json

@@ -10,7 +10,6 @@
     "AutoModelForCausalLM": "modeling_mplug_owl2.MPLUGOwl2LlamaForCausalLM"
   },
   "attention_bias": false,
-  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "freeze_vision_model": false,
@@ -31,7 +30,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.36.1",
+  "transformers_version": "4.37.0",
   "tune_visual_abstractor": true,
   "use_cache": true,
   "visual_abstractor_lr": null,
@@ -183,7 +182,7 @@
       "top_p": 1.0,
       "torch_dtype": null,
       "torchscript": false,
-      "transformers_version": "4.28.1",
+      "transformers_version": "4.37.0",
       "typical_p": 1.0,
       "use_bfloat16": false,
       "use_flash_attn": false

pytorch_model-00001-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ac4839a29e48a8896368aa8f7816e18cc3a459eccb95ff7a571290bb6730cb6
+oid sha256:966906c35a40c6f23c5ac6f516cc3ed5cb09cec69d1d730bff18bdd2730ab50f
 size 4981108780

pytorch_model-00002-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b34ff911880a7f8bd60b2a3ee0f7a5ec885748fc4d5308d5e00cfc404960515
+oid sha256:483997c9987818581dfe391d50b35a9dcfd19b61c6beb31e208567e46e812f42
 size 4920293259

pytorch_model-00003-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce918e7e43822d390d528cab57892c1d50a25cae752155924339ac048f51df0b
+oid sha256:bec9927ae3cccd46d14d55edb65aee238d735b15496557c84622b8c73b2a972b
 size 4989532454

pytorch_model-00004-of-00004.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:920bba40c5cb6469732d171220fa6dc2c3f957270d5ce4060fe298e9f29bff1a
+oid sha256:7130429abb53cfb6e5b1c55ca16f3ff605d4a30d42872b55d025c9f1f70803fa
 size 1518469929

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d77889eaae62c56d315288e947ae6f9270d5e05c2c5af1f2fc65f6bb5f4d89
+oid sha256:3df716bc8cc87a8c8020346e18daef7f53e0f713f2249889e77ad19cfa7c9ce6
 size 6139