Update config.json

config.json

@@ -1,192 +1,32 @@
 {
-  "_name_or_path": "q-future/one-align",
-  "model_type": "mplug_owl2",
+  "_name_or_path": "Addax-Data-Science/Namib-Desert-v1",
   "architectures": [
-    "MPLUGOwl2LlamaForCausalLM"
+    "ViTForImageClassification"
   ],
-  "auto_map": {
-    "AutoConfig": "configuration_mplug_owl2.MPLUGOwl2Config",
-    "AutoModel": "modeling_mplug_owl2.MPLUGOwl2LlamaForCausalLM",
-    "AutoModelForCausalLM": "modeling_mplug_owl2.MPLUGOwl2LlamaForCausalLM"
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1536,
+  "id2label": {
+    "0": "hq",
+    "1": "lq"
   },
-  "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,
+  "image_size": 1024,
   "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": "4.31.0",
-  "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": "4.28.1",
-      "typical_p": 1.0,
-      "use_bfloat16": false,
-      "use_flash_attn": false
-    }
+  "intermediate_size": 4192,
+  "label2id": {
+    "hq": "0",
+    "lq": "1"
   },
-  "vocab_size": 32000
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 48,
+  "patch_size": 64,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.2"
 }