updated config.json

config.json

@@ -1,84 +1,127 @@
 {
+  "architectures": [
+    "H2OVLChatModel"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_h2ovl_chat.H2OVLChatConfig",
+    "AutoModel": "modeling_h2ovl_chat.H2OVLChatModel",
+    "AutoModelForCausalLM": "modeling_h2ovl_chat.H2OVLChatModel"
+  },
+  "downsample_ratio": 0.5,
+  "dynamic_image_size": true,
+  "force_image_size": 448,
+  "max_dynamic_patch": 6,
+  "min_dynamic_patch": 1,
+  "model_type": "h2ovl_chat",
+  "pad2square": false,
+  "ps_version": "v2",
+  "select_layer": -1,
+  "template": "h2ogpt2",
+  "torch_dtype": "bfloat16",
+  "use_backbone_lora": 0,
+  "use_llm_lora": 0,
+  "use_thumbnail": true,
+  "use_msac": true, 
+  "llm_config": {
+    "_name_or_path": "h2oai/h2o-danube2-1.8b-chat",
+    "model_type": "mistral",
     "architectures": [
-      "H2OVLChatModel"
+        "MistralForCausalLM"
     ],
+    "attention_dropout": 0.0,
+    "torch_dtype": "bfloat16",
+    "use_bfloat16": true,
+    "hidden_size": 2560,
+    "intermediate_size": 6912,
+    "max_position_embeddings": 8192,
+    "num_hidden_layers": 24,
+    "num_attention_heads": 32,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "hidden_act": "silu",
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "pad_token_id": 0,
+    "vocab_size": 32010,
+    "add_cross_attention": false,
+    "return_dict": true,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "prefix": null,
+    "rope_theta": 10000,
+    "sep_token_id": null,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "tie_encoder_decoder": false,
+    "torchscript": false,
+    "use_cache": true,
+    "transformers_version": "4.44.0"
+  },    
+  "vision_config": {
+    "_name_or_path": "OpenGVLab/InternViT-300M-448px",
+    "add_cross_attention": false,
+    "architectures": [
+      "InternVisionModel"
+    ],
+    "attention_dropout": 0.0,
     "auto_map": {
-      "AutoConfig": "configuration_h2ovl_chat.H2OVLChatConfig",
-      "AutoModel": "modeling_h2ovl_chat.H2OVLChatModel",
-      "AutoModelForCausalLM": "modeling_h2ovl_chat.H2OVLChatModel"
+      "AutoConfig": "OpenGVLab/InternViT-300M-448px--configuration_intern_vit.InternVisionConfig",
+      "AutoModel": "OpenGVLab/InternViT-300M-448px--modeling_intern_vit.InternVisionModel"
     },
-    
-    "downsample_ratio": 0.5,
-    "dynamic_image_size": true,
-    "force_image_size": 448,
-    "max_dynamic_patch": 6,
-    "min_dynamic_patch": 1,
-    "model_type": "h2ovl_chat",
-    "pad2square": false,
-    "ps_version": "v2",
-    "select_layer": -1,
-    "template": "h2ogpt2",
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "drop_path_rate": 0.0,
+    "dropout": 0.0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "hidden_act": "gelu",
+    "hidden_size": 1024,
+    "image_size": 448,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "layer_norm_eps": 1e-06,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "intern_vit_6b",
+    "no_repeat_ngram_size": 0,
+    "norm_type": "layer_norm",
+    "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,
+    "pruned_heads": {},
+    "qk_normalization": false,
+    "qkv_bias": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
     "torch_dtype": "bfloat16",
-    "use_backbone_lora": 0,
-    "use_llm_lora": 0,
-    "use_thumbnail": true,
-    "use_msac": true,
-    
-    "llm_config": {
-      "_name_or_path": "h2oai/h2o-danube2-1.8b-chat",
-      "model_type": "mistral",
-      "architectures": [
-          "MistralForCausalLM"
-      ],
-      "attention_dropout": 0.0,
-      "torch_dtype": "bfloat16",
-      "use_bfloat16": true,
-      "hidden_size": 2560,
-      "intermediate_size": 6912,
-      "num_hidden_layers": 24,
-      "num_attention_heads": 32,
-      "num_key_value_heads": 8,
-      "rms_norm_eps": 1e-05,
-      "hidden_act": "silu",
-      "bos_token_id": 1,
-      "eos_token_id": 2,
-      "pad_token_id": 0,
-      "vocab_size": 32010,
-      "add_cross_attention": false,
-      "return_dict": true,
-      "output_attentions": false,
-      "output_hidden_states": false,
-      "output_scores": false,
-      "prefix": null,
-      "rope_theta": 10000,
-      "sep_token_id": null,
-      "sliding_window": null,
-      "tie_word_embeddings": false,
-      "tie_encoder_decoder": false,
-      "torchscript": false,
-      "use_cache": true,
-      "transformers_version": "4.44.0"
-  },
-    
-    "vision_config": {
-      "architectures": [
-        "InternVisionModel"
-      ],
-      "hidden_size": 1024,
-      "image_size": 448,
-      "intermediate_size": 4096,
-      "model_type": "intern_vit_6b",
-      "norm_type": "layer_norm",
-      "num_attention_heads": 16,
-      "num_channels": 3,
-      "num_hidden_layers": 24,
-      "patch_size": 14,
-      "qk_normalization": false,
-      "qkv_bias": true,
-      "return_dict": true,
-      "torch_dtype": "bfloat16",
-      "use_bfloat16": true,
-      "use_flash_attn": true
-    }
+    "torchscript": false,
+    "transformers_version": "4.42.0.dev0",
+    "use_bfloat16": false,
+    "use_flash_attn": true
   }
-  
+}