Upload config.json

config.json

@@ -0,0 +1,107 @@
+{
+  "_name_or_path": "LeroyDyer/Mixtral_AI_CyberBrain_3_0",
+  "architectures": [
+    "MistralForCausalLM","QuietForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "LeroyDyer/Mixtral_AI_CyberBrain_3_0--configuration_mistral.MistralConfig",
+    "AutoModel": "LeroyDyer/Mixtral_AI_CyberBrain_3_0--modeling_mistral.MistralModel",
+    "AutoModelForCausalLM": "LeroyDyer/Mixtral_AI_CyberBrain_3_0--modeling_mistral.MistralForCausalLM",
+    "QuietForCausalLM": "LeroyDyer/Mixtral_AI_CyberBrain_3_0--modeling_quiet.QuietForCausalLM",   
+    "QuietConfig": "LeroyDyer/Mixtral_AI_CyberBrain_3_0--configuration_quiet.QuietConfig"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "max_thoughts": 10,
+  "merged_lm_and_talk_heads": false,
+  "merged_lm_and_think_heads": true,
+  "merged_talk_heads": true,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": true,
+  "use_complex_talk_head": true,
+  "use_complex_think_head": false,
+  "use_concat_talk_head": true,
+  "use_shallow_talk": false,
+  "use_shallow_think": true,
+  "use_weighted_talk_head": true,
+  "vocab_size": 32004,
+  "freeze_mm_mlp_adapter": false,
+  "freeze_mm_vision_resampler": false,
+  "ignore_index": -100,
+  "image_aspect_ratio": "anyres",
+  "image_crop_resolution": 224,
+  "image_grid_pinpoints": [
+      [
+          336,
+          672
+      ],
+      [
+          672,
+          336
+      ],
+      [
+          672,
+          672
+      ],
+      [
+          1008,
+          336
+      ],
+      [
+          336,
+          1008
+      ]
+  ],
+  "image_split_resolution": 224,
+  "image_token_index": 32002,
+  "mm_hidden_size": 1024,
+  "mm_patch_merge_type": "spatial_unpad",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "openai/clip-vit-large-patch14-336",
+  "mm_vision_tower_lr": 2e-06,
+  "projector_hidden_act": "gelu",
+  "text_config": {
+      "model_type": "llama"
+  },
+  "tokenizer_model_max_length": 4096,
+  "tokenizer_padding_side": "right",
+  "tune_mm_mlp_adapter": false,
+  "tune_mm_vision_resampler": false,
+  "unfreeze_mm_vision_tower": true,
+  "use_mm_proj": true,
+  "vision_config": {
+      "hidden_size": 1024,
+      "image_size": 336,
+      "intermediate_size": 4096,
+      "model_type": "clip_vision_model",
+      "num_attention_heads": 16,
+      "num_hidden_layers": 24,
+      "patch_size": 14,
+      "projection_dim": 768,
+      "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default"
+}  
+