(Trained with Unsloth)

config.json

@@ -1,48 +1,3 @@
 {
-  "_name_or_path": "LeroyDyer/Mixtral_AI_CyberBrain_3_0",
-  "architectures": [
-    "MistralForCausalLM"
-  ],
-  "attention_dropout": 0.0,
-  "auto_map": {
-    "AutoConfig": "LeroyDyer/Mixtral_AI_CyberBrain_3_0--configuration_mistral.MistralConfig",
-    "AutoModelForCausalLM": "LeroyDyer/Mixtral_AI_CyberBrain_3_0--modeling_yarn.MistralForCausalLM"
-  },
-  "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_sequence_length": 131072,
-  "max_thoughts": 3,
-  "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_scaling": {
-    "factor": 16.0,
-    "finetuned": true,
-    "original_max_position_embeddings": 8192,
-    "type": "yarn"
-  },
-  "rope_theta": 10000.0,
-  "sliding_window": 131072,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.40.0.dev0",
-  "unsloth_version": "2024.3",
-  "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": 32002
-}
+    "model_type": "mistral"
+}