| { | |
| "_name_or_path": "LeroyDyer/Mixtral_AI_PsycoTron", | |
| "architectures": [ | |
| "MistralForTokenClassification" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "LeroyDyer/Mixtral_AI_PsycoTron--configuration_mistral.MistralConfig", | |
| "AutoModel": "LeroyDyer/Mixtral_AI_PsycoTron--modeling_mistral.MistralModel", | |
| "AutoModelForCausalLM": "LeroyDyer/Mixtral_AI_PsycoTron--modeling_mistral.MistralForCausalLM", | |
| "AutoModelForQuestionAnswering": "LeroyDyer/Mixtral_AI_PsycoTron--modeling_mistral.MistralForQuestionAnswering", | |
| "AutoModelForTokenClassification": "LeroyDyer/Mixtral_AI_PsycoTron--modeling_mistral.MistralForTokenClassification", | |
| "MistralForCausalThoughtsLM": "LeroyDyer/Mixtral_AI_PsycoTron--modeling_mistral.MistralForCausalThoughtsLM", | |
| "MistralThoughtsConfig": "LeroyDyer/Mixtral_AI_PsycoTron--configuration_mistral.MistralThoughtsConfig" | |
| }, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_dropout_prob": 0.02, | |
| "hidden_size": 4096, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1", | |
| "2": "LABEL_2" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1, | |
| "LABEL_2": 2 | |
| }, | |
| "max_position_embeddings": 32768, | |
| "model_type": "mistral", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 2, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 4096, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.38.2", | |
| "unsloth_version": "2024.4", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |