{ "_name_or_path": "/data/models/mistral/CollectiveCognition_chats-data-2023-09-27_/batch1_epochs4_lr1e-05_paged_adamw_32bit_cosine_warmup_0.05_max_grad1.0_grad_accu16", "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "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, "model_type": "llama", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "float32", "transformers_version": "4.34.0", "use_cache": true, "vocab_size": 32000 }