{ "_name_or_path": "mistralai/Mistral-7B-v0.1", "architectures": [ "MistralForCausalLM" ], "attention_dropout": 0.0, "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": "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": "4.36.2", "use_cache": true, "sources": [ { "model": "google/gemma-7b", "layer_range": [0, 32] }, { "model": "SuperAGI/SAM", "layer_range": [0, 32] } ], "merge_method": "slerp", "base_model": "google/gemma-7b", "parameters": { "t": [ { "filter": "self_attn", "value": [0, 0.5, 0.3, 0.7, 1] }, { "filter": "mlp", "value": [1, 0.5, 0.7, 0.3, 0] }, { "value": 0.5 } ] }, "dtype": "bfloat16" }