{ "_name_or_path": "ultragist-mistral-7b-inst", "architectures": [ "MistralForCausalLM" ], "auto_map": { "AutoConfig": "configuration_mistral.MistralConfig", "AutoModelForCausalLM": "modeling_mistral.MistralForCausalLM" }, "attention_dropout": 0.0, "ultragist_attend_prev": false, "ultragist_attn": "step-expansion", "ultragist_embed_init": "eos", "ultragist_param": [ "q", "k", "v", "o" ], "ultragist_ratio": [ 2, 4, 8, 16, 32 ], "ultragist_ratio_mix": "adapt-1024", "ultragist_sink_size": 1, "ultragist_stride": 2048, "ultragist_window": 2048, "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_scaling": null, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.39.3", "use_cache": true, "vocab_size": 32000 }