| { | |
| "_name_or_path": "llmware/slim-xsum-phi-3", | |
| "aib_version": "model_archive_073124_phi-3-xsum_eot_1", | |
| "architectures": [ | |
| "Phi3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config", | |
| "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM" | |
| }, | |
| "bos_token_id": 1, | |
| "embd_pdrop": 0.0, | |
| "eos_token_id": 32000, | |
| "hidden_act": "silu", | |
| "hidden_size": 3072, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "max_position_embeddings": 4096, | |
| "model_type": "phi3", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "original_max_position_embeddings": 4096, | |
| "pad_token_id": 32000, | |
| "resid_pdrop": 0.0, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 2047, | |
| "tie_word_embeddings": false, | |
| "trained": "custom training", | |
| "training_comments": "phi3-xsum-0302-og-45k-eot-073124-1", | |
| "training_dataset": [ | |
| "xsum_030224_eot_1_45416.jsonl" | |
| ], | |
| "training_timestamp": "Wed Jul 31 10:51:35 2024", | |
| "transformers_version": "4.41.2", | |
| "use_cache": true, | |
| "vocab_size": 32064 | |
| } | |