| { | |
| "_name_or_path": "llmware/slim-topics", | |
| "aib_version": "model_archive_122723_tiny_llama-1.1b-29", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 5632, | |
| "max_position_embeddings": 2048, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 22, | |
| "num_key_value_heads": 4, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "trained": "custom training", | |
| "training_comments": "tiny-llama-1.1b-27", | |
| "training_dataset": [ | |
| "aib_label_samples_524s.jsonl" | |
| ], | |
| "training_timestamp": "Wed Dec 27 17:43:21 2023", | |
| "transformers_version": "4.41.2", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |