| { | |
| "_name_or_path": "/mnt5/output/y34k32-rat-t1lr1x-t2lr1-361klr1-t2lr1-t2lr1k26-407klr0.6-300klr1-253klr0.5-160klr1.2/final/", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 7168, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 20480, | |
| "max_position_embeddings": 131072, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 56, | |
| "num_hidden_layers": 60, | |
| "num_key_value_heads": 8, | |
| "pos_encoding_type": "rope", | |
| "pretraining_tp": 1, | |
| "quantization_config": { | |
| "bits": 4, | |
| "checkpoint_format": "gptq", | |
| "damp_percent": 0.1, | |
| "desc_act": false, | |
| "group_size": 128, | |
| "model_file_base_name": null, | |
| "model_name_or_path": null, | |
| "quant_method": "gptq", | |
| "static_groups": false, | |
| "sym": true, | |
| "true_sequential": true | |
| }, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.41.2", | |
| "use_cache": true, | |
| "vocab_size": 65280 | |
| } | |