| { | |
| "_name_or_path": "/ceph/hdd/staff/charpent/.cache/modelsznfbs0tp8brogchp", | |
| "aib_version": "", | |
| "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, | |
| "quantization_config": { | |
| "bits": 4, | |
| "group_size": 128, | |
| "modules_to_not_convert": null, | |
| "quant_method": "awq", | |
| "version": "gemm", | |
| "zero_point": true | |
| }, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "trained": "custom training", | |
| "training_comments": "shared_LLaMa-1.3B", | |
| "training_dataset": "", | |
| "training_timestamp": "Mon Jan 1 00:46:42 2024", | |
| "transformers_version": "4.41.2", | |
| "use_cache": false, | |
| "vocab_size": 32000 | |
| } | |