| { | |
| "_name_or_path": "/home/maziyar/.cache/huggingface/hub/models--THUDM--LongAlign-13B-64k/snapshots/4bd5c5eba03d6f99fd346e264475eb7af535f36a", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 13824, | |
| "max_position_embeddings": 65536, | |
| "max_sequence_length": 65536, | |
| "model_type": "llama", | |
| "num_attention_heads": 40, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 40, | |
| "pad_token_id": 0, | |
| "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": 2000000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.38.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 32256 | |
| } | |