| { | |
| "architectures": [ | |
| "PolyLLaMAForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "auto_map": { | |
| "AutoConfig": "configuration_polyllama.PolyLlamaConfig", | |
| "AutoModel": "modeling_polyllama.PolyLlamaForCausalLM", | |
| "AutoModelForCausalLM": "modeling_polyllama.PolyLlamaForCausalLM" | |
| }, | |
| "bos_token_id": null, | |
| "eos_token_id": null, | |
| "hidden_act": "PolyReLU", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8256, | |
| "max_position_embeddings": 4096, | |
| "max_sequence_length": 4096, | |
| "model_type": "polyllama", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 16, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.34.1", | |
| "use_cache": true, | |
| "vocab_size": 32001 | |
| } | |