| { |
| "A_dff": 170, |
| "architectures": [ |
| "PldrllmForCausalLM" |
| ], |
| "attention_bias": true, |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_pldrllm.PldrllmConfig", |
| "AutoModelForCausalLM": "modeling_pldrllm.PldrllmForCausalLM" |
| }, |
| "bos_token_id": 2, |
| "cache_first_G": false, |
| "custom_G_type": "external", |
| "eos_token_id": 3, |
| "final_bias": true, |
| "glu_bias": true, |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 896, |
| "initializer_range": 0.02, |
| "intermediate_size": 2389, |
| "layer_norm_eps": 1e-06, |
| "max_position_embeddings": 1024, |
| "model_type": "pldrllm", |
| "num_attention_heads": 14, |
| "num_denseA": 2, |
| "num_hidden_layers": 5, |
| "num_reslayerA": 8, |
| "output_pldr_attentions": false, |
| "pad_token_id": 0, |
| "reference_rope": true, |
| "rope_scaling": null, |
| "rope_theta": 10000.0, |
| "tie_word_embeddings": false, |
| "torch_dtype": "float32", |
| "transformers_version": "4.56.1", |
| "use_cache": true, |
| "vocab_size": 32000 |
| } |
|
|
