| { |
| "architectures": [ |
| "GLAswaForCausalLM" |
| ], |
| "auto_map": { |
| "AutoConfig": "configuration_gla_swa.GLAswaConfig", |
| "AutoModelForCausalLM": "modeling_gla_swa.GLAswaForCausalLM" |
| }, |
| "attention_dropout": 0.0, |
| "attn_layers": [ |
| 1, |
| 3, |
| 5, |
| 7, |
| 9, |
| 11, |
| 13, |
| 15, |
| 17, |
| 19, |
| 21, |
| 23, |
| 25, |
| 27 |
| ], |
| "attn_mode": "chunk", |
| "bos_token_id": 151643, |
| "conv_size": 4, |
| "elementwise_affine": true, |
| "eos_token_id": 151643, |
| "fuse_cross_entropy": true, |
| "hidden_act": "swish", |
| "hidden_size": 3584, |
| "initializer_range": 0.02, |
| "intermediate_size": 18944, |
| "max_position_embeddings": 131072, |
| "model_type": "gla_swa", |
| "norm_eps": 1e-06, |
| "num_attention_heads": 28, |
| "num_hidden_layers": 28, |
| "num_key_value_heads": 4, |
| "rope_theta": 1000000.0, |
| "sliding_window": 4096, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.45.0", |
| "use_cache": true, |
| "use_short_conv": false, |
| "vocab_size": 152064 |
| } |
|
|
