| { | |
| "architectures": [ | |
| "Lfm3ForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_lfm3.Lfm3Config", | |
| "AutoModel": "modeling_lfm3.Lfm3Model", | |
| "AutoModelForCausalLM": "modeling_lfm3.Lfm3ForCausalLM" | |
| }, | |
| "bos_token_id": 124894, | |
| "conv_L_cache": 7, | |
| "conv_bias": false, | |
| "dtype": "float32", | |
| "eos_token_id": 124900, | |
| "head_dim": 8, | |
| "hidden_size": 16, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 32, | |
| "layer_types": [ | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "sliding_attention", | |
| "conv", | |
| "sliding_attention" | |
| ], | |
| "max_position_embeddings": 262144, | |
| "model_type": "lfm3", | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 7, | |
| "num_key_value_heads": 2, | |
| "pad_token_id": 124893, | |
| "rope_parameters": { | |
| "full_attention": { | |
| "partial_rotary_factor": 0.5, | |
| "rope_theta": 1000000.0, | |
| "rope_type": "default" | |
| }, | |
| "sliding_attention": { | |
| "rope_theta": 10000, | |
| "rope_type": "default" | |
| } | |
| }, | |
| "sliding_window": 4, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.20.0", | |
| "use_cache": true, | |
| "use_sandwich_norm": true, | |
| "vocab_size": 128000 | |
| } | |