| { |
| "architectures": [ |
| "Lfm2ForCausalLM" |
| ], |
| "block_auto_adjust_ff_dim": true, |
| "block_ffn_dim_multiplier": 1.0, |
| "block_multiple_of": 256, |
| "bos_token_id": 1, |
| "conv_L_cache": 3, |
| "conv_bias": false, |
| "dtype": "float32", |
| "eos_token_id": 2, |
| "hidden_size": 1024, |
| "initializer_range": 0.02, |
| "intermediate_size": 2720, |
| "layer_types": [ |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention" |
| ], |
| "max_batch_size": 512, |
| "max_position_embeddings": 2048, |
| "model_type": "lfm2", |
| "norm_eps": 1e-05, |
| "num_attention_heads": 16, |
| "num_hidden_layers": 12, |
| "num_key_value_heads": 4, |
| "pad_token_id": 0, |
| "rope_theta": 1000000.0, |
| "transformers_version": "4.56.0", |
| "use_cache": false, |
| "vocab_size": 50257 |
| } |
|
|
