| { | |
| "architectures": [ | |
| "Lfm2ForCausalLM" | |
| ], | |
| "block_auto_adjust_ff_dim": true, | |
| "block_dim": 2048, | |
| "block_ff_dim": 12288, | |
| "block_ffn_dim_multiplier": 1.0, | |
| "block_mlp_init_scale": 1.0, | |
| "block_multiple_of": 256, | |
| "block_norm_eps": 1e-05, | |
| "block_out_init_scale": 1.0, | |
| "block_use_swiglu": true, | |
| "block_use_xavier_init": true, | |
| "bos_token_id": 1, | |
| "conv_L_cache": 3, | |
| "conv_bias": false, | |
| "conv_dim": 2048, | |
| "conv_use_xavier_init": true, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 7, | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 12288, | |
| "layer_types": [ | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "full_attention", | |
| "conv" | |
| ], | |
| "max_position_embeddings": 128000, | |
| "model_type": "lfm2", | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 32, | |
| "num_heads": 32, | |
| "num_hidden_layers": 16, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 0, | |
| "rope_theta": 1000000.0, | |
| "tie_embedding": true, | |
| "transformers_version": "4.57.6", | |
| "use_cache": false, | |
| "use_pos_enc": true, | |
| "vocab_size": 65536, | |
| "quantization_config": { | |
| "config_groups": { | |
| "group_0": { | |
| "input_activations": { | |
| "dynamic": false, | |
| "num_bits": 4, | |
| "type": "float", | |
| "group_size": 16 | |
| }, | |
| "weights": { | |
| "dynamic": false, | |
| "num_bits": 4, | |
| "type": "float", | |
| "group_size": 16 | |
| }, | |
| "targets": [ | |
| "Linear" | |
| ] | |
| } | |
| }, | |
| "ignore": [ | |
| "lm_head" | |
| ], | |
| "quant_algo": "NVFP4", | |
| "producer": { | |
| "name": "modelopt", | |
| "version": "0.41.0" | |
| }, | |
| "quant_method": "modelopt" | |
| } | |
| } |