|
{ |
|
"architectures": [ |
|
"Lfm2ForCausalLM" |
|
], |
|
"block_auto_adjust_ff_dim": true, |
|
"block_dim": 1536, |
|
"block_ff_dim": 10240, |
|
"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": 1536, |
|
"conv_dim_out": 1536, |
|
"conv_use_xavier_init": true, |
|
"eos_token_id": 7, |
|
"hidden_size": 1536, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 10240, |
|
"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": 24, |
|
"num_heads": 24, |
|
"num_hidden_layers": 16, |
|
"num_key_value_heads": 8, |
|
"pad_token_id": 0, |
|
"quantization_config": { |
|
"config_groups": { |
|
"group_0": { |
|
"input_activations": null, |
|
"output_activations": null, |
|
"targets": [ |
|
"Linear" |
|
], |
|
"weights": { |
|
"actorder": null, |
|
"block_structure": null, |
|
"dynamic": false, |
|
"group_size": 16, |
|
"num_bits": 4, |
|
"observer": "minmax", |
|
"observer_kwargs": {}, |
|
"strategy": "tensor_group", |
|
"symmetric": true, |
|
"type": "float" |
|
} |
|
} |
|
}, |
|
"format": "nvfp4-pack-quantized", |
|
"global_compression_ratio": null, |
|
"ignore": [ |
|
"lm_head" |
|
], |
|
"kv_cache_scheme": null, |
|
"quant_method": "compressed-tensors", |
|
"quantization_status": "compressed" |
|
}, |
|
"rope_theta": 1000000.0, |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.54.0.dev0", |
|
"use_cache": true, |
|
"use_pos_enc": true, |
|
"vocab_size": 65536 |
|
} |