bgkit-350m: merged encoder + decoder, compressor parts, standalone inference, model card
3149048 verified | { | |
| "architectures": [ | |
| "Lfm2ForCausalLM" | |
| ], | |
| "block_auto_adjust_ff_dim": true, | |
| "block_dim": 1024, | |
| "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": 1024, | |
| "conv_use_xavier_init": true, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 7, | |
| "full_attn_idxs": null, | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6656, | |
| "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": 16, | |
| "num_heads": 16, | |
| "num_hidden_layers": 16, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 0, | |
| "rope_parameters": { | |
| "rope_theta": 1000000.0, | |
| "rope_type": "default" | |
| }, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.5.4", | |
| "use_cache": false, | |
| "use_pos_enc": true, | |
| "vocab_size": 65536 | |
| } | |