| { |
| "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, |
| "quantization": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine", |
| "model.embed_tokens": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.0.conv.in_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.0.conv.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.0.feed_forward.w1": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.0.feed_forward.w3": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.0.feed_forward.w2": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.1.conv.in_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.1.conv.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.1.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.1.feed_forward.w3": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.1.feed_forward.w2": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.2.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.2.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.2.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.2.self_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.2.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.2.feed_forward.w3": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.2.feed_forward.w2": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.3.conv.in_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.3.conv.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.3.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.3.feed_forward.w3": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.3.feed_forward.w2": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.4.conv.in_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.4.conv.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.4.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.4.feed_forward.w3": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.4.feed_forward.w2": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.5.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.5.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.5.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.5.self_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.5.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.5.feed_forward.w3": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.5.feed_forward.w2": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.6.conv.in_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.6.conv.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.6.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.6.feed_forward.w3": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.6.feed_forward.w2": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.7.conv.in_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.7.conv.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.7.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.7.feed_forward.w3": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.7.feed_forward.w2": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.8.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.8.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.8.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.8.self_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.8.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.8.feed_forward.w3": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.8.feed_forward.w2": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.9.conv.in_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.9.conv.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.9.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.9.feed_forward.w3": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.9.feed_forward.w2": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.10.self_attn.q_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.10.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.10.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.10.self_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.10.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.10.feed_forward.w3": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.10.feed_forward.w2": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.11.conv.in_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.11.conv.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.11.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.11.feed_forward.w3": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.11.feed_forward.w2": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.12.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.12.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.12.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.12.self_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.12.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.12.feed_forward.w3": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.12.feed_forward.w2": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.13.conv.in_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.13.conv.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.13.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.13.feed_forward.w3": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.13.feed_forward.w2": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.14.self_attn.q_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.14.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.14.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.14.self_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.14.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.14.feed_forward.w3": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.14.feed_forward.w2": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.15.conv.in_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.15.conv.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.15.feed_forward.w1": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.15.feed_forward.w3": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.15.feed_forward.w2": { |
| "bits": 8, |
| "group_size": 64 |
| } |
| }, |
| "quantization_config": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine", |
| "model.embed_tokens": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.0.conv.in_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.0.conv.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.0.feed_forward.w1": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.0.feed_forward.w3": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.0.feed_forward.w2": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.1.conv.in_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.1.conv.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.1.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.1.feed_forward.w3": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.1.feed_forward.w2": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.2.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.2.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.2.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.2.self_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.2.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.2.feed_forward.w3": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.2.feed_forward.w2": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.3.conv.in_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.3.conv.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.3.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.3.feed_forward.w3": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.3.feed_forward.w2": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.4.conv.in_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.4.conv.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.4.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.4.feed_forward.w3": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.4.feed_forward.w2": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.5.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.5.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.5.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.5.self_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.5.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.5.feed_forward.w3": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.5.feed_forward.w2": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.6.conv.in_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.6.conv.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.6.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.6.feed_forward.w3": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.6.feed_forward.w2": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.7.conv.in_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.7.conv.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.7.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.7.feed_forward.w3": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.7.feed_forward.w2": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.8.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.8.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.8.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.8.self_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.8.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.8.feed_forward.w3": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.8.feed_forward.w2": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.9.conv.in_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.9.conv.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.9.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.9.feed_forward.w3": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.9.feed_forward.w2": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.10.self_attn.q_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.10.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.10.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.10.self_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.10.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.10.feed_forward.w3": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.10.feed_forward.w2": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.11.conv.in_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.11.conv.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.11.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.11.feed_forward.w3": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.11.feed_forward.w2": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.12.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.12.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.12.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.12.self_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.12.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.12.feed_forward.w3": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.12.feed_forward.w2": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.13.conv.in_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.13.conv.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.13.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.13.feed_forward.w3": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.13.feed_forward.w2": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.14.self_attn.q_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.14.self_attn.k_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.14.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.14.self_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.14.feed_forward.w1": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.14.feed_forward.w3": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.14.feed_forward.w2": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "model.layers.15.conv.in_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.15.conv.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.15.feed_forward.w1": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.15.feed_forward.w3": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "model.layers.15.feed_forward.w2": { |
| "bits": 8, |
| "group_size": 64 |
| } |
| }, |
| "rope_theta": 1000000.0, |
| "tie_embedding": true, |
| "transformers_version": "4.57.2", |
| "use_cache": true, |
| "use_pos_enc": true, |
| "vocab_size": 65536 |
| } |
