| { | |
| "architectures": [ | |
| "Lfm2MoeForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_lfm2_moe.Lfm2MoeConfig", | |
| "AutoModelForCausalLM": "modeling_lfm2_moe.Lfm2MoeForCausalLM" | |
| }, | |
| "bos_token_id": 1, | |
| "conv_L_cache": 3, | |
| "conv_bias": false, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 7, | |
| "hidden_size": 2048, | |
| "intermediate_size": 7168, | |
| "layer_types": [ | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv" | |
| ], | |
| "max_position_embeddings": 128000, | |
| "model_type": "lfm2_moe", | |
| "moe_intermediate_size": 1792, | |
| "norm_eps": 1e-05, | |
| "norm_topk_prob": true, | |
| "num_attention_heads": 32, | |
| "num_dense_layers": 2, | |
| "num_experts": 32, | |
| "num_experts_per_tok": 4, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 0, | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine", | |
| "model.layers.2.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.3.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.4.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.5.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.6.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.7.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.8.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.9.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.10.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.11.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.12.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.13.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.14.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.15.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.16.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.17.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.18.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.19.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.20.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.21.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.22.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.23.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| } | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine", | |
| "model.layers.2.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.3.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.4.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.5.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.6.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.7.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.8.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.9.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.10.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.11.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.12.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.13.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.14.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.15.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.16.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.17.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.18.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.19.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.20.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.21.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.22.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.23.feed_forward.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| } | |
| }, | |
| "rope_theta": 1000000.0, | |
| "routed_scaling_factor": 1.0, | |
| "transformers_version": "4.56.1", | |
| "use_cache": true, | |
| "use_expert_bias": true, | |
| "vocab_size": 65536 | |
| } |