| { |
| "metadata": { |
| "total_size": 33107908480 |
| }, |
| "weight_map": { |
| "lm_head.weight": "model-00020-of-00020.safetensors", |
| "model.layers.0.attention.dense.weight": "model-00001-of-00020.safetensors", |
| "model.layers.0.attention.key_layernorm.weight": "model-00001-of-00020.safetensors", |
| "model.layers.0.attention.query_key_value.weight": "model-00001-of-00020.safetensors", |
| "model.layers.0.attention.query_layernorm.weight": "model-00001-of-00020.safetensors", |
| "model.layers.0.input_layernorm.weight": "model-00001-of-00020.safetensors", |
| "model.layers.0.mlp.down_proj.weight": "model-00001-of-00020.safetensors", |
| "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00020.safetensors", |
| "model.layers.0.mlp.up_proj.weight": "model-00001-of-00020.safetensors", |
| "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00020.safetensors", |
| "model.layers.1.attention.dense.weight": "model-00001-of-00020.safetensors", |
| "model.layers.1.attention.key_layernorm.weight": "model-00001-of-00020.safetensors", |
| "model.layers.1.attention.query_key_value.weight": "model-00001-of-00020.safetensors", |
| "model.layers.1.attention.query_layernorm.weight": "model-00001-of-00020.safetensors", |
| "model.layers.1.input_layernorm.weight": "model-00002-of-00020.safetensors", |
| "model.layers.1.mlp.experts_w12": "model-00001-of-00020.safetensors", |
| "model.layers.1.mlp.experts_w3": "model-00002-of-00020.safetensors", |
| "model.layers.1.mlp.gate.expert_bias": "model-00002-of-00020.safetensors", |
| "model.layers.1.mlp.gate.weight": "model-00002-of-00020.safetensors", |
| "model.layers.1.mlp.shared_experts.down_proj.weight": "model-00002-of-00020.safetensors", |
| "model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00002-of-00020.safetensors", |
| "model.layers.1.mlp.shared_experts.up_proj.weight": "model-00002-of-00020.safetensors", |
| "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00020.safetensors", |
| "model.layers.10.attention.branch_global_output_gain": "model-00009-of-00020.safetensors", |
| "model.layers.10.attention.branch_local_window_mix_logit": "model-00009-of-00020.safetensors", |
| "model.layers.10.attention.branch_mix_logits": "model-00009-of-00020.safetensors", |
| "model.layers.10.attention.branch_output_adapter_down.weight": "model-00009-of-00020.safetensors", |
| "model.layers.10.attention.branch_output_adapter_up.weight": "model-00009-of-00020.safetensors", |
| "model.layers.10.attention.branch_output_channel_gain": "model-00009-of-00020.safetensors", |
| "model.layers.10.attention.branch_output_gain": "model-00009-of-00020.safetensors", |
| "model.layers.10.attention.dense.weight": "model-00009-of-00020.safetensors", |
| "model.layers.10.attention.key_layernorm.weight": "model-00009-of-00020.safetensors", |
| "model.layers.10.attention.query_key_value.weight": "model-00009-of-00020.safetensors", |
| "model.layers.10.attention.query_layernorm.weight": "model-00009-of-00020.safetensors", |
| "model.layers.10.attention.raven_attention.A_log": "model-00009-of-00020.safetensors", |
| "model.layers.10.attention.raven_attention.a_proj.weight": "model-00009-of-00020.safetensors", |
| "model.layers.10.attention.raven_attention.dt_bias": "model-00009-of-00020.safetensors", |
| "model.layers.10.attention.raven_attention.g_norm.weight": "model-00009-of-00020.safetensors", |
| "model.layers.10.attention.raven_attention.k_norm.weight": "model-00009-of-00020.safetensors", |
| "model.layers.10.attention.raven_attention.k_proj.weight": "model-00009-of-00020.safetensors", |
| "model.layers.10.attention.raven_attention.o_proj.weight": "model-00009-of-00020.safetensors", |
| "model.layers.10.attention.raven_attention.q_norm.weight": "model-00009-of-00020.safetensors", |
| "model.layers.10.attention.raven_attention.q_proj.weight": "model-00009-of-00020.safetensors", |
| "model.layers.10.attention.raven_attention.r_proj.weight": "model-00009-of-00020.safetensors", |
| "model.layers.10.attention.raven_attention.v_proj.weight": "model-00009-of-00020.safetensors", |
| "model.layers.10.attention.replace_alpha_raw": "model-00009-of-00020.safetensors", |
| "model.layers.10.input_layernorm.weight": "model-00010-of-00020.safetensors", |
| "model.layers.10.mlp.experts_w12": "model-00010-of-00020.safetensors", |
| "model.layers.10.mlp.experts_w3": "model-00010-of-00020.safetensors", |
| "model.layers.10.mlp.gate.expert_bias": "model-00010-of-00020.safetensors", |
| "model.layers.10.mlp.gate.weight": "model-00010-of-00020.safetensors", |
| "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00010-of-00020.safetensors", |
| "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00010-of-00020.safetensors", |
| "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00010-of-00020.safetensors", |
| "model.layers.10.post_attention_layernorm.weight": "model-00010-of-00020.safetensors", |
| "model.layers.11.attention.branch_global_output_gain": "model-00010-of-00020.safetensors", |
| "model.layers.11.attention.branch_local_window_mix_logit": "model-00010-of-00020.safetensors", |
| "model.layers.11.attention.branch_mix_logits": "model-00010-of-00020.safetensors", |
| "model.layers.11.attention.branch_output_adapter_down.weight": "model-00010-of-00020.safetensors", |
| "model.layers.11.attention.branch_output_adapter_up.weight": "model-00010-of-00020.safetensors", |
| "model.layers.11.attention.branch_output_channel_gain": "model-00010-of-00020.safetensors", |
| "model.layers.11.attention.branch_output_gain": "model-00010-of-00020.safetensors", |
| "model.layers.11.attention.dense.weight": "model-00010-of-00020.safetensors", |
| "model.layers.11.attention.key_layernorm.weight": "model-00010-of-00020.safetensors", |
| "model.layers.11.attention.quasar_attention.A_log": "model-00010-of-00020.safetensors", |
| "model.layers.11.attention.quasar_attention.b_proj.weight": "model-00010-of-00020.safetensors", |
| "model.layers.11.attention.quasar_attention.dt_bias": "model-00010-of-00020.safetensors", |
| "model.layers.11.attention.quasar_attention.f_proj.weight": "model-00010-of-00020.safetensors", |
| "model.layers.11.attention.quasar_attention.g_proj.0.weight": "model-00010-of-00020.safetensors", |
| "model.layers.11.attention.quasar_attention.g_proj.1.bias": "model-00010-of-00020.safetensors", |
| "model.layers.11.attention.quasar_attention.g_proj.1.weight": "model-00010-of-00020.safetensors", |
| "model.layers.11.attention.quasar_attention.k_proj.weight": "model-00010-of-00020.safetensors", |
| "model.layers.11.attention.quasar_attention.o_norm.weight": "model-00010-of-00020.safetensors", |
| "model.layers.11.attention.quasar_attention.o_proj.weight": "model-00010-of-00020.safetensors", |
| "model.layers.11.attention.quasar_attention.q_proj.weight": "model-00010-of-00020.safetensors", |
| "model.layers.11.attention.quasar_attention.v_proj.weight": "model-00010-of-00020.safetensors", |
| "model.layers.11.attention.query_key_value.weight": "model-00010-of-00020.safetensors", |
| "model.layers.11.attention.query_layernorm.weight": "model-00010-of-00020.safetensors", |
| "model.layers.11.attention.replace_alpha_raw": "model-00010-of-00020.safetensors", |
| "model.layers.11.input_layernorm.weight": "model-00011-of-00020.safetensors", |
| "model.layers.11.mlp.experts_w12": "model-00011-of-00020.safetensors", |
| "model.layers.11.mlp.experts_w3": "model-00011-of-00020.safetensors", |
| "model.layers.11.mlp.gate.expert_bias": "model-00011-of-00020.safetensors", |
| "model.layers.11.mlp.gate.weight": "model-00011-of-00020.safetensors", |
| "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00011-of-00020.safetensors", |
| "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00011-of-00020.safetensors", |
| "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00011-of-00020.safetensors", |
| "model.layers.11.post_attention_layernorm.weight": "model-00011-of-00020.safetensors", |
| "model.layers.12.attention.branch_global_output_gain": "model-00011-of-00020.safetensors", |
| "model.layers.12.attention.branch_local_window_mix_logit": "model-00011-of-00020.safetensors", |
| "model.layers.12.attention.branch_mix_logits": "model-00011-of-00020.safetensors", |
| "model.layers.12.attention.branch_output_adapter_down.weight": "model-00011-of-00020.safetensors", |
| "model.layers.12.attention.branch_output_adapter_up.weight": "model-00011-of-00020.safetensors", |
| "model.layers.12.attention.branch_output_channel_gain": "model-00011-of-00020.safetensors", |
| "model.layers.12.attention.branch_output_gain": "model-00011-of-00020.safetensors", |
| "model.layers.12.attention.dense.weight": "model-00011-of-00020.safetensors", |
| "model.layers.12.attention.key_layernorm.weight": "model-00011-of-00020.safetensors", |
| "model.layers.12.attention.quasar_attention.A_log": "model-00011-of-00020.safetensors", |
| "model.layers.12.attention.quasar_attention.b_proj.weight": "model-00011-of-00020.safetensors", |
| "model.layers.12.attention.quasar_attention.dt_bias": "model-00011-of-00020.safetensors", |
| "model.layers.12.attention.quasar_attention.f_proj.weight": "model-00011-of-00020.safetensors", |
| "model.layers.12.attention.quasar_attention.g_proj.0.weight": "model-00011-of-00020.safetensors", |
| "model.layers.12.attention.quasar_attention.g_proj.1.bias": "model-00011-of-00020.safetensors", |
| "model.layers.12.attention.quasar_attention.g_proj.1.weight": "model-00011-of-00020.safetensors", |
| "model.layers.12.attention.quasar_attention.k_proj.weight": "model-00011-of-00020.safetensors", |
| "model.layers.12.attention.quasar_attention.o_norm.weight": "model-00011-of-00020.safetensors", |
| "model.layers.12.attention.quasar_attention.o_proj.weight": "model-00011-of-00020.safetensors", |
| "model.layers.12.attention.quasar_attention.q_proj.weight": "model-00011-of-00020.safetensors", |
| "model.layers.12.attention.quasar_attention.v_proj.weight": "model-00011-of-00020.safetensors", |
| "model.layers.12.attention.query_key_value.weight": "model-00011-of-00020.safetensors", |
| "model.layers.12.attention.query_layernorm.weight": "model-00011-of-00020.safetensors", |
| "model.layers.12.attention.replace_alpha_raw": "model-00011-of-00020.safetensors", |
| "model.layers.12.input_layernorm.weight": "model-00012-of-00020.safetensors", |
| "model.layers.12.mlp.experts_w12": "model-00012-of-00020.safetensors", |
| "model.layers.12.mlp.experts_w3": "model-00012-of-00020.safetensors", |
| "model.layers.12.mlp.gate.expert_bias": "model-00012-of-00020.safetensors", |
| "model.layers.12.mlp.gate.weight": "model-00012-of-00020.safetensors", |
| "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00012-of-00020.safetensors", |
| "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00012-of-00020.safetensors", |
| "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00012-of-00020.safetensors", |
| "model.layers.12.post_attention_layernorm.weight": "model-00012-of-00020.safetensors", |
| "model.layers.13.attention.branch_global_output_gain": "model-00012-of-00020.safetensors", |
| "model.layers.13.attention.branch_local_window_mix_logit": "model-00012-of-00020.safetensors", |
| "model.layers.13.attention.branch_mix_logits": "model-00012-of-00020.safetensors", |
| "model.layers.13.attention.branch_output_adapter_down.weight": "model-00012-of-00020.safetensors", |
| "model.layers.13.attention.branch_output_adapter_up.weight": "model-00012-of-00020.safetensors", |
| "model.layers.13.attention.branch_output_channel_gain": "model-00012-of-00020.safetensors", |
| "model.layers.13.attention.branch_output_gain": "model-00012-of-00020.safetensors", |
| "model.layers.13.attention.dense.weight": "model-00012-of-00020.safetensors", |
| "model.layers.13.attention.gla_attention.dense.weight": "model-00012-of-00020.safetensors", |
| "model.layers.13.attention.gla_attention.g_norm.weight": "model-00012-of-00020.safetensors", |
| "model.layers.13.attention.gla_attention.g_proj.weight": "model-00012-of-00020.safetensors", |
| "model.layers.13.attention.gla_attention.key_layernorm.weight": "model-00012-of-00020.safetensors", |
| "model.layers.13.attention.gla_attention.query_key_value.weight": "model-00012-of-00020.safetensors", |
| "model.layers.13.attention.gla_attention.query_layernorm.weight": "model-00012-of-00020.safetensors", |
| "model.layers.13.attention.gla_attention.slope": "model-00012-of-00020.safetensors", |
| "model.layers.13.attention.key_layernorm.weight": "model-00012-of-00020.safetensors", |
| "model.layers.13.attention.query_key_value.weight": "model-00012-of-00020.safetensors", |
| "model.layers.13.attention.query_layernorm.weight": "model-00012-of-00020.safetensors", |
| "model.layers.13.attention.replace_alpha_raw": "model-00012-of-00020.safetensors", |
| "model.layers.13.input_layernorm.weight": "model-00013-of-00020.safetensors", |
| "model.layers.13.mlp.experts_w12": "model-00013-of-00020.safetensors", |
| "model.layers.13.mlp.experts_w3": "model-00013-of-00020.safetensors", |
| "model.layers.13.mlp.gate.expert_bias": "model-00013-of-00020.safetensors", |
| "model.layers.13.mlp.gate.weight": "model-00013-of-00020.safetensors", |
| "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00013-of-00020.safetensors", |
| "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00013-of-00020.safetensors", |
| "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00013-of-00020.safetensors", |
| "model.layers.13.post_attention_layernorm.weight": "model-00013-of-00020.safetensors", |
| "model.layers.14.attention.branch_global_output_gain": "model-00013-of-00020.safetensors", |
| "model.layers.14.attention.branch_local_window_mix_logit": "model-00013-of-00020.safetensors", |
| "model.layers.14.attention.branch_mix_logits": "model-00013-of-00020.safetensors", |
| "model.layers.14.attention.branch_output_adapter_down.weight": "model-00013-of-00020.safetensors", |
| "model.layers.14.attention.branch_output_adapter_up.weight": "model-00013-of-00020.safetensors", |
| "model.layers.14.attention.branch_output_channel_gain": "model-00013-of-00020.safetensors", |
| "model.layers.14.attention.branch_output_gain": "model-00013-of-00020.safetensors", |
| "model.layers.14.attention.dense.weight": "model-00013-of-00020.safetensors", |
| "model.layers.14.attention.key_layernorm.weight": "model-00013-of-00020.safetensors", |
| "model.layers.14.attention.quasar_attention.A_log": "model-00013-of-00020.safetensors", |
| "model.layers.14.attention.quasar_attention.b_proj.weight": "model-00013-of-00020.safetensors", |
| "model.layers.14.attention.quasar_attention.dt_bias": "model-00013-of-00020.safetensors", |
| "model.layers.14.attention.quasar_attention.f_proj.weight": "model-00013-of-00020.safetensors", |
| "model.layers.14.attention.quasar_attention.g_proj.0.weight": "model-00013-of-00020.safetensors", |
| "model.layers.14.attention.quasar_attention.g_proj.1.bias": "model-00013-of-00020.safetensors", |
| "model.layers.14.attention.quasar_attention.g_proj.1.weight": "model-00013-of-00020.safetensors", |
| "model.layers.14.attention.quasar_attention.k_proj.weight": "model-00013-of-00020.safetensors", |
| "model.layers.14.attention.quasar_attention.o_norm.weight": "model-00013-of-00020.safetensors", |
| "model.layers.14.attention.quasar_attention.o_proj.weight": "model-00013-of-00020.safetensors", |
| "model.layers.14.attention.quasar_attention.q_proj.weight": "model-00013-of-00020.safetensors", |
| "model.layers.14.attention.quasar_attention.v_proj.weight": "model-00013-of-00020.safetensors", |
| "model.layers.14.attention.query_key_value.weight": "model-00013-of-00020.safetensors", |
| "model.layers.14.attention.query_layernorm.weight": "model-00013-of-00020.safetensors", |
| "model.layers.14.attention.replace_alpha_raw": "model-00013-of-00020.safetensors", |
| "model.layers.14.input_layernorm.weight": "model-00014-of-00020.safetensors", |
| "model.layers.14.mlp.experts_w12": "model-00014-of-00020.safetensors", |
| "model.layers.14.mlp.experts_w3": "model-00014-of-00020.safetensors", |
| "model.layers.14.mlp.gate.expert_bias": "model-00014-of-00020.safetensors", |
| "model.layers.14.mlp.gate.weight": "model-00014-of-00020.safetensors", |
| "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00014-of-00020.safetensors", |
| "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00014-of-00020.safetensors", |
| "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00014-of-00020.safetensors", |
| "model.layers.14.post_attention_layernorm.weight": "model-00014-of-00020.safetensors", |
| "model.layers.15.attention.branch_global_output_gain": "model-00014-of-00020.safetensors", |
| "model.layers.15.attention.branch_local_window_mix_logit": "model-00014-of-00020.safetensors", |
| "model.layers.15.attention.branch_mix_logits": "model-00014-of-00020.safetensors", |
| "model.layers.15.attention.branch_output_adapter_down.weight": "model-00014-of-00020.safetensors", |
| "model.layers.15.attention.branch_output_adapter_up.weight": "model-00014-of-00020.safetensors", |
| "model.layers.15.attention.branch_output_channel_gain": "model-00014-of-00020.safetensors", |
| "model.layers.15.attention.branch_output_gain": "model-00014-of-00020.safetensors", |
| "model.layers.15.attention.dense.weight": "model-00014-of-00020.safetensors", |
| "model.layers.15.attention.key_layernorm.weight": "model-00014-of-00020.safetensors", |
| "model.layers.15.attention.query_key_value.weight": "model-00014-of-00020.safetensors", |
| "model.layers.15.attention.query_layernorm.weight": "model-00014-of-00020.safetensors", |
| "model.layers.15.attention.raven_attention.A_log": "model-00014-of-00020.safetensors", |
| "model.layers.15.attention.raven_attention.a_proj.weight": "model-00014-of-00020.safetensors", |
| "model.layers.15.attention.raven_attention.dt_bias": "model-00014-of-00020.safetensors", |
| "model.layers.15.attention.raven_attention.g_norm.weight": "model-00014-of-00020.safetensors", |
| "model.layers.15.attention.raven_attention.k_norm.weight": "model-00014-of-00020.safetensors", |
| "model.layers.15.attention.raven_attention.k_proj.weight": "model-00014-of-00020.safetensors", |
| "model.layers.15.attention.raven_attention.o_proj.weight": "model-00014-of-00020.safetensors", |
| "model.layers.15.attention.raven_attention.q_norm.weight": "model-00014-of-00020.safetensors", |
| "model.layers.15.attention.raven_attention.q_proj.weight": "model-00014-of-00020.safetensors", |
| "model.layers.15.attention.raven_attention.r_proj.weight": "model-00014-of-00020.safetensors", |
| "model.layers.15.attention.raven_attention.v_proj.weight": "model-00014-of-00020.safetensors", |
| "model.layers.15.attention.replace_alpha_raw": "model-00014-of-00020.safetensors", |
| "model.layers.15.input_layernorm.weight": "model-00015-of-00020.safetensors", |
| "model.layers.15.mlp.experts_w12": "model-00015-of-00020.safetensors", |
| "model.layers.15.mlp.experts_w3": "model-00015-of-00020.safetensors", |
| "model.layers.15.mlp.gate.expert_bias": "model-00015-of-00020.safetensors", |
| "model.layers.15.mlp.gate.weight": "model-00015-of-00020.safetensors", |
| "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00015-of-00020.safetensors", |
| "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00015-of-00020.safetensors", |
| "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00015-of-00020.safetensors", |
| "model.layers.15.post_attention_layernorm.weight": "model-00015-of-00020.safetensors", |
| "model.layers.16.attention.branch_global_output_gain": "model-00015-of-00020.safetensors", |
| "model.layers.16.attention.branch_local_window_mix_logit": "model-00015-of-00020.safetensors", |
| "model.layers.16.attention.branch_mix_logits": "model-00015-of-00020.safetensors", |
| "model.layers.16.attention.branch_output_adapter_down.weight": "model-00015-of-00020.safetensors", |
| "model.layers.16.attention.branch_output_adapter_up.weight": "model-00015-of-00020.safetensors", |
| "model.layers.16.attention.branch_output_channel_gain": "model-00015-of-00020.safetensors", |
| "model.layers.16.attention.branch_output_gain": "model-00015-of-00020.safetensors", |
| "model.layers.16.attention.dense.weight": "model-00015-of-00020.safetensors", |
| "model.layers.16.attention.key_layernorm.weight": "model-00015-of-00020.safetensors", |
| "model.layers.16.attention.quasar_attention.A_log": "model-00015-of-00020.safetensors", |
| "model.layers.16.attention.quasar_attention.b_proj.weight": "model-00015-of-00020.safetensors", |
| "model.layers.16.attention.quasar_attention.dt_bias": "model-00015-of-00020.safetensors", |
| "model.layers.16.attention.quasar_attention.f_proj.weight": "model-00015-of-00020.safetensors", |
| "model.layers.16.attention.quasar_attention.g_proj.0.weight": "model-00015-of-00020.safetensors", |
| "model.layers.16.attention.quasar_attention.g_proj.1.bias": "model-00015-of-00020.safetensors", |
| "model.layers.16.attention.quasar_attention.g_proj.1.weight": "model-00015-of-00020.safetensors", |
| "model.layers.16.attention.quasar_attention.k_proj.weight": "model-00015-of-00020.safetensors", |
| "model.layers.16.attention.quasar_attention.o_norm.weight": "model-00015-of-00020.safetensors", |
| "model.layers.16.attention.quasar_attention.o_proj.weight": "model-00015-of-00020.safetensors", |
| "model.layers.16.attention.quasar_attention.q_proj.weight": "model-00015-of-00020.safetensors", |
| "model.layers.16.attention.quasar_attention.v_proj.weight": "model-00015-of-00020.safetensors", |
| "model.layers.16.attention.query_key_value.weight": "model-00015-of-00020.safetensors", |
| "model.layers.16.attention.query_layernorm.weight": "model-00015-of-00020.safetensors", |
| "model.layers.16.attention.replace_alpha_raw": "model-00015-of-00020.safetensors", |
| "model.layers.16.input_layernorm.weight": "model-00016-of-00020.safetensors", |
| "model.layers.16.mlp.experts_w12": "model-00016-of-00020.safetensors", |
| "model.layers.16.mlp.experts_w3": "model-00016-of-00020.safetensors", |
| "model.layers.16.mlp.gate.expert_bias": "model-00016-of-00020.safetensors", |
| "model.layers.16.mlp.gate.weight": "model-00016-of-00020.safetensors", |
| "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00016-of-00020.safetensors", |
| "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00016-of-00020.safetensors", |
| "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00016-of-00020.safetensors", |
| "model.layers.16.post_attention_layernorm.weight": "model-00016-of-00020.safetensors", |
| "model.layers.17.attention.branch_global_output_gain": "model-00016-of-00020.safetensors", |
| "model.layers.17.attention.branch_local_window_mix_logit": "model-00016-of-00020.safetensors", |
| "model.layers.17.attention.branch_mix_logits": "model-00016-of-00020.safetensors", |
| "model.layers.17.attention.branch_output_adapter_down.weight": "model-00016-of-00020.safetensors", |
| "model.layers.17.attention.branch_output_adapter_up.weight": "model-00016-of-00020.safetensors", |
| "model.layers.17.attention.branch_output_channel_gain": "model-00016-of-00020.safetensors", |
| "model.layers.17.attention.branch_output_gain": "model-00016-of-00020.safetensors", |
| "model.layers.17.attention.dense.weight": "model-00016-of-00020.safetensors", |
| "model.layers.17.attention.key_layernorm.weight": "model-00016-of-00020.safetensors", |
| "model.layers.17.attention.quasar_attention.A_log": "model-00016-of-00020.safetensors", |
| "model.layers.17.attention.quasar_attention.b_proj.weight": "model-00016-of-00020.safetensors", |
| "model.layers.17.attention.quasar_attention.dt_bias": "model-00016-of-00020.safetensors", |
| "model.layers.17.attention.quasar_attention.f_proj.weight": "model-00016-of-00020.safetensors", |
| "model.layers.17.attention.quasar_attention.g_proj.0.weight": "model-00016-of-00020.safetensors", |
| "model.layers.17.attention.quasar_attention.g_proj.1.bias": "model-00016-of-00020.safetensors", |
| "model.layers.17.attention.quasar_attention.g_proj.1.weight": "model-00016-of-00020.safetensors", |
| "model.layers.17.attention.quasar_attention.k_proj.weight": "model-00016-of-00020.safetensors", |
| "model.layers.17.attention.quasar_attention.o_norm.weight": "model-00016-of-00020.safetensors", |
| "model.layers.17.attention.quasar_attention.o_proj.weight": "model-00016-of-00020.safetensors", |
| "model.layers.17.attention.quasar_attention.q_proj.weight": "model-00016-of-00020.safetensors", |
| "model.layers.17.attention.quasar_attention.v_proj.weight": "model-00016-of-00020.safetensors", |
| "model.layers.17.attention.query_key_value.weight": "model-00016-of-00020.safetensors", |
| "model.layers.17.attention.query_layernorm.weight": "model-00016-of-00020.safetensors", |
| "model.layers.17.attention.replace_alpha_raw": "model-00016-of-00020.safetensors", |
| "model.layers.17.input_layernorm.weight": "model-00017-of-00020.safetensors", |
| "model.layers.17.mlp.experts_w12": "model-00017-of-00020.safetensors", |
| "model.layers.17.mlp.experts_w3": "model-00017-of-00020.safetensors", |
| "model.layers.17.mlp.gate.expert_bias": "model-00017-of-00020.safetensors", |
| "model.layers.17.mlp.gate.weight": "model-00017-of-00020.safetensors", |
| "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00017-of-00020.safetensors", |
| "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00017-of-00020.safetensors", |
| "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00017-of-00020.safetensors", |
| "model.layers.17.post_attention_layernorm.weight": "model-00017-of-00020.safetensors", |
| "model.layers.18.attention.branch_global_output_gain": "model-00017-of-00020.safetensors", |
| "model.layers.18.attention.branch_local_window_mix_logit": "model-00017-of-00020.safetensors", |
| "model.layers.18.attention.branch_mix_logits": "model-00017-of-00020.safetensors", |
| "model.layers.18.attention.branch_output_adapter_down.weight": "model-00017-of-00020.safetensors", |
| "model.layers.18.attention.branch_output_adapter_up.weight": "model-00017-of-00020.safetensors", |
| "model.layers.18.attention.branch_output_channel_gain": "model-00017-of-00020.safetensors", |
| "model.layers.18.attention.branch_output_gain": "model-00017-of-00020.safetensors", |
| "model.layers.18.attention.dense.weight": "model-00017-of-00020.safetensors", |
| "model.layers.18.attention.gla_attention.dense.weight": "model-00017-of-00020.safetensors", |
| "model.layers.18.attention.gla_attention.g_norm.weight": "model-00017-of-00020.safetensors", |
| "model.layers.18.attention.gla_attention.g_proj.weight": "model-00017-of-00020.safetensors", |
| "model.layers.18.attention.gla_attention.key_layernorm.weight": "model-00017-of-00020.safetensors", |
| "model.layers.18.attention.gla_attention.query_key_value.weight": "model-00017-of-00020.safetensors", |
| "model.layers.18.attention.gla_attention.query_layernorm.weight": "model-00017-of-00020.safetensors", |
| "model.layers.18.attention.gla_attention.slope": "model-00017-of-00020.safetensors", |
| "model.layers.18.attention.key_layernorm.weight": "model-00017-of-00020.safetensors", |
| "model.layers.18.attention.query_key_value.weight": "model-00017-of-00020.safetensors", |
| "model.layers.18.attention.query_layernorm.weight": "model-00017-of-00020.safetensors", |
| "model.layers.18.attention.replace_alpha_raw": "model-00017-of-00020.safetensors", |
| "model.layers.18.input_layernorm.weight": "model-00018-of-00020.safetensors", |
| "model.layers.18.mlp.experts_w12": "model-00018-of-00020.safetensors", |
| "model.layers.18.mlp.experts_w3": "model-00018-of-00020.safetensors", |
| "model.layers.18.mlp.gate.expert_bias": "model-00018-of-00020.safetensors", |
| "model.layers.18.mlp.gate.weight": "model-00018-of-00020.safetensors", |
| "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00018-of-00020.safetensors", |
| "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00018-of-00020.safetensors", |
| "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00018-of-00020.safetensors", |
| "model.layers.18.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", |
| "model.layers.19.attention.branch_global_output_gain": "model-00018-of-00020.safetensors", |
| "model.layers.19.attention.branch_local_window_mix_logit": "model-00018-of-00020.safetensors", |
| "model.layers.19.attention.branch_mix_logits": "model-00018-of-00020.safetensors", |
| "model.layers.19.attention.branch_output_adapter_down.weight": "model-00018-of-00020.safetensors", |
| "model.layers.19.attention.branch_output_adapter_up.weight": "model-00018-of-00020.safetensors", |
| "model.layers.19.attention.branch_output_channel_gain": "model-00018-of-00020.safetensors", |
| "model.layers.19.attention.branch_output_gain": "model-00018-of-00020.safetensors", |
| "model.layers.19.attention.dense.weight": "model-00018-of-00020.safetensors", |
| "model.layers.19.attention.key_layernorm.weight": "model-00018-of-00020.safetensors", |
| "model.layers.19.attention.quasar_attention.A_log": "model-00018-of-00020.safetensors", |
| "model.layers.19.attention.quasar_attention.b_proj.weight": "model-00018-of-00020.safetensors", |
| "model.layers.19.attention.quasar_attention.dt_bias": "model-00018-of-00020.safetensors", |
| "model.layers.19.attention.quasar_attention.f_proj.weight": "model-00018-of-00020.safetensors", |
| "model.layers.19.attention.quasar_attention.g_proj.0.weight": "model-00018-of-00020.safetensors", |
| "model.layers.19.attention.quasar_attention.g_proj.1.bias": "model-00018-of-00020.safetensors", |
| "model.layers.19.attention.quasar_attention.g_proj.1.weight": "model-00018-of-00020.safetensors", |
| "model.layers.19.attention.quasar_attention.k_proj.weight": "model-00018-of-00020.safetensors", |
| "model.layers.19.attention.quasar_attention.o_norm.weight": "model-00018-of-00020.safetensors", |
| "model.layers.19.attention.quasar_attention.o_proj.weight": "model-00018-of-00020.safetensors", |
| "model.layers.19.attention.quasar_attention.q_proj.weight": "model-00018-of-00020.safetensors", |
| "model.layers.19.attention.quasar_attention.v_proj.weight": "model-00018-of-00020.safetensors", |
| "model.layers.19.attention.query_key_value.weight": "model-00018-of-00020.safetensors", |
| "model.layers.19.attention.query_layernorm.weight": "model-00018-of-00020.safetensors", |
| "model.layers.19.attention.replace_alpha_raw": "model-00018-of-00020.safetensors", |
| "model.layers.19.input_layernorm.weight": "model-00019-of-00020.safetensors", |
| "model.layers.19.mlp.experts_w12": "model-00019-of-00020.safetensors", |
| "model.layers.19.mlp.experts_w3": "model-00019-of-00020.safetensors", |
| "model.layers.19.mlp.gate.expert_bias": "model-00019-of-00020.safetensors", |
| "model.layers.19.mlp.gate.weight": "model-00019-of-00020.safetensors", |
| "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00019-of-00020.safetensors", |
| "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00019-of-00020.safetensors", |
| "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00019-of-00020.safetensors", |
| "model.layers.19.post_attention_layernorm.weight": "model-00019-of-00020.safetensors", |
| "model.layers.2.attention.dense.weight": "model-00002-of-00020.safetensors", |
| "model.layers.2.attention.key_layernorm.weight": "model-00002-of-00020.safetensors", |
| "model.layers.2.attention.query_key_value.weight": "model-00002-of-00020.safetensors", |
| "model.layers.2.attention.query_layernorm.weight": "model-00002-of-00020.safetensors", |
| "model.layers.2.input_layernorm.weight": "model-00002-of-00020.safetensors", |
| "model.layers.2.mlp.experts_w12": "model-00002-of-00020.safetensors", |
| "model.layers.2.mlp.experts_w3": "model-00002-of-00020.safetensors", |
| "model.layers.2.mlp.gate.expert_bias": "model-00002-of-00020.safetensors", |
| "model.layers.2.mlp.gate.weight": "model-00002-of-00020.safetensors", |
| "model.layers.2.mlp.shared_experts.down_proj.weight": "model-00002-of-00020.safetensors", |
| "model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00002-of-00020.safetensors", |
| "model.layers.2.mlp.shared_experts.up_proj.weight": "model-00002-of-00020.safetensors", |
| "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00020.safetensors", |
| "model.layers.3.attention.dense.weight": "model-00002-of-00020.safetensors", |
| "model.layers.3.attention.key_layernorm.weight": "model-00002-of-00020.safetensors", |
| "model.layers.3.attention.query_key_value.weight": "model-00002-of-00020.safetensors", |
| "model.layers.3.attention.query_layernorm.weight": "model-00002-of-00020.safetensors", |
| "model.layers.3.input_layernorm.weight": "model-00003-of-00020.safetensors", |
| "model.layers.3.mlp.experts_w12": "model-00003-of-00020.safetensors", |
| "model.layers.3.mlp.experts_w3": "model-00003-of-00020.safetensors", |
| "model.layers.3.mlp.gate.expert_bias": "model-00003-of-00020.safetensors", |
| "model.layers.3.mlp.gate.weight": "model-00003-of-00020.safetensors", |
| "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00003-of-00020.safetensors", |
| "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00003-of-00020.safetensors", |
| "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00003-of-00020.safetensors", |
| "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00020.safetensors", |
| "model.layers.4.attention.branch_global_output_gain": "model-00003-of-00020.safetensors", |
| "model.layers.4.attention.branch_local_window_mix_logit": "model-00003-of-00020.safetensors", |
| "model.layers.4.attention.branch_mix_logits": "model-00003-of-00020.safetensors", |
| "model.layers.4.attention.branch_output_adapter_down.weight": "model-00003-of-00020.safetensors", |
| "model.layers.4.attention.branch_output_adapter_up.weight": "model-00003-of-00020.safetensors", |
| "model.layers.4.attention.branch_output_channel_gain": "model-00003-of-00020.safetensors", |
| "model.layers.4.attention.branch_output_gain": "model-00003-of-00020.safetensors", |
| "model.layers.4.attention.dense.weight": "model-00003-of-00020.safetensors", |
| "model.layers.4.attention.key_layernorm.weight": "model-00003-of-00020.safetensors", |
| "model.layers.4.attention.quasar_attention.A_log": "model-00003-of-00020.safetensors", |
| "model.layers.4.attention.quasar_attention.b_proj.weight": "model-00003-of-00020.safetensors", |
| "model.layers.4.attention.quasar_attention.dt_bias": "model-00003-of-00020.safetensors", |
| "model.layers.4.attention.quasar_attention.f_proj.weight": "model-00003-of-00020.safetensors", |
| "model.layers.4.attention.quasar_attention.g_proj.0.weight": "model-00003-of-00020.safetensors", |
| "model.layers.4.attention.quasar_attention.g_proj.1.bias": "model-00003-of-00020.safetensors", |
| "model.layers.4.attention.quasar_attention.g_proj.1.weight": "model-00003-of-00020.safetensors", |
| "model.layers.4.attention.quasar_attention.k_proj.weight": "model-00003-of-00020.safetensors", |
| "model.layers.4.attention.quasar_attention.o_norm.weight": "model-00003-of-00020.safetensors", |
| "model.layers.4.attention.quasar_attention.o_proj.weight": "model-00003-of-00020.safetensors", |
| "model.layers.4.attention.quasar_attention.q_proj.weight": "model-00003-of-00020.safetensors", |
| "model.layers.4.attention.quasar_attention.v_proj.weight": "model-00003-of-00020.safetensors", |
| "model.layers.4.attention.query_key_value.weight": "model-00003-of-00020.safetensors", |
| "model.layers.4.attention.query_layernorm.weight": "model-00003-of-00020.safetensors", |
| "model.layers.4.attention.replace_alpha_raw": "model-00003-of-00020.safetensors", |
| "model.layers.4.input_layernorm.weight": "model-00004-of-00020.safetensors", |
| "model.layers.4.mlp.experts_w12": "model-00004-of-00020.safetensors", |
| "model.layers.4.mlp.experts_w3": "model-00004-of-00020.safetensors", |
| "model.layers.4.mlp.gate.expert_bias": "model-00004-of-00020.safetensors", |
| "model.layers.4.mlp.gate.weight": "model-00004-of-00020.safetensors", |
| "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00004-of-00020.safetensors", |
| "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00004-of-00020.safetensors", |
| "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00004-of-00020.safetensors", |
| "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00020.safetensors", |
| "model.layers.5.attention.branch_global_output_gain": "model-00004-of-00020.safetensors", |
| "model.layers.5.attention.branch_local_window_mix_logit": "model-00004-of-00020.safetensors", |
| "model.layers.5.attention.branch_mix_logits": "model-00004-of-00020.safetensors", |
| "model.layers.5.attention.branch_output_adapter_down.weight": "model-00004-of-00020.safetensors", |
| "model.layers.5.attention.branch_output_adapter_up.weight": "model-00004-of-00020.safetensors", |
| "model.layers.5.attention.branch_output_channel_gain": "model-00004-of-00020.safetensors", |
| "model.layers.5.attention.branch_output_gain": "model-00004-of-00020.safetensors", |
| "model.layers.5.attention.dense.weight": "model-00004-of-00020.safetensors", |
| "model.layers.5.attention.key_layernorm.weight": "model-00004-of-00020.safetensors", |
| "model.layers.5.attention.query_key_value.weight": "model-00004-of-00020.safetensors", |
| "model.layers.5.attention.query_layernorm.weight": "model-00004-of-00020.safetensors", |
| "model.layers.5.attention.raven_attention.A_log": "model-00004-of-00020.safetensors", |
| "model.layers.5.attention.raven_attention.a_proj.weight": "model-00004-of-00020.safetensors", |
| "model.layers.5.attention.raven_attention.dt_bias": "model-00004-of-00020.safetensors", |
| "model.layers.5.attention.raven_attention.g_norm.weight": "model-00004-of-00020.safetensors", |
| "model.layers.5.attention.raven_attention.k_norm.weight": "model-00004-of-00020.safetensors", |
| "model.layers.5.attention.raven_attention.k_proj.weight": "model-00004-of-00020.safetensors", |
| "model.layers.5.attention.raven_attention.o_proj.weight": "model-00004-of-00020.safetensors", |
| "model.layers.5.attention.raven_attention.q_norm.weight": "model-00004-of-00020.safetensors", |
| "model.layers.5.attention.raven_attention.q_proj.weight": "model-00004-of-00020.safetensors", |
| "model.layers.5.attention.raven_attention.r_proj.weight": "model-00004-of-00020.safetensors", |
| "model.layers.5.attention.raven_attention.v_proj.weight": "model-00004-of-00020.safetensors", |
| "model.layers.5.attention.replace_alpha_raw": "model-00004-of-00020.safetensors", |
| "model.layers.5.input_layernorm.weight": "model-00005-of-00020.safetensors", |
| "model.layers.5.mlp.experts_w12": "model-00005-of-00020.safetensors", |
| "model.layers.5.mlp.experts_w3": "model-00005-of-00020.safetensors", |
| "model.layers.5.mlp.gate.expert_bias": "model-00005-of-00020.safetensors", |
| "model.layers.5.mlp.gate.weight": "model-00005-of-00020.safetensors", |
| "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00005-of-00020.safetensors", |
| "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00005-of-00020.safetensors", |
| "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00005-of-00020.safetensors", |
| "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00020.safetensors", |
| "model.layers.6.attention.branch_global_output_gain": "model-00005-of-00020.safetensors", |
| "model.layers.6.attention.branch_local_window_mix_logit": "model-00005-of-00020.safetensors", |
| "model.layers.6.attention.branch_mix_logits": "model-00005-of-00020.safetensors", |
| "model.layers.6.attention.branch_output_adapter_down.weight": "model-00005-of-00020.safetensors", |
| "model.layers.6.attention.branch_output_adapter_up.weight": "model-00005-of-00020.safetensors", |
| "model.layers.6.attention.branch_output_channel_gain": "model-00005-of-00020.safetensors", |
| "model.layers.6.attention.branch_output_gain": "model-00005-of-00020.safetensors", |
| "model.layers.6.attention.dense.weight": "model-00005-of-00020.safetensors", |
| "model.layers.6.attention.key_layernorm.weight": "model-00005-of-00020.safetensors", |
| "model.layers.6.attention.quasar_attention.A_log": "model-00005-of-00020.safetensors", |
| "model.layers.6.attention.quasar_attention.b_proj.weight": "model-00005-of-00020.safetensors", |
| "model.layers.6.attention.quasar_attention.dt_bias": "model-00005-of-00020.safetensors", |
| "model.layers.6.attention.quasar_attention.f_proj.weight": "model-00005-of-00020.safetensors", |
| "model.layers.6.attention.quasar_attention.g_proj.0.weight": "model-00005-of-00020.safetensors", |
| "model.layers.6.attention.quasar_attention.g_proj.1.bias": "model-00005-of-00020.safetensors", |
| "model.layers.6.attention.quasar_attention.g_proj.1.weight": "model-00005-of-00020.safetensors", |
| "model.layers.6.attention.quasar_attention.k_proj.weight": "model-00005-of-00020.safetensors", |
| "model.layers.6.attention.quasar_attention.o_norm.weight": "model-00005-of-00020.safetensors", |
| "model.layers.6.attention.quasar_attention.o_proj.weight": "model-00005-of-00020.safetensors", |
| "model.layers.6.attention.quasar_attention.q_proj.weight": "model-00005-of-00020.safetensors", |
| "model.layers.6.attention.quasar_attention.v_proj.weight": "model-00005-of-00020.safetensors", |
| "model.layers.6.attention.query_key_value.weight": "model-00005-of-00020.safetensors", |
| "model.layers.6.attention.query_layernorm.weight": "model-00005-of-00020.safetensors", |
| "model.layers.6.attention.replace_alpha_raw": "model-00005-of-00020.safetensors", |
| "model.layers.6.input_layernorm.weight": "model-00006-of-00020.safetensors", |
| "model.layers.6.mlp.experts_w12": "model-00006-of-00020.safetensors", |
| "model.layers.6.mlp.experts_w3": "model-00006-of-00020.safetensors", |
| "model.layers.6.mlp.gate.expert_bias": "model-00006-of-00020.safetensors", |
| "model.layers.6.mlp.gate.weight": "model-00006-of-00020.safetensors", |
| "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00006-of-00020.safetensors", |
| "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00006-of-00020.safetensors", |
| "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00006-of-00020.safetensors", |
| "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00020.safetensors", |
| "model.layers.7.attention.branch_global_output_gain": "model-00006-of-00020.safetensors", |
| "model.layers.7.attention.branch_local_window_mix_logit": "model-00006-of-00020.safetensors", |
| "model.layers.7.attention.branch_mix_logits": "model-00006-of-00020.safetensors", |
| "model.layers.7.attention.branch_output_adapter_down.weight": "model-00006-of-00020.safetensors", |
| "model.layers.7.attention.branch_output_adapter_up.weight": "model-00006-of-00020.safetensors", |
| "model.layers.7.attention.branch_output_channel_gain": "model-00006-of-00020.safetensors", |
| "model.layers.7.attention.branch_output_gain": "model-00006-of-00020.safetensors", |
| "model.layers.7.attention.dense.weight": "model-00006-of-00020.safetensors", |
| "model.layers.7.attention.key_layernorm.weight": "model-00006-of-00020.safetensors", |
| "model.layers.7.attention.quasar_attention.A_log": "model-00006-of-00020.safetensors", |
| "model.layers.7.attention.quasar_attention.b_proj.weight": "model-00006-of-00020.safetensors", |
| "model.layers.7.attention.quasar_attention.dt_bias": "model-00006-of-00020.safetensors", |
| "model.layers.7.attention.quasar_attention.f_proj.weight": "model-00006-of-00020.safetensors", |
| "model.layers.7.attention.quasar_attention.g_proj.0.weight": "model-00006-of-00020.safetensors", |
| "model.layers.7.attention.quasar_attention.g_proj.1.bias": "model-00006-of-00020.safetensors", |
| "model.layers.7.attention.quasar_attention.g_proj.1.weight": "model-00006-of-00020.safetensors", |
| "model.layers.7.attention.quasar_attention.k_proj.weight": "model-00006-of-00020.safetensors", |
| "model.layers.7.attention.quasar_attention.o_norm.weight": "model-00006-of-00020.safetensors", |
| "model.layers.7.attention.quasar_attention.o_proj.weight": "model-00006-of-00020.safetensors", |
| "model.layers.7.attention.quasar_attention.q_proj.weight": "model-00006-of-00020.safetensors", |
| "model.layers.7.attention.quasar_attention.v_proj.weight": "model-00006-of-00020.safetensors", |
| "model.layers.7.attention.query_key_value.weight": "model-00006-of-00020.safetensors", |
| "model.layers.7.attention.query_layernorm.weight": "model-00006-of-00020.safetensors", |
| "model.layers.7.attention.replace_alpha_raw": "model-00006-of-00020.safetensors", |
| "model.layers.7.input_layernorm.weight": "model-00007-of-00020.safetensors", |
| "model.layers.7.mlp.experts_w12": "model-00007-of-00020.safetensors", |
| "model.layers.7.mlp.experts_w3": "model-00007-of-00020.safetensors", |
| "model.layers.7.mlp.gate.expert_bias": "model-00007-of-00020.safetensors", |
| "model.layers.7.mlp.gate.weight": "model-00007-of-00020.safetensors", |
| "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00007-of-00020.safetensors", |
| "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00007-of-00020.safetensors", |
| "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00007-of-00020.safetensors", |
| "model.layers.7.post_attention_layernorm.weight": "model-00007-of-00020.safetensors", |
| "model.layers.8.attention.branch_global_output_gain": "model-00007-of-00020.safetensors", |
| "model.layers.8.attention.branch_local_window_mix_logit": "model-00007-of-00020.safetensors", |
| "model.layers.8.attention.branch_mix_logits": "model-00007-of-00020.safetensors", |
| "model.layers.8.attention.branch_output_adapter_down.weight": "model-00007-of-00020.safetensors", |
| "model.layers.8.attention.branch_output_adapter_up.weight": "model-00007-of-00020.safetensors", |
| "model.layers.8.attention.branch_output_channel_gain": "model-00007-of-00020.safetensors", |
| "model.layers.8.attention.branch_output_gain": "model-00007-of-00020.safetensors", |
| "model.layers.8.attention.dense.weight": "model-00007-of-00020.safetensors", |
| "model.layers.8.attention.gla_attention.dense.weight": "model-00007-of-00020.safetensors", |
| "model.layers.8.attention.gla_attention.g_norm.weight": "model-00007-of-00020.safetensors", |
| "model.layers.8.attention.gla_attention.g_proj.weight": "model-00007-of-00020.safetensors", |
| "model.layers.8.attention.gla_attention.key_layernorm.weight": "model-00007-of-00020.safetensors", |
| "model.layers.8.attention.gla_attention.query_key_value.weight": "model-00007-of-00020.safetensors", |
| "model.layers.8.attention.gla_attention.query_layernorm.weight": "model-00007-of-00020.safetensors", |
| "model.layers.8.attention.gla_attention.slope": "model-00007-of-00020.safetensors", |
| "model.layers.8.attention.key_layernorm.weight": "model-00007-of-00020.safetensors", |
| "model.layers.8.attention.query_key_value.weight": "model-00007-of-00020.safetensors", |
| "model.layers.8.attention.query_layernorm.weight": "model-00007-of-00020.safetensors", |
| "model.layers.8.attention.replace_alpha_raw": "model-00007-of-00020.safetensors", |
| "model.layers.8.input_layernorm.weight": "model-00008-of-00020.safetensors", |
| "model.layers.8.mlp.experts_w12": "model-00008-of-00020.safetensors", |
| "model.layers.8.mlp.experts_w3": "model-00008-of-00020.safetensors", |
| "model.layers.8.mlp.gate.expert_bias": "model-00008-of-00020.safetensors", |
| "model.layers.8.mlp.gate.weight": "model-00008-of-00020.safetensors", |
| "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00008-of-00020.safetensors", |
| "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00008-of-00020.safetensors", |
| "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00008-of-00020.safetensors", |
| "model.layers.8.post_attention_layernorm.weight": "model-00008-of-00020.safetensors", |
| "model.layers.9.attention.branch_global_output_gain": "model-00008-of-00020.safetensors", |
| "model.layers.9.attention.branch_local_window_mix_logit": "model-00008-of-00020.safetensors", |
| "model.layers.9.attention.branch_mix_logits": "model-00008-of-00020.safetensors", |
| "model.layers.9.attention.branch_output_adapter_down.weight": "model-00008-of-00020.safetensors", |
| "model.layers.9.attention.branch_output_adapter_up.weight": "model-00008-of-00020.safetensors", |
| "model.layers.9.attention.branch_output_channel_gain": "model-00008-of-00020.safetensors", |
| "model.layers.9.attention.branch_output_gain": "model-00008-of-00020.safetensors", |
| "model.layers.9.attention.dense.weight": "model-00008-of-00020.safetensors", |
| "model.layers.9.attention.key_layernorm.weight": "model-00008-of-00020.safetensors", |
| "model.layers.9.attention.quasar_attention.A_log": "model-00008-of-00020.safetensors", |
| "model.layers.9.attention.quasar_attention.b_proj.weight": "model-00008-of-00020.safetensors", |
| "model.layers.9.attention.quasar_attention.dt_bias": "model-00008-of-00020.safetensors", |
| "model.layers.9.attention.quasar_attention.f_proj.weight": "model-00008-of-00020.safetensors", |
| "model.layers.9.attention.quasar_attention.g_proj.0.weight": "model-00008-of-00020.safetensors", |
| "model.layers.9.attention.quasar_attention.g_proj.1.bias": "model-00008-of-00020.safetensors", |
| "model.layers.9.attention.quasar_attention.g_proj.1.weight": "model-00008-of-00020.safetensors", |
| "model.layers.9.attention.quasar_attention.k_proj.weight": "model-00008-of-00020.safetensors", |
| "model.layers.9.attention.quasar_attention.o_norm.weight": "model-00008-of-00020.safetensors", |
| "model.layers.9.attention.quasar_attention.o_proj.weight": "model-00008-of-00020.safetensors", |
| "model.layers.9.attention.quasar_attention.q_proj.weight": "model-00008-of-00020.safetensors", |
| "model.layers.9.attention.quasar_attention.v_proj.weight": "model-00008-of-00020.safetensors", |
| "model.layers.9.attention.query_key_value.weight": "model-00008-of-00020.safetensors", |
| "model.layers.9.attention.query_layernorm.weight": "model-00008-of-00020.safetensors", |
| "model.layers.9.attention.replace_alpha_raw": "model-00008-of-00020.safetensors", |
| "model.layers.9.input_layernorm.weight": "model-00009-of-00020.safetensors", |
| "model.layers.9.mlp.experts_w12": "model-00009-of-00020.safetensors", |
| "model.layers.9.mlp.experts_w3": "model-00009-of-00020.safetensors", |
| "model.layers.9.mlp.gate.expert_bias": "model-00009-of-00020.safetensors", |
| "model.layers.9.mlp.gate.weight": "model-00009-of-00020.safetensors", |
| "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00009-of-00020.safetensors", |
| "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00009-of-00020.safetensors", |
| "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00009-of-00020.safetensors", |
| "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00020.safetensors", |
| "model.norm.weight": "model-00019-of-00020.safetensors", |
| "model.rotary_emb.inv_freq": "model-00019-of-00020.safetensors", |
| "model.word_embeddings.weight": "model-00001-of-00020.safetensors" |
| } |
| } |
|
|
