gamansai/asteria-kimi-k27-brain-sparse
Add L01_exp6 — 102 tensors
Add L01_exp5 — 150 tensors
Add L01_exp4 — 150 tensors
Add L01_exp3 — 150 tensors
Add L01_exp2 — 150 tensors
Add L01_exp1 — 150 tensors
Add L01_exp0 — 150 tensors
Add L01_experts_0 — 450 tensors
Add L01 — 2304 tensors
Add language_model.model.layers.11.self_attn.q_b_proj.weight
Add language_model.model.layers.11.self_attn.q_a_proj.weight
Add language_model.model.layers.11.self_attn.q_a_layernorm.weight
Add language_model.model.layers.10.mlp.gate.weight
Add language_model.model.layers.10.mlp.gate.e_score_correction_bias
Add language_model.model.layers.10.self_attn.o_proj.weight
Add language_model.model.layers.10.post_attention_layernorm.weight
Add language_model.model.layers.10.input_layernorm.weight
Add language_model.model.layers.10.self_attn.kv_b_proj.weight
Add language_model.model.layers.10.self_attn.kv_a_layernorm.weight
Add language_model.model.layers.10.self_attn.q_b_proj.weight
Add language_model.model.layers.10.self_attn.kv_a_proj_with_mqa.weight
Add language_model.model.layers.10.self_attn.q_a_proj.weight
Add language_model.model.layers.10.self_attn.q_a_layernorm.weight
Add language_model.model.layers.9.mlp.gate.weight
Add language_model.model.layers.9.mlp.gate.e_score_correction_bias
Add language_model.model.layers.9.post_attention_layernorm.weight
Add language_model.model.layers.9.self_attn.o_proj.weight
Add language_model.model.layers.9.input_layernorm.weight
Add language_model.model.layers.9.self_attn.kv_b_proj.weight
Add language_model.model.layers.9.self_attn.kv_a_layernorm.weight
Add language_model.model.layers.9.self_attn.kv_a_proj_with_mqa.weight
Add language_model.model.layers.9.self_attn.q_b_proj.weight
Add language_model.model.layers.9.self_attn.q_a_proj.weight
Add language_model.model.layers.9.self_attn.q_a_layernorm.weight
Add language_model.model.layers.8.mlp.gate.e_score_correction_bias
Add language_model.model.layers.8.mlp.gate.weight
Add language_model.model.layers.8.self_attn.o_proj.weight
Add language_model.model.layers.8.post_attention_layernorm.weight
Add language_model.model.layers.8.input_layernorm.weight
Add language_model.model.layers.8.self_attn.kv_b_proj.weight
Add language_model.model.layers.8.self_attn.kv_a_layernorm.weight
Add language_model.model.layers.8.self_attn.kv_a_proj_with_mqa.weight
Add language_model.model.layers.8.self_attn.q_b_proj.weight
Add language_model.model.layers.8.self_attn.q_a_proj.weight
Add language_model.model.layers.8.self_attn.q_a_layernorm.weight
Add language_model.model.layers.7.mlp.gate.weight
Add language_model.model.layers.7.mlp.gate.e_score_correction_bias
Add language_model.model.layers.7.post_attention_layernorm.weight
Add language_model.model.layers.7.input_layernorm.weight
Add language_model.model.layers.7.self_attn.o_proj.weight