Files
FastDeploy/tests/e2e/Qwen3VL_RL/baseline.txt
T
sunxin 2533836dbb [Optimization] Accelerate Qwen3 QK RMSNorm via Fused Triton Kernel (#5880)
* qk rmsnorm fused

* inplace

* glm

* fix

* add qknorm layer

* fix

* update

* fix qwen3 vl

* update rl baseline

* fix qwen3 vl moe

* test

* fix qwen vl moe rl

* fix
2026-01-12 05:10:21 -08:00

1357 lines
74 KiB
Plaintext

lm_head.linear.weight
lm_head.linear.weight:lm_head.weight
model.embed_tokens.embeddings.weight
model.embed_tokens.embeddings.weight:model.embed_tokens.weight
model.layers.0.input_layernorm.weight
model.layers.0.input_layernorm.weight:model.layers.0.input_layernorm.weight
model.layers.0.mlp.down_proj.weight
model.layers.0.mlp.down_proj.weight:model.layers.0.mlp.down_proj.weight
model.layers.0.mlp.down_proj.weight_scale
model.layers.0.mlp.up_gate_proj.weight
model.layers.0.mlp.up_gate_proj.weight:model.layers.0.mlp.gate_up_fused_proj.weight
model.layers.0.mlp.up_gate_proj.weight_scale
model.layers.0.post_attention_layernorm.weight
model.layers.0.post_attention_layernorm.weight:model.layers.0.post_attention_layernorm.weight
model.layers.0.self_attn.o_proj.weight
model.layers.0.self_attn.o_proj.weight:model.layers.0.self_attn.o_proj.weight
model.layers.0.self_attn.o_proj.weight_scale
model.layers.0.self_attn.qk_norm.k_norm.weight
model.layers.0.self_attn.qk_norm.k_norm.weight:model.layers.0.self_attn.qk_norm.k_norm.weight
model.layers.0.self_attn.qk_norm.q_norm.weight
model.layers.0.self_attn.qk_norm.q_norm.weight:model.layers.0.self_attn.qk_norm.q_norm.weight
model.layers.0.self_attn.qkv_proj.weight
model.layers.0.self_attn.qkv_proj.weight:model.layers.0.self_attn.qkv_proj.weight
model.layers.0.self_attn.qkv_proj.weight_scale
model.layers.1.input_layernorm.weight
model.layers.1.input_layernorm.weight:model.layers.1.input_layernorm.weight
model.layers.1.mlp.down_proj.weight
model.layers.1.mlp.down_proj.weight:model.layers.1.mlp.down_proj.weight
model.layers.1.mlp.down_proj.weight_scale
model.layers.1.mlp.up_gate_proj.weight
model.layers.1.mlp.up_gate_proj.weight:model.layers.1.mlp.gate_up_fused_proj.weight
model.layers.1.mlp.up_gate_proj.weight_scale
model.layers.1.post_attention_layernorm.weight
model.layers.1.post_attention_layernorm.weight:model.layers.1.post_attention_layernorm.weight
model.layers.1.self_attn.o_proj.weight
model.layers.1.self_attn.o_proj.weight:model.layers.1.self_attn.o_proj.weight
model.layers.1.self_attn.o_proj.weight_scale
model.layers.1.self_attn.qk_norm.k_norm.weight
model.layers.1.self_attn.qk_norm.k_norm.weight:model.layers.1.self_attn.qk_norm.k_norm.weight
model.layers.1.self_attn.qk_norm.q_norm.weight
model.layers.1.self_attn.qk_norm.q_norm.weight:model.layers.1.self_attn.qk_norm.q_norm.weight
model.layers.1.self_attn.qkv_proj.weight
model.layers.1.self_attn.qkv_proj.weight:model.layers.1.self_attn.qkv_proj.weight
model.layers.1.self_attn.qkv_proj.weight_scale
model.layers.10.input_layernorm.weight
model.layers.10.input_layernorm.weight:model.layers.10.input_layernorm.weight
model.layers.10.mlp.down_proj.weight
model.layers.10.mlp.down_proj.weight:model.layers.10.mlp.down_proj.weight
model.layers.10.mlp.down_proj.weight_scale
model.layers.10.mlp.up_gate_proj.weight
model.layers.10.mlp.up_gate_proj.weight:model.layers.10.mlp.gate_up_fused_proj.weight
model.layers.10.mlp.up_gate_proj.weight_scale
model.layers.10.post_attention_layernorm.weight
model.layers.10.post_attention_layernorm.weight:model.layers.10.post_attention_layernorm.weight
model.layers.10.self_attn.o_proj.weight
model.layers.10.self_attn.o_proj.weight:model.layers.10.self_attn.o_proj.weight
model.layers.10.self_attn.o_proj.weight_scale
model.layers.10.self_attn.qk_norm.k_norm.weight
model.layers.10.self_attn.qk_norm.k_norm.weight:model.layers.10.self_attn.qk_norm.k_norm.weight
model.layers.10.self_attn.qk_norm.q_norm.weight
model.layers.10.self_attn.qk_norm.q_norm.weight:model.layers.10.self_attn.qk_norm.q_norm.weight
model.layers.10.self_attn.qkv_proj.weight
model.layers.10.self_attn.qkv_proj.weight:model.layers.10.self_attn.qkv_proj.weight
model.layers.10.self_attn.qkv_proj.weight_scale
model.layers.11.input_layernorm.weight
model.layers.11.input_layernorm.weight:model.layers.11.input_layernorm.weight
model.layers.11.mlp.down_proj.weight
model.layers.11.mlp.down_proj.weight:model.layers.11.mlp.down_proj.weight
model.layers.11.mlp.down_proj.weight_scale
model.layers.11.mlp.up_gate_proj.weight
model.layers.11.mlp.up_gate_proj.weight:model.layers.11.mlp.gate_up_fused_proj.weight
model.layers.11.mlp.up_gate_proj.weight_scale
model.layers.11.post_attention_layernorm.weight
model.layers.11.post_attention_layernorm.weight:model.layers.11.post_attention_layernorm.weight
model.layers.11.self_attn.o_proj.weight
model.layers.11.self_attn.o_proj.weight:model.layers.11.self_attn.o_proj.weight
model.layers.11.self_attn.o_proj.weight_scale
model.layers.11.self_attn.qk_norm.k_norm.weight
model.layers.11.self_attn.qk_norm.k_norm.weight:model.layers.11.self_attn.qk_norm.k_norm.weight
model.layers.11.self_attn.qk_norm.q_norm.weight
model.layers.11.self_attn.qk_norm.q_norm.weight:model.layers.11.self_attn.qk_norm.q_norm.weight
model.layers.11.self_attn.qkv_proj.weight
model.layers.11.self_attn.qkv_proj.weight:model.layers.11.self_attn.qkv_proj.weight
model.layers.11.self_attn.qkv_proj.weight_scale
model.layers.12.input_layernorm.weight
model.layers.12.input_layernorm.weight:model.layers.12.input_layernorm.weight
model.layers.12.mlp.down_proj.weight
model.layers.12.mlp.down_proj.weight:model.layers.12.mlp.down_proj.weight
model.layers.12.mlp.down_proj.weight_scale
model.layers.12.mlp.up_gate_proj.weight
model.layers.12.mlp.up_gate_proj.weight:model.layers.12.mlp.gate_up_fused_proj.weight
model.layers.12.mlp.up_gate_proj.weight_scale
model.layers.12.post_attention_layernorm.weight
model.layers.12.post_attention_layernorm.weight:model.layers.12.post_attention_layernorm.weight
model.layers.12.self_attn.o_proj.weight
model.layers.12.self_attn.o_proj.weight:model.layers.12.self_attn.o_proj.weight
model.layers.12.self_attn.o_proj.weight_scale
model.layers.12.self_attn.qk_norm.k_norm.weight
model.layers.12.self_attn.qk_norm.k_norm.weight:model.layers.12.self_attn.qk_norm.k_norm.weight
model.layers.12.self_attn.qk_norm.q_norm.weight
model.layers.12.self_attn.qk_norm.q_norm.weight:model.layers.12.self_attn.qk_norm.q_norm.weight
model.layers.12.self_attn.qkv_proj.weight
model.layers.12.self_attn.qkv_proj.weight:model.layers.12.self_attn.qkv_proj.weight
model.layers.12.self_attn.qkv_proj.weight_scale
model.layers.13.input_layernorm.weight
model.layers.13.input_layernorm.weight:model.layers.13.input_layernorm.weight
model.layers.13.mlp.down_proj.weight
model.layers.13.mlp.down_proj.weight:model.layers.13.mlp.down_proj.weight
model.layers.13.mlp.down_proj.weight_scale
model.layers.13.mlp.up_gate_proj.weight
model.layers.13.mlp.up_gate_proj.weight:model.layers.13.mlp.gate_up_fused_proj.weight
model.layers.13.mlp.up_gate_proj.weight_scale
model.layers.13.post_attention_layernorm.weight
model.layers.13.post_attention_layernorm.weight:model.layers.13.post_attention_layernorm.weight
model.layers.13.self_attn.o_proj.weight
model.layers.13.self_attn.o_proj.weight:model.layers.13.self_attn.o_proj.weight
model.layers.13.self_attn.o_proj.weight_scale
model.layers.13.self_attn.qk_norm.k_norm.weight
model.layers.13.self_attn.qk_norm.k_norm.weight:model.layers.13.self_attn.qk_norm.k_norm.weight
model.layers.13.self_attn.qk_norm.q_norm.weight
model.layers.13.self_attn.qk_norm.q_norm.weight:model.layers.13.self_attn.qk_norm.q_norm.weight
model.layers.13.self_attn.qkv_proj.weight
model.layers.13.self_attn.qkv_proj.weight:model.layers.13.self_attn.qkv_proj.weight
model.layers.13.self_attn.qkv_proj.weight_scale
model.layers.14.input_layernorm.weight
model.layers.14.input_layernorm.weight:model.layers.14.input_layernorm.weight
model.layers.14.mlp.down_proj.weight
model.layers.14.mlp.down_proj.weight:model.layers.14.mlp.down_proj.weight
model.layers.14.mlp.down_proj.weight_scale
model.layers.14.mlp.up_gate_proj.weight
model.layers.14.mlp.up_gate_proj.weight:model.layers.14.mlp.gate_up_fused_proj.weight
model.layers.14.mlp.up_gate_proj.weight_scale
model.layers.14.post_attention_layernorm.weight
model.layers.14.post_attention_layernorm.weight:model.layers.14.post_attention_layernorm.weight
model.layers.14.self_attn.o_proj.weight
model.layers.14.self_attn.o_proj.weight:model.layers.14.self_attn.o_proj.weight
model.layers.14.self_attn.o_proj.weight_scale
model.layers.14.self_attn.qk_norm.k_norm.weight
model.layers.14.self_attn.qk_norm.k_norm.weight:model.layers.14.self_attn.qk_norm.k_norm.weight
model.layers.14.self_attn.qk_norm.q_norm.weight
model.layers.14.self_attn.qk_norm.q_norm.weight:model.layers.14.self_attn.qk_norm.q_norm.weight
model.layers.14.self_attn.qkv_proj.weight
model.layers.14.self_attn.qkv_proj.weight:model.layers.14.self_attn.qkv_proj.weight
model.layers.14.self_attn.qkv_proj.weight_scale
model.layers.15.input_layernorm.weight
model.layers.15.input_layernorm.weight:model.layers.15.input_layernorm.weight
model.layers.15.mlp.down_proj.weight
model.layers.15.mlp.down_proj.weight:model.layers.15.mlp.down_proj.weight
model.layers.15.mlp.down_proj.weight_scale
model.layers.15.mlp.up_gate_proj.weight
model.layers.15.mlp.up_gate_proj.weight:model.layers.15.mlp.gate_up_fused_proj.weight
model.layers.15.mlp.up_gate_proj.weight_scale
model.layers.15.post_attention_layernorm.weight
model.layers.15.post_attention_layernorm.weight:model.layers.15.post_attention_layernorm.weight
model.layers.15.self_attn.o_proj.weight
model.layers.15.self_attn.o_proj.weight:model.layers.15.self_attn.o_proj.weight
model.layers.15.self_attn.o_proj.weight_scale
model.layers.15.self_attn.qk_norm.k_norm.weight
model.layers.15.self_attn.qk_norm.k_norm.weight:model.layers.15.self_attn.qk_norm.k_norm.weight
model.layers.15.self_attn.qk_norm.q_norm.weight
model.layers.15.self_attn.qk_norm.q_norm.weight:model.layers.15.self_attn.qk_norm.q_norm.weight
model.layers.15.self_attn.qkv_proj.weight
model.layers.15.self_attn.qkv_proj.weight:model.layers.15.self_attn.qkv_proj.weight
model.layers.15.self_attn.qkv_proj.weight_scale
model.layers.16.input_layernorm.weight
model.layers.16.input_layernorm.weight:model.layers.16.input_layernorm.weight
model.layers.16.mlp.down_proj.weight
model.layers.16.mlp.down_proj.weight:model.layers.16.mlp.down_proj.weight
model.layers.16.mlp.down_proj.weight_scale
model.layers.16.mlp.up_gate_proj.weight
model.layers.16.mlp.up_gate_proj.weight:model.layers.16.mlp.gate_up_fused_proj.weight
model.layers.16.mlp.up_gate_proj.weight_scale
model.layers.16.post_attention_layernorm.weight
model.layers.16.post_attention_layernorm.weight:model.layers.16.post_attention_layernorm.weight
model.layers.16.self_attn.o_proj.weight
model.layers.16.self_attn.o_proj.weight:model.layers.16.self_attn.o_proj.weight
model.layers.16.self_attn.o_proj.weight_scale
model.layers.16.self_attn.qk_norm.k_norm.weight
model.layers.16.self_attn.qk_norm.k_norm.weight:model.layers.16.self_attn.qk_norm.k_norm.weight
model.layers.16.self_attn.qk_norm.q_norm.weight
model.layers.16.self_attn.qk_norm.q_norm.weight:model.layers.16.self_attn.qk_norm.q_norm.weight
model.layers.16.self_attn.qkv_proj.weight
model.layers.16.self_attn.qkv_proj.weight:model.layers.16.self_attn.qkv_proj.weight
model.layers.16.self_attn.qkv_proj.weight_scale
model.layers.17.input_layernorm.weight
model.layers.17.input_layernorm.weight:model.layers.17.input_layernorm.weight
model.layers.17.mlp.down_proj.weight
model.layers.17.mlp.down_proj.weight:model.layers.17.mlp.down_proj.weight
model.layers.17.mlp.down_proj.weight_scale
model.layers.17.mlp.up_gate_proj.weight
model.layers.17.mlp.up_gate_proj.weight:model.layers.17.mlp.gate_up_fused_proj.weight
model.layers.17.mlp.up_gate_proj.weight_scale
model.layers.17.post_attention_layernorm.weight
model.layers.17.post_attention_layernorm.weight:model.layers.17.post_attention_layernorm.weight
model.layers.17.self_attn.o_proj.weight
model.layers.17.self_attn.o_proj.weight:model.layers.17.self_attn.o_proj.weight
model.layers.17.self_attn.o_proj.weight_scale
model.layers.17.self_attn.qk_norm.k_norm.weight
model.layers.17.self_attn.qk_norm.k_norm.weight:model.layers.17.self_attn.qk_norm.k_norm.weight
model.layers.17.self_attn.qk_norm.q_norm.weight
model.layers.17.self_attn.qk_norm.q_norm.weight:model.layers.17.self_attn.qk_norm.q_norm.weight
model.layers.17.self_attn.qkv_proj.weight
model.layers.17.self_attn.qkv_proj.weight:model.layers.17.self_attn.qkv_proj.weight
model.layers.17.self_attn.qkv_proj.weight_scale
model.layers.18.input_layernorm.weight
model.layers.18.input_layernorm.weight:model.layers.18.input_layernorm.weight
model.layers.18.mlp.down_proj.weight
model.layers.18.mlp.down_proj.weight:model.layers.18.mlp.down_proj.weight
model.layers.18.mlp.down_proj.weight_scale
model.layers.18.mlp.up_gate_proj.weight
model.layers.18.mlp.up_gate_proj.weight:model.layers.18.mlp.gate_up_fused_proj.weight
model.layers.18.mlp.up_gate_proj.weight_scale
model.layers.18.post_attention_layernorm.weight
model.layers.18.post_attention_layernorm.weight:model.layers.18.post_attention_layernorm.weight
model.layers.18.self_attn.o_proj.weight
model.layers.18.self_attn.o_proj.weight:model.layers.18.self_attn.o_proj.weight
model.layers.18.self_attn.o_proj.weight_scale
model.layers.18.self_attn.qk_norm.k_norm.weight
model.layers.18.self_attn.qk_norm.k_norm.weight:model.layers.18.self_attn.qk_norm.k_norm.weight
model.layers.18.self_attn.qk_norm.q_norm.weight
model.layers.18.self_attn.qk_norm.q_norm.weight:model.layers.18.self_attn.qk_norm.q_norm.weight
model.layers.18.self_attn.qkv_proj.weight
model.layers.18.self_attn.qkv_proj.weight:model.layers.18.self_attn.qkv_proj.weight
model.layers.18.self_attn.qkv_proj.weight_scale
model.layers.19.input_layernorm.weight
model.layers.19.input_layernorm.weight:model.layers.19.input_layernorm.weight
model.layers.19.mlp.down_proj.weight
model.layers.19.mlp.down_proj.weight:model.layers.19.mlp.down_proj.weight
model.layers.19.mlp.down_proj.weight_scale
model.layers.19.mlp.up_gate_proj.weight
model.layers.19.mlp.up_gate_proj.weight:model.layers.19.mlp.gate_up_fused_proj.weight
model.layers.19.mlp.up_gate_proj.weight_scale
model.layers.19.post_attention_layernorm.weight
model.layers.19.post_attention_layernorm.weight:model.layers.19.post_attention_layernorm.weight
model.layers.19.self_attn.o_proj.weight
model.layers.19.self_attn.o_proj.weight:model.layers.19.self_attn.o_proj.weight
model.layers.19.self_attn.o_proj.weight_scale
model.layers.19.self_attn.qk_norm.k_norm.weight
model.layers.19.self_attn.qk_norm.k_norm.weight:model.layers.19.self_attn.qk_norm.k_norm.weight
model.layers.19.self_attn.qk_norm.q_norm.weight
model.layers.19.self_attn.qk_norm.q_norm.weight:model.layers.19.self_attn.qk_norm.q_norm.weight
model.layers.19.self_attn.qkv_proj.weight
model.layers.19.self_attn.qkv_proj.weight:model.layers.19.self_attn.qkv_proj.weight
model.layers.19.self_attn.qkv_proj.weight_scale
model.layers.2.input_layernorm.weight
model.layers.2.input_layernorm.weight:model.layers.2.input_layernorm.weight
model.layers.2.mlp.down_proj.weight
model.layers.2.mlp.down_proj.weight:model.layers.2.mlp.down_proj.weight
model.layers.2.mlp.down_proj.weight_scale
model.layers.2.mlp.up_gate_proj.weight
model.layers.2.mlp.up_gate_proj.weight:model.layers.2.mlp.gate_up_fused_proj.weight
model.layers.2.mlp.up_gate_proj.weight_scale
model.layers.2.post_attention_layernorm.weight
model.layers.2.post_attention_layernorm.weight:model.layers.2.post_attention_layernorm.weight
model.layers.2.self_attn.o_proj.weight
model.layers.2.self_attn.o_proj.weight:model.layers.2.self_attn.o_proj.weight
model.layers.2.self_attn.o_proj.weight_scale
model.layers.2.self_attn.qk_norm.k_norm.weight
model.layers.2.self_attn.qk_norm.k_norm.weight:model.layers.2.self_attn.qk_norm.k_norm.weight
model.layers.2.self_attn.qk_norm.q_norm.weight
model.layers.2.self_attn.qk_norm.q_norm.weight:model.layers.2.self_attn.qk_norm.q_norm.weight
model.layers.2.self_attn.qkv_proj.weight
model.layers.2.self_attn.qkv_proj.weight:model.layers.2.self_attn.qkv_proj.weight
model.layers.2.self_attn.qkv_proj.weight_scale
model.layers.20.input_layernorm.weight
model.layers.20.input_layernorm.weight:model.layers.20.input_layernorm.weight
model.layers.20.mlp.down_proj.weight
model.layers.20.mlp.down_proj.weight:model.layers.20.mlp.down_proj.weight
model.layers.20.mlp.down_proj.weight_scale
model.layers.20.mlp.up_gate_proj.weight
model.layers.20.mlp.up_gate_proj.weight:model.layers.20.mlp.gate_up_fused_proj.weight
model.layers.20.mlp.up_gate_proj.weight_scale
model.layers.20.post_attention_layernorm.weight
model.layers.20.post_attention_layernorm.weight:model.layers.20.post_attention_layernorm.weight
model.layers.20.self_attn.o_proj.weight
model.layers.20.self_attn.o_proj.weight:model.layers.20.self_attn.o_proj.weight
model.layers.20.self_attn.o_proj.weight_scale
model.layers.20.self_attn.qk_norm.k_norm.weight
model.layers.20.self_attn.qk_norm.k_norm.weight:model.layers.20.self_attn.qk_norm.k_norm.weight
model.layers.20.self_attn.qk_norm.q_norm.weight
model.layers.20.self_attn.qk_norm.q_norm.weight:model.layers.20.self_attn.qk_norm.q_norm.weight
model.layers.20.self_attn.qkv_proj.weight
model.layers.20.self_attn.qkv_proj.weight:model.layers.20.self_attn.qkv_proj.weight
model.layers.20.self_attn.qkv_proj.weight_scale
model.layers.21.input_layernorm.weight
model.layers.21.input_layernorm.weight:model.layers.21.input_layernorm.weight
model.layers.21.mlp.down_proj.weight
model.layers.21.mlp.down_proj.weight:model.layers.21.mlp.down_proj.weight
model.layers.21.mlp.down_proj.weight_scale
model.layers.21.mlp.up_gate_proj.weight
model.layers.21.mlp.up_gate_proj.weight:model.layers.21.mlp.gate_up_fused_proj.weight
model.layers.21.mlp.up_gate_proj.weight_scale
model.layers.21.post_attention_layernorm.weight
model.layers.21.post_attention_layernorm.weight:model.layers.21.post_attention_layernorm.weight
model.layers.21.self_attn.o_proj.weight
model.layers.21.self_attn.o_proj.weight:model.layers.21.self_attn.o_proj.weight
model.layers.21.self_attn.o_proj.weight_scale
model.layers.21.self_attn.qk_norm.k_norm.weight
model.layers.21.self_attn.qk_norm.k_norm.weight:model.layers.21.self_attn.qk_norm.k_norm.weight
model.layers.21.self_attn.qk_norm.q_norm.weight
model.layers.21.self_attn.qk_norm.q_norm.weight:model.layers.21.self_attn.qk_norm.q_norm.weight
model.layers.21.self_attn.qkv_proj.weight
model.layers.21.self_attn.qkv_proj.weight:model.layers.21.self_attn.qkv_proj.weight
model.layers.21.self_attn.qkv_proj.weight_scale
model.layers.22.input_layernorm.weight
model.layers.22.input_layernorm.weight:model.layers.22.input_layernorm.weight
model.layers.22.mlp.down_proj.weight
model.layers.22.mlp.down_proj.weight:model.layers.22.mlp.down_proj.weight
model.layers.22.mlp.down_proj.weight_scale
model.layers.22.mlp.up_gate_proj.weight
model.layers.22.mlp.up_gate_proj.weight:model.layers.22.mlp.gate_up_fused_proj.weight
model.layers.22.mlp.up_gate_proj.weight_scale
model.layers.22.post_attention_layernorm.weight
model.layers.22.post_attention_layernorm.weight:model.layers.22.post_attention_layernorm.weight
model.layers.22.self_attn.o_proj.weight
model.layers.22.self_attn.o_proj.weight:model.layers.22.self_attn.o_proj.weight
model.layers.22.self_attn.o_proj.weight_scale
model.layers.22.self_attn.qk_norm.k_norm.weight
model.layers.22.self_attn.qk_norm.k_norm.weight:model.layers.22.self_attn.qk_norm.k_norm.weight
model.layers.22.self_attn.qk_norm.q_norm.weight
model.layers.22.self_attn.qk_norm.q_norm.weight:model.layers.22.self_attn.qk_norm.q_norm.weight
model.layers.22.self_attn.qkv_proj.weight
model.layers.22.self_attn.qkv_proj.weight:model.layers.22.self_attn.qkv_proj.weight
model.layers.22.self_attn.qkv_proj.weight_scale
model.layers.23.input_layernorm.weight
model.layers.23.input_layernorm.weight:model.layers.23.input_layernorm.weight
model.layers.23.mlp.down_proj.weight
model.layers.23.mlp.down_proj.weight:model.layers.23.mlp.down_proj.weight
model.layers.23.mlp.down_proj.weight_scale
model.layers.23.mlp.up_gate_proj.weight
model.layers.23.mlp.up_gate_proj.weight:model.layers.23.mlp.gate_up_fused_proj.weight
model.layers.23.mlp.up_gate_proj.weight_scale
model.layers.23.post_attention_layernorm.weight
model.layers.23.post_attention_layernorm.weight:model.layers.23.post_attention_layernorm.weight
model.layers.23.self_attn.o_proj.weight
model.layers.23.self_attn.o_proj.weight:model.layers.23.self_attn.o_proj.weight
model.layers.23.self_attn.o_proj.weight_scale
model.layers.23.self_attn.qk_norm.k_norm.weight
model.layers.23.self_attn.qk_norm.k_norm.weight:model.layers.23.self_attn.qk_norm.k_norm.weight
model.layers.23.self_attn.qk_norm.q_norm.weight
model.layers.23.self_attn.qk_norm.q_norm.weight:model.layers.23.self_attn.qk_norm.q_norm.weight
model.layers.23.self_attn.qkv_proj.weight
model.layers.23.self_attn.qkv_proj.weight:model.layers.23.self_attn.qkv_proj.weight
model.layers.23.self_attn.qkv_proj.weight_scale
model.layers.24.input_layernorm.weight
model.layers.24.input_layernorm.weight:model.layers.24.input_layernorm.weight
model.layers.24.mlp.down_proj.weight
model.layers.24.mlp.down_proj.weight:model.layers.24.mlp.down_proj.weight
model.layers.24.mlp.down_proj.weight_scale
model.layers.24.mlp.up_gate_proj.weight
model.layers.24.mlp.up_gate_proj.weight:model.layers.24.mlp.gate_up_fused_proj.weight
model.layers.24.mlp.up_gate_proj.weight_scale
model.layers.24.post_attention_layernorm.weight
model.layers.24.post_attention_layernorm.weight:model.layers.24.post_attention_layernorm.weight
model.layers.24.self_attn.o_proj.weight
model.layers.24.self_attn.o_proj.weight:model.layers.24.self_attn.o_proj.weight
model.layers.24.self_attn.o_proj.weight_scale
model.layers.24.self_attn.qk_norm.k_norm.weight
model.layers.24.self_attn.qk_norm.k_norm.weight:model.layers.24.self_attn.qk_norm.k_norm.weight
model.layers.24.self_attn.qk_norm.q_norm.weight
model.layers.24.self_attn.qk_norm.q_norm.weight:model.layers.24.self_attn.qk_norm.q_norm.weight
model.layers.24.self_attn.qkv_proj.weight
model.layers.24.self_attn.qkv_proj.weight:model.layers.24.self_attn.qkv_proj.weight
model.layers.24.self_attn.qkv_proj.weight_scale
model.layers.25.input_layernorm.weight
model.layers.25.input_layernorm.weight:model.layers.25.input_layernorm.weight
model.layers.25.mlp.down_proj.weight
model.layers.25.mlp.down_proj.weight:model.layers.25.mlp.down_proj.weight
model.layers.25.mlp.down_proj.weight_scale
model.layers.25.mlp.up_gate_proj.weight
model.layers.25.mlp.up_gate_proj.weight:model.layers.25.mlp.gate_up_fused_proj.weight
model.layers.25.mlp.up_gate_proj.weight_scale
model.layers.25.post_attention_layernorm.weight
model.layers.25.post_attention_layernorm.weight:model.layers.25.post_attention_layernorm.weight
model.layers.25.self_attn.o_proj.weight
model.layers.25.self_attn.o_proj.weight:model.layers.25.self_attn.o_proj.weight
model.layers.25.self_attn.o_proj.weight_scale
model.layers.25.self_attn.qk_norm.k_norm.weight
model.layers.25.self_attn.qk_norm.k_norm.weight:model.layers.25.self_attn.qk_norm.k_norm.weight
model.layers.25.self_attn.qk_norm.q_norm.weight
model.layers.25.self_attn.qk_norm.q_norm.weight:model.layers.25.self_attn.qk_norm.q_norm.weight
model.layers.25.self_attn.qkv_proj.weight
model.layers.25.self_attn.qkv_proj.weight:model.layers.25.self_attn.qkv_proj.weight
model.layers.25.self_attn.qkv_proj.weight_scale
model.layers.26.input_layernorm.weight
model.layers.26.input_layernorm.weight:model.layers.26.input_layernorm.weight
model.layers.26.mlp.down_proj.weight
model.layers.26.mlp.down_proj.weight:model.layers.26.mlp.down_proj.weight
model.layers.26.mlp.down_proj.weight_scale
model.layers.26.mlp.up_gate_proj.weight
model.layers.26.mlp.up_gate_proj.weight:model.layers.26.mlp.gate_up_fused_proj.weight
model.layers.26.mlp.up_gate_proj.weight_scale
model.layers.26.post_attention_layernorm.weight
model.layers.26.post_attention_layernorm.weight:model.layers.26.post_attention_layernorm.weight
model.layers.26.self_attn.o_proj.weight
model.layers.26.self_attn.o_proj.weight:model.layers.26.self_attn.o_proj.weight
model.layers.26.self_attn.o_proj.weight_scale
model.layers.26.self_attn.qk_norm.k_norm.weight
model.layers.26.self_attn.qk_norm.k_norm.weight:model.layers.26.self_attn.qk_norm.k_norm.weight
model.layers.26.self_attn.qk_norm.q_norm.weight
model.layers.26.self_attn.qk_norm.q_norm.weight:model.layers.26.self_attn.qk_norm.q_norm.weight
model.layers.26.self_attn.qkv_proj.weight
model.layers.26.self_attn.qkv_proj.weight:model.layers.26.self_attn.qkv_proj.weight
model.layers.26.self_attn.qkv_proj.weight_scale
model.layers.27.input_layernorm.weight
model.layers.27.input_layernorm.weight:model.layers.27.input_layernorm.weight
model.layers.27.mlp.down_proj.weight
model.layers.27.mlp.down_proj.weight:model.layers.27.mlp.down_proj.weight
model.layers.27.mlp.down_proj.weight_scale
model.layers.27.mlp.up_gate_proj.weight
model.layers.27.mlp.up_gate_proj.weight:model.layers.27.mlp.gate_up_fused_proj.weight
model.layers.27.mlp.up_gate_proj.weight_scale
model.layers.27.post_attention_layernorm.weight
model.layers.27.post_attention_layernorm.weight:model.layers.27.post_attention_layernorm.weight
model.layers.27.self_attn.o_proj.weight
model.layers.27.self_attn.o_proj.weight:model.layers.27.self_attn.o_proj.weight
model.layers.27.self_attn.o_proj.weight_scale
model.layers.27.self_attn.qk_norm.k_norm.weight
model.layers.27.self_attn.qk_norm.k_norm.weight:model.layers.27.self_attn.qk_norm.k_norm.weight
model.layers.27.self_attn.qk_norm.q_norm.weight
model.layers.27.self_attn.qk_norm.q_norm.weight:model.layers.27.self_attn.qk_norm.q_norm.weight
model.layers.27.self_attn.qkv_proj.weight
model.layers.27.self_attn.qkv_proj.weight:model.layers.27.self_attn.qkv_proj.weight
model.layers.27.self_attn.qkv_proj.weight_scale
model.layers.28.input_layernorm.weight
model.layers.28.input_layernorm.weight:model.layers.28.input_layernorm.weight
model.layers.28.mlp.down_proj.weight
model.layers.28.mlp.down_proj.weight:model.layers.28.mlp.down_proj.weight
model.layers.28.mlp.down_proj.weight_scale
model.layers.28.mlp.up_gate_proj.weight
model.layers.28.mlp.up_gate_proj.weight:model.layers.28.mlp.gate_up_fused_proj.weight
model.layers.28.mlp.up_gate_proj.weight_scale
model.layers.28.post_attention_layernorm.weight
model.layers.28.post_attention_layernorm.weight:model.layers.28.post_attention_layernorm.weight
model.layers.28.self_attn.o_proj.weight
model.layers.28.self_attn.o_proj.weight:model.layers.28.self_attn.o_proj.weight
model.layers.28.self_attn.o_proj.weight_scale
model.layers.28.self_attn.qk_norm.k_norm.weight
model.layers.28.self_attn.qk_norm.k_norm.weight:model.layers.28.self_attn.qk_norm.k_norm.weight
model.layers.28.self_attn.qk_norm.q_norm.weight
model.layers.28.self_attn.qk_norm.q_norm.weight:model.layers.28.self_attn.qk_norm.q_norm.weight
model.layers.28.self_attn.qkv_proj.weight
model.layers.28.self_attn.qkv_proj.weight:model.layers.28.self_attn.qkv_proj.weight
model.layers.28.self_attn.qkv_proj.weight_scale
model.layers.29.input_layernorm.weight
model.layers.29.input_layernorm.weight:model.layers.29.input_layernorm.weight
model.layers.29.mlp.down_proj.weight
model.layers.29.mlp.down_proj.weight:model.layers.29.mlp.down_proj.weight
model.layers.29.mlp.down_proj.weight_scale
model.layers.29.mlp.up_gate_proj.weight
model.layers.29.mlp.up_gate_proj.weight:model.layers.29.mlp.gate_up_fused_proj.weight
model.layers.29.mlp.up_gate_proj.weight_scale
model.layers.29.post_attention_layernorm.weight
model.layers.29.post_attention_layernorm.weight:model.layers.29.post_attention_layernorm.weight
model.layers.29.self_attn.o_proj.weight
model.layers.29.self_attn.o_proj.weight:model.layers.29.self_attn.o_proj.weight
model.layers.29.self_attn.o_proj.weight_scale
model.layers.29.self_attn.qk_norm.k_norm.weight
model.layers.29.self_attn.qk_norm.k_norm.weight:model.layers.29.self_attn.qk_norm.k_norm.weight
model.layers.29.self_attn.qk_norm.q_norm.weight
model.layers.29.self_attn.qk_norm.q_norm.weight:model.layers.29.self_attn.qk_norm.q_norm.weight
model.layers.29.self_attn.qkv_proj.weight
model.layers.29.self_attn.qkv_proj.weight:model.layers.29.self_attn.qkv_proj.weight
model.layers.29.self_attn.qkv_proj.weight_scale
model.layers.3.input_layernorm.weight
model.layers.3.input_layernorm.weight:model.layers.3.input_layernorm.weight
model.layers.3.mlp.down_proj.weight
model.layers.3.mlp.down_proj.weight:model.layers.3.mlp.down_proj.weight
model.layers.3.mlp.down_proj.weight_scale
model.layers.3.mlp.up_gate_proj.weight
model.layers.3.mlp.up_gate_proj.weight:model.layers.3.mlp.gate_up_fused_proj.weight
model.layers.3.mlp.up_gate_proj.weight_scale
model.layers.3.post_attention_layernorm.weight
model.layers.3.post_attention_layernorm.weight:model.layers.3.post_attention_layernorm.weight
model.layers.3.self_attn.o_proj.weight
model.layers.3.self_attn.o_proj.weight:model.layers.3.self_attn.o_proj.weight
model.layers.3.self_attn.o_proj.weight_scale
model.layers.3.self_attn.qk_norm.k_norm.weight
model.layers.3.self_attn.qk_norm.k_norm.weight:model.layers.3.self_attn.qk_norm.k_norm.weight
model.layers.3.self_attn.qk_norm.q_norm.weight
model.layers.3.self_attn.qk_norm.q_norm.weight:model.layers.3.self_attn.qk_norm.q_norm.weight
model.layers.3.self_attn.qkv_proj.weight
model.layers.3.self_attn.qkv_proj.weight:model.layers.3.self_attn.qkv_proj.weight
model.layers.3.self_attn.qkv_proj.weight_scale
model.layers.30.input_layernorm.weight
model.layers.30.input_layernorm.weight:model.layers.30.input_layernorm.weight
model.layers.30.mlp.down_proj.weight
model.layers.30.mlp.down_proj.weight:model.layers.30.mlp.down_proj.weight
model.layers.30.mlp.down_proj.weight_scale
model.layers.30.mlp.up_gate_proj.weight
model.layers.30.mlp.up_gate_proj.weight:model.layers.30.mlp.gate_up_fused_proj.weight
model.layers.30.mlp.up_gate_proj.weight_scale
model.layers.30.post_attention_layernorm.weight
model.layers.30.post_attention_layernorm.weight:model.layers.30.post_attention_layernorm.weight
model.layers.30.self_attn.o_proj.weight
model.layers.30.self_attn.o_proj.weight:model.layers.30.self_attn.o_proj.weight
model.layers.30.self_attn.o_proj.weight_scale
model.layers.30.self_attn.qk_norm.k_norm.weight
model.layers.30.self_attn.qk_norm.k_norm.weight:model.layers.30.self_attn.qk_norm.k_norm.weight
model.layers.30.self_attn.qk_norm.q_norm.weight
model.layers.30.self_attn.qk_norm.q_norm.weight:model.layers.30.self_attn.qk_norm.q_norm.weight
model.layers.30.self_attn.qkv_proj.weight
model.layers.30.self_attn.qkv_proj.weight:model.layers.30.self_attn.qkv_proj.weight
model.layers.30.self_attn.qkv_proj.weight_scale
model.layers.31.input_layernorm.weight
model.layers.31.input_layernorm.weight:model.layers.31.input_layernorm.weight
model.layers.31.mlp.down_proj.weight
model.layers.31.mlp.down_proj.weight:model.layers.31.mlp.down_proj.weight
model.layers.31.mlp.down_proj.weight_scale
model.layers.31.mlp.up_gate_proj.weight
model.layers.31.mlp.up_gate_proj.weight:model.layers.31.mlp.gate_up_fused_proj.weight
model.layers.31.mlp.up_gate_proj.weight_scale
model.layers.31.post_attention_layernorm.weight
model.layers.31.post_attention_layernorm.weight:model.layers.31.post_attention_layernorm.weight
model.layers.31.self_attn.o_proj.weight
model.layers.31.self_attn.o_proj.weight:model.layers.31.self_attn.o_proj.weight
model.layers.31.self_attn.o_proj.weight_scale
model.layers.31.self_attn.qk_norm.k_norm.weight
model.layers.31.self_attn.qk_norm.k_norm.weight:model.layers.31.self_attn.qk_norm.k_norm.weight
model.layers.31.self_attn.qk_norm.q_norm.weight
model.layers.31.self_attn.qk_norm.q_norm.weight:model.layers.31.self_attn.qk_norm.q_norm.weight
model.layers.31.self_attn.qkv_proj.weight
model.layers.31.self_attn.qkv_proj.weight:model.layers.31.self_attn.qkv_proj.weight
model.layers.31.self_attn.qkv_proj.weight_scale
model.layers.32.input_layernorm.weight
model.layers.32.input_layernorm.weight:model.layers.32.input_layernorm.weight
model.layers.32.mlp.down_proj.weight
model.layers.32.mlp.down_proj.weight:model.layers.32.mlp.down_proj.weight
model.layers.32.mlp.down_proj.weight_scale
model.layers.32.mlp.up_gate_proj.weight
model.layers.32.mlp.up_gate_proj.weight:model.layers.32.mlp.gate_up_fused_proj.weight
model.layers.32.mlp.up_gate_proj.weight_scale
model.layers.32.post_attention_layernorm.weight
model.layers.32.post_attention_layernorm.weight:model.layers.32.post_attention_layernorm.weight
model.layers.32.self_attn.o_proj.weight
model.layers.32.self_attn.o_proj.weight:model.layers.32.self_attn.o_proj.weight
model.layers.32.self_attn.o_proj.weight_scale
model.layers.32.self_attn.qk_norm.k_norm.weight
model.layers.32.self_attn.qk_norm.k_norm.weight:model.layers.32.self_attn.qk_norm.k_norm.weight
model.layers.32.self_attn.qk_norm.q_norm.weight
model.layers.32.self_attn.qk_norm.q_norm.weight:model.layers.32.self_attn.qk_norm.q_norm.weight
model.layers.32.self_attn.qkv_proj.weight
model.layers.32.self_attn.qkv_proj.weight:model.layers.32.self_attn.qkv_proj.weight
model.layers.32.self_attn.qkv_proj.weight_scale
model.layers.33.input_layernorm.weight
model.layers.33.input_layernorm.weight:model.layers.33.input_layernorm.weight
model.layers.33.mlp.down_proj.weight
model.layers.33.mlp.down_proj.weight:model.layers.33.mlp.down_proj.weight
model.layers.33.mlp.down_proj.weight_scale
model.layers.33.mlp.up_gate_proj.weight
model.layers.33.mlp.up_gate_proj.weight:model.layers.33.mlp.gate_up_fused_proj.weight
model.layers.33.mlp.up_gate_proj.weight_scale
model.layers.33.post_attention_layernorm.weight
model.layers.33.post_attention_layernorm.weight:model.layers.33.post_attention_layernorm.weight
model.layers.33.self_attn.o_proj.weight
model.layers.33.self_attn.o_proj.weight:model.layers.33.self_attn.o_proj.weight
model.layers.33.self_attn.o_proj.weight_scale
model.layers.33.self_attn.qk_norm.k_norm.weight
model.layers.33.self_attn.qk_norm.k_norm.weight:model.layers.33.self_attn.qk_norm.k_norm.weight
model.layers.33.self_attn.qk_norm.q_norm.weight
model.layers.33.self_attn.qk_norm.q_norm.weight:model.layers.33.self_attn.qk_norm.q_norm.weight
model.layers.33.self_attn.qkv_proj.weight
model.layers.33.self_attn.qkv_proj.weight:model.layers.33.self_attn.qkv_proj.weight
model.layers.33.self_attn.qkv_proj.weight_scale
model.layers.34.input_layernorm.weight
model.layers.34.input_layernorm.weight:model.layers.34.input_layernorm.weight
model.layers.34.mlp.down_proj.weight
model.layers.34.mlp.down_proj.weight:model.layers.34.mlp.down_proj.weight
model.layers.34.mlp.down_proj.weight_scale
model.layers.34.mlp.up_gate_proj.weight
model.layers.34.mlp.up_gate_proj.weight:model.layers.34.mlp.gate_up_fused_proj.weight
model.layers.34.mlp.up_gate_proj.weight_scale
model.layers.34.post_attention_layernorm.weight
model.layers.34.post_attention_layernorm.weight:model.layers.34.post_attention_layernorm.weight
model.layers.34.self_attn.o_proj.weight
model.layers.34.self_attn.o_proj.weight:model.layers.34.self_attn.o_proj.weight
model.layers.34.self_attn.o_proj.weight_scale
model.layers.34.self_attn.qk_norm.k_norm.weight
model.layers.34.self_attn.qk_norm.k_norm.weight:model.layers.34.self_attn.qk_norm.k_norm.weight
model.layers.34.self_attn.qk_norm.q_norm.weight
model.layers.34.self_attn.qk_norm.q_norm.weight:model.layers.34.self_attn.qk_norm.q_norm.weight
model.layers.34.self_attn.qkv_proj.weight
model.layers.34.self_attn.qkv_proj.weight:model.layers.34.self_attn.qkv_proj.weight
model.layers.34.self_attn.qkv_proj.weight_scale
model.layers.35.input_layernorm.weight
model.layers.35.input_layernorm.weight:model.layers.35.input_layernorm.weight
model.layers.35.mlp.down_proj.weight
model.layers.35.mlp.down_proj.weight:model.layers.35.mlp.down_proj.weight
model.layers.35.mlp.down_proj.weight_scale
model.layers.35.mlp.up_gate_proj.weight
model.layers.35.mlp.up_gate_proj.weight:model.layers.35.mlp.gate_up_fused_proj.weight
model.layers.35.mlp.up_gate_proj.weight_scale
model.layers.35.post_attention_layernorm.weight
model.layers.35.post_attention_layernorm.weight:model.layers.35.post_attention_layernorm.weight
model.layers.35.self_attn.o_proj.weight
model.layers.35.self_attn.o_proj.weight:model.layers.35.self_attn.o_proj.weight
model.layers.35.self_attn.o_proj.weight_scale
model.layers.35.self_attn.qk_norm.k_norm.weight
model.layers.35.self_attn.qk_norm.k_norm.weight:model.layers.35.self_attn.qk_norm.k_norm.weight
model.layers.35.self_attn.qk_norm.q_norm.weight
model.layers.35.self_attn.qk_norm.q_norm.weight:model.layers.35.self_attn.qk_norm.q_norm.weight
model.layers.35.self_attn.qkv_proj.weight
model.layers.35.self_attn.qkv_proj.weight:model.layers.35.self_attn.qkv_proj.weight
model.layers.35.self_attn.qkv_proj.weight_scale
model.layers.4.input_layernorm.weight
model.layers.4.input_layernorm.weight:model.layers.4.input_layernorm.weight
model.layers.4.mlp.down_proj.weight
model.layers.4.mlp.down_proj.weight:model.layers.4.mlp.down_proj.weight
model.layers.4.mlp.down_proj.weight_scale
model.layers.4.mlp.up_gate_proj.weight
model.layers.4.mlp.up_gate_proj.weight:model.layers.4.mlp.gate_up_fused_proj.weight
model.layers.4.mlp.up_gate_proj.weight_scale
model.layers.4.post_attention_layernorm.weight
model.layers.4.post_attention_layernorm.weight:model.layers.4.post_attention_layernorm.weight
model.layers.4.self_attn.o_proj.weight
model.layers.4.self_attn.o_proj.weight:model.layers.4.self_attn.o_proj.weight
model.layers.4.self_attn.o_proj.weight_scale
model.layers.4.self_attn.qk_norm.k_norm.weight
model.layers.4.self_attn.qk_norm.k_norm.weight:model.layers.4.self_attn.qk_norm.k_norm.weight
model.layers.4.self_attn.qk_norm.q_norm.weight
model.layers.4.self_attn.qk_norm.q_norm.weight:model.layers.4.self_attn.qk_norm.q_norm.weight
model.layers.4.self_attn.qkv_proj.weight
model.layers.4.self_attn.qkv_proj.weight:model.layers.4.self_attn.qkv_proj.weight
model.layers.4.self_attn.qkv_proj.weight_scale
model.layers.5.input_layernorm.weight
model.layers.5.input_layernorm.weight:model.layers.5.input_layernorm.weight
model.layers.5.mlp.down_proj.weight
model.layers.5.mlp.down_proj.weight:model.layers.5.mlp.down_proj.weight
model.layers.5.mlp.down_proj.weight_scale
model.layers.5.mlp.up_gate_proj.weight
model.layers.5.mlp.up_gate_proj.weight:model.layers.5.mlp.gate_up_fused_proj.weight
model.layers.5.mlp.up_gate_proj.weight_scale
model.layers.5.post_attention_layernorm.weight
model.layers.5.post_attention_layernorm.weight:model.layers.5.post_attention_layernorm.weight
model.layers.5.self_attn.o_proj.weight
model.layers.5.self_attn.o_proj.weight:model.layers.5.self_attn.o_proj.weight
model.layers.5.self_attn.o_proj.weight_scale
model.layers.5.self_attn.qk_norm.k_norm.weight
model.layers.5.self_attn.qk_norm.k_norm.weight:model.layers.5.self_attn.qk_norm.k_norm.weight
model.layers.5.self_attn.qk_norm.q_norm.weight
model.layers.5.self_attn.qk_norm.q_norm.weight:model.layers.5.self_attn.qk_norm.q_norm.weight
model.layers.5.self_attn.qkv_proj.weight
model.layers.5.self_attn.qkv_proj.weight:model.layers.5.self_attn.qkv_proj.weight
model.layers.5.self_attn.qkv_proj.weight_scale
model.layers.6.input_layernorm.weight
model.layers.6.input_layernorm.weight:model.layers.6.input_layernorm.weight
model.layers.6.mlp.down_proj.weight
model.layers.6.mlp.down_proj.weight:model.layers.6.mlp.down_proj.weight
model.layers.6.mlp.down_proj.weight_scale
model.layers.6.mlp.up_gate_proj.weight
model.layers.6.mlp.up_gate_proj.weight:model.layers.6.mlp.gate_up_fused_proj.weight
model.layers.6.mlp.up_gate_proj.weight_scale
model.layers.6.post_attention_layernorm.weight
model.layers.6.post_attention_layernorm.weight:model.layers.6.post_attention_layernorm.weight
model.layers.6.self_attn.o_proj.weight
model.layers.6.self_attn.o_proj.weight:model.layers.6.self_attn.o_proj.weight
model.layers.6.self_attn.o_proj.weight_scale
model.layers.6.self_attn.qk_norm.k_norm.weight
model.layers.6.self_attn.qk_norm.k_norm.weight:model.layers.6.self_attn.qk_norm.k_norm.weight
model.layers.6.self_attn.qk_norm.q_norm.weight
model.layers.6.self_attn.qk_norm.q_norm.weight:model.layers.6.self_attn.qk_norm.q_norm.weight
model.layers.6.self_attn.qkv_proj.weight
model.layers.6.self_attn.qkv_proj.weight:model.layers.6.self_attn.qkv_proj.weight
model.layers.6.self_attn.qkv_proj.weight_scale
model.layers.7.input_layernorm.weight
model.layers.7.input_layernorm.weight:model.layers.7.input_layernorm.weight
model.layers.7.mlp.down_proj.weight
model.layers.7.mlp.down_proj.weight:model.layers.7.mlp.down_proj.weight
model.layers.7.mlp.down_proj.weight_scale
model.layers.7.mlp.up_gate_proj.weight
model.layers.7.mlp.up_gate_proj.weight:model.layers.7.mlp.gate_up_fused_proj.weight
model.layers.7.mlp.up_gate_proj.weight_scale
model.layers.7.post_attention_layernorm.weight
model.layers.7.post_attention_layernorm.weight:model.layers.7.post_attention_layernorm.weight
model.layers.7.self_attn.o_proj.weight
model.layers.7.self_attn.o_proj.weight:model.layers.7.self_attn.o_proj.weight
model.layers.7.self_attn.o_proj.weight_scale
model.layers.7.self_attn.qk_norm.k_norm.weight
model.layers.7.self_attn.qk_norm.k_norm.weight:model.layers.7.self_attn.qk_norm.k_norm.weight
model.layers.7.self_attn.qk_norm.q_norm.weight
model.layers.7.self_attn.qk_norm.q_norm.weight:model.layers.7.self_attn.qk_norm.q_norm.weight
model.layers.7.self_attn.qkv_proj.weight
model.layers.7.self_attn.qkv_proj.weight:model.layers.7.self_attn.qkv_proj.weight
model.layers.7.self_attn.qkv_proj.weight_scale
model.layers.8.input_layernorm.weight
model.layers.8.input_layernorm.weight:model.layers.8.input_layernorm.weight
model.layers.8.mlp.down_proj.weight
model.layers.8.mlp.down_proj.weight:model.layers.8.mlp.down_proj.weight
model.layers.8.mlp.down_proj.weight_scale
model.layers.8.mlp.up_gate_proj.weight
model.layers.8.mlp.up_gate_proj.weight:model.layers.8.mlp.gate_up_fused_proj.weight
model.layers.8.mlp.up_gate_proj.weight_scale
model.layers.8.post_attention_layernorm.weight
model.layers.8.post_attention_layernorm.weight:model.layers.8.post_attention_layernorm.weight
model.layers.8.self_attn.o_proj.weight
model.layers.8.self_attn.o_proj.weight:model.layers.8.self_attn.o_proj.weight
model.layers.8.self_attn.o_proj.weight_scale
model.layers.8.self_attn.qk_norm.k_norm.weight
model.layers.8.self_attn.qk_norm.k_norm.weight:model.layers.8.self_attn.qk_norm.k_norm.weight
model.layers.8.self_attn.qk_norm.q_norm.weight
model.layers.8.self_attn.qk_norm.q_norm.weight:model.layers.8.self_attn.qk_norm.q_norm.weight
model.layers.8.self_attn.qkv_proj.weight
model.layers.8.self_attn.qkv_proj.weight:model.layers.8.self_attn.qkv_proj.weight
model.layers.8.self_attn.qkv_proj.weight_scale
model.layers.9.input_layernorm.weight
model.layers.9.input_layernorm.weight:model.layers.9.input_layernorm.weight
model.layers.9.mlp.down_proj.weight
model.layers.9.mlp.down_proj.weight:model.layers.9.mlp.down_proj.weight
model.layers.9.mlp.down_proj.weight_scale
model.layers.9.mlp.up_gate_proj.weight
model.layers.9.mlp.up_gate_proj.weight:model.layers.9.mlp.gate_up_fused_proj.weight
model.layers.9.mlp.up_gate_proj.weight_scale
model.layers.9.post_attention_layernorm.weight
model.layers.9.post_attention_layernorm.weight:model.layers.9.post_attention_layernorm.weight
model.layers.9.self_attn.o_proj.weight
model.layers.9.self_attn.o_proj.weight:model.layers.9.self_attn.o_proj.weight
model.layers.9.self_attn.o_proj.weight_scale
model.layers.9.self_attn.qk_norm.k_norm.weight
model.layers.9.self_attn.qk_norm.k_norm.weight:model.layers.9.self_attn.qk_norm.k_norm.weight
model.layers.9.self_attn.qk_norm.q_norm.weight
model.layers.9.self_attn.qk_norm.q_norm.weight:model.layers.9.self_attn.qk_norm.q_norm.weight
model.layers.9.self_attn.qkv_proj.weight
model.layers.9.self_attn.qkv_proj.weight:model.layers.9.self_attn.qkv_proj.weight
model.layers.9.self_attn.qkv_proj.weight_scale
model.norm.weight
model.norm.weight:model.norm.weight
visual.blocks.0.attn.proj.bias
visual.blocks.0.attn.proj.bias:visual.blocks.0.attn.proj.bias
visual.blocks.0.attn.proj.weight
visual.blocks.0.attn.proj.weight:visual.blocks.0.attn.proj.weight
visual.blocks.0.attn.qkv.bias
visual.blocks.0.attn.qkv.bias:visual.blocks.0.attn.qkv.bias
visual.blocks.0.attn.qkv.weight
visual.blocks.0.attn.qkv.weight:visual.blocks.0.attn.qkv.weight
visual.blocks.0.mlp.linear_fc1.bias
visual.blocks.0.mlp.linear_fc1.bias:visual.blocks.0.mlp.linear_fc1.bias
visual.blocks.0.mlp.linear_fc1.weight
visual.blocks.0.mlp.linear_fc1.weight:visual.blocks.0.mlp.linear_fc1.weight
visual.blocks.0.mlp.linear_fc2.bias
visual.blocks.0.mlp.linear_fc2.bias:visual.blocks.0.mlp.linear_fc2.bias
visual.blocks.0.mlp.linear_fc2.weight
visual.blocks.0.mlp.linear_fc2.weight:visual.blocks.0.mlp.linear_fc2.weight
visual.blocks.0.norm1.bias
visual.blocks.0.norm1.bias:visual.blocks.0.norm1.bias
visual.blocks.0.norm1.weight
visual.blocks.0.norm1.weight:visual.blocks.0.norm1.weight
visual.blocks.0.norm2.bias
visual.blocks.0.norm2.bias:visual.blocks.0.norm2.bias
visual.blocks.0.norm2.weight
visual.blocks.0.norm2.weight:visual.blocks.0.norm2.weight
visual.blocks.1.attn.proj.bias
visual.blocks.1.attn.proj.bias:visual.blocks.1.attn.proj.bias
visual.blocks.1.attn.proj.weight
visual.blocks.1.attn.proj.weight:visual.blocks.1.attn.proj.weight
visual.blocks.1.attn.qkv.bias
visual.blocks.1.attn.qkv.bias:visual.blocks.1.attn.qkv.bias
visual.blocks.1.attn.qkv.weight
visual.blocks.1.attn.qkv.weight:visual.blocks.1.attn.qkv.weight
visual.blocks.1.mlp.linear_fc1.bias
visual.blocks.1.mlp.linear_fc1.bias:visual.blocks.1.mlp.linear_fc1.bias
visual.blocks.1.mlp.linear_fc1.weight
visual.blocks.1.mlp.linear_fc1.weight:visual.blocks.1.mlp.linear_fc1.weight
visual.blocks.1.mlp.linear_fc2.bias
visual.blocks.1.mlp.linear_fc2.bias:visual.blocks.1.mlp.linear_fc2.bias
visual.blocks.1.mlp.linear_fc2.weight
visual.blocks.1.mlp.linear_fc2.weight:visual.blocks.1.mlp.linear_fc2.weight
visual.blocks.1.norm1.bias
visual.blocks.1.norm1.bias:visual.blocks.1.norm1.bias
visual.blocks.1.norm1.weight
visual.blocks.1.norm1.weight:visual.blocks.1.norm1.weight
visual.blocks.1.norm2.bias
visual.blocks.1.norm2.bias:visual.blocks.1.norm2.bias
visual.blocks.1.norm2.weight
visual.blocks.1.norm2.weight:visual.blocks.1.norm2.weight
visual.blocks.10.attn.proj.bias
visual.blocks.10.attn.proj.bias:visual.blocks.10.attn.proj.bias
visual.blocks.10.attn.proj.weight
visual.blocks.10.attn.proj.weight:visual.blocks.10.attn.proj.weight
visual.blocks.10.attn.qkv.bias
visual.blocks.10.attn.qkv.bias:visual.blocks.10.attn.qkv.bias
visual.blocks.10.attn.qkv.weight
visual.blocks.10.attn.qkv.weight:visual.blocks.10.attn.qkv.weight
visual.blocks.10.mlp.linear_fc1.bias
visual.blocks.10.mlp.linear_fc1.bias:visual.blocks.10.mlp.linear_fc1.bias
visual.blocks.10.mlp.linear_fc1.weight
visual.blocks.10.mlp.linear_fc1.weight:visual.blocks.10.mlp.linear_fc1.weight
visual.blocks.10.mlp.linear_fc2.bias
visual.blocks.10.mlp.linear_fc2.bias:visual.blocks.10.mlp.linear_fc2.bias
visual.blocks.10.mlp.linear_fc2.weight
visual.blocks.10.mlp.linear_fc2.weight:visual.blocks.10.mlp.linear_fc2.weight
visual.blocks.10.norm1.bias
visual.blocks.10.norm1.bias:visual.blocks.10.norm1.bias
visual.blocks.10.norm1.weight
visual.blocks.10.norm1.weight:visual.blocks.10.norm1.weight
visual.blocks.10.norm2.bias
visual.blocks.10.norm2.bias:visual.blocks.10.norm2.bias
visual.blocks.10.norm2.weight
visual.blocks.10.norm2.weight:visual.blocks.10.norm2.weight
visual.blocks.11.attn.proj.bias
visual.blocks.11.attn.proj.bias:visual.blocks.11.attn.proj.bias
visual.blocks.11.attn.proj.weight
visual.blocks.11.attn.proj.weight:visual.blocks.11.attn.proj.weight
visual.blocks.11.attn.qkv.bias
visual.blocks.11.attn.qkv.bias:visual.blocks.11.attn.qkv.bias
visual.blocks.11.attn.qkv.weight
visual.blocks.11.attn.qkv.weight:visual.blocks.11.attn.qkv.weight
visual.blocks.11.mlp.linear_fc1.bias
visual.blocks.11.mlp.linear_fc1.bias:visual.blocks.11.mlp.linear_fc1.bias
visual.blocks.11.mlp.linear_fc1.weight
visual.blocks.11.mlp.linear_fc1.weight:visual.blocks.11.mlp.linear_fc1.weight
visual.blocks.11.mlp.linear_fc2.bias
visual.blocks.11.mlp.linear_fc2.bias:visual.blocks.11.mlp.linear_fc2.bias
visual.blocks.11.mlp.linear_fc2.weight
visual.blocks.11.mlp.linear_fc2.weight:visual.blocks.11.mlp.linear_fc2.weight
visual.blocks.11.norm1.bias
visual.blocks.11.norm1.bias:visual.blocks.11.norm1.bias
visual.blocks.11.norm1.weight
visual.blocks.11.norm1.weight:visual.blocks.11.norm1.weight
visual.blocks.11.norm2.bias
visual.blocks.11.norm2.bias:visual.blocks.11.norm2.bias
visual.blocks.11.norm2.weight
visual.blocks.11.norm2.weight:visual.blocks.11.norm2.weight
visual.blocks.12.attn.proj.bias
visual.blocks.12.attn.proj.bias:visual.blocks.12.attn.proj.bias
visual.blocks.12.attn.proj.weight
visual.blocks.12.attn.proj.weight:visual.blocks.12.attn.proj.weight
visual.blocks.12.attn.qkv.bias
visual.blocks.12.attn.qkv.bias:visual.blocks.12.attn.qkv.bias
visual.blocks.12.attn.qkv.weight
visual.blocks.12.attn.qkv.weight:visual.blocks.12.attn.qkv.weight
visual.blocks.12.mlp.linear_fc1.bias
visual.blocks.12.mlp.linear_fc1.bias:visual.blocks.12.mlp.linear_fc1.bias
visual.blocks.12.mlp.linear_fc1.weight
visual.blocks.12.mlp.linear_fc1.weight:visual.blocks.12.mlp.linear_fc1.weight
visual.blocks.12.mlp.linear_fc2.bias
visual.blocks.12.mlp.linear_fc2.bias:visual.blocks.12.mlp.linear_fc2.bias
visual.blocks.12.mlp.linear_fc2.weight
visual.blocks.12.mlp.linear_fc2.weight:visual.blocks.12.mlp.linear_fc2.weight
visual.blocks.12.norm1.bias
visual.blocks.12.norm1.bias:visual.blocks.12.norm1.bias
visual.blocks.12.norm1.weight
visual.blocks.12.norm1.weight:visual.blocks.12.norm1.weight
visual.blocks.12.norm2.bias
visual.blocks.12.norm2.bias:visual.blocks.12.norm2.bias
visual.blocks.12.norm2.weight
visual.blocks.12.norm2.weight:visual.blocks.12.norm2.weight
visual.blocks.13.attn.proj.bias
visual.blocks.13.attn.proj.bias:visual.blocks.13.attn.proj.bias
visual.blocks.13.attn.proj.weight
visual.blocks.13.attn.proj.weight:visual.blocks.13.attn.proj.weight
visual.blocks.13.attn.qkv.bias
visual.blocks.13.attn.qkv.bias:visual.blocks.13.attn.qkv.bias
visual.blocks.13.attn.qkv.weight
visual.blocks.13.attn.qkv.weight:visual.blocks.13.attn.qkv.weight
visual.blocks.13.mlp.linear_fc1.bias
visual.blocks.13.mlp.linear_fc1.bias:visual.blocks.13.mlp.linear_fc1.bias
visual.blocks.13.mlp.linear_fc1.weight
visual.blocks.13.mlp.linear_fc1.weight:visual.blocks.13.mlp.linear_fc1.weight
visual.blocks.13.mlp.linear_fc2.bias
visual.blocks.13.mlp.linear_fc2.bias:visual.blocks.13.mlp.linear_fc2.bias
visual.blocks.13.mlp.linear_fc2.weight
visual.blocks.13.mlp.linear_fc2.weight:visual.blocks.13.mlp.linear_fc2.weight
visual.blocks.13.norm1.bias
visual.blocks.13.norm1.bias:visual.blocks.13.norm1.bias
visual.blocks.13.norm1.weight
visual.blocks.13.norm1.weight:visual.blocks.13.norm1.weight
visual.blocks.13.norm2.bias
visual.blocks.13.norm2.bias:visual.blocks.13.norm2.bias
visual.blocks.13.norm2.weight
visual.blocks.13.norm2.weight:visual.blocks.13.norm2.weight
visual.blocks.14.attn.proj.bias
visual.blocks.14.attn.proj.bias:visual.blocks.14.attn.proj.bias
visual.blocks.14.attn.proj.weight
visual.blocks.14.attn.proj.weight:visual.blocks.14.attn.proj.weight
visual.blocks.14.attn.qkv.bias
visual.blocks.14.attn.qkv.bias:visual.blocks.14.attn.qkv.bias
visual.blocks.14.attn.qkv.weight
visual.blocks.14.attn.qkv.weight:visual.blocks.14.attn.qkv.weight
visual.blocks.14.mlp.linear_fc1.bias
visual.blocks.14.mlp.linear_fc1.bias:visual.blocks.14.mlp.linear_fc1.bias
visual.blocks.14.mlp.linear_fc1.weight
visual.blocks.14.mlp.linear_fc1.weight:visual.blocks.14.mlp.linear_fc1.weight
visual.blocks.14.mlp.linear_fc2.bias
visual.blocks.14.mlp.linear_fc2.bias:visual.blocks.14.mlp.linear_fc2.bias
visual.blocks.14.mlp.linear_fc2.weight
visual.blocks.14.mlp.linear_fc2.weight:visual.blocks.14.mlp.linear_fc2.weight
visual.blocks.14.norm1.bias
visual.blocks.14.norm1.bias:visual.blocks.14.norm1.bias
visual.blocks.14.norm1.weight
visual.blocks.14.norm1.weight:visual.blocks.14.norm1.weight
visual.blocks.14.norm2.bias
visual.blocks.14.norm2.bias:visual.blocks.14.norm2.bias
visual.blocks.14.norm2.weight
visual.blocks.14.norm2.weight:visual.blocks.14.norm2.weight
visual.blocks.15.attn.proj.bias
visual.blocks.15.attn.proj.bias:visual.blocks.15.attn.proj.bias
visual.blocks.15.attn.proj.weight
visual.blocks.15.attn.proj.weight:visual.blocks.15.attn.proj.weight
visual.blocks.15.attn.qkv.bias
visual.blocks.15.attn.qkv.bias:visual.blocks.15.attn.qkv.bias
visual.blocks.15.attn.qkv.weight
visual.blocks.15.attn.qkv.weight:visual.blocks.15.attn.qkv.weight
visual.blocks.15.mlp.linear_fc1.bias
visual.blocks.15.mlp.linear_fc1.bias:visual.blocks.15.mlp.linear_fc1.bias
visual.blocks.15.mlp.linear_fc1.weight
visual.blocks.15.mlp.linear_fc1.weight:visual.blocks.15.mlp.linear_fc1.weight
visual.blocks.15.mlp.linear_fc2.bias
visual.blocks.15.mlp.linear_fc2.bias:visual.blocks.15.mlp.linear_fc2.bias
visual.blocks.15.mlp.linear_fc2.weight
visual.blocks.15.mlp.linear_fc2.weight:visual.blocks.15.mlp.linear_fc2.weight
visual.blocks.15.norm1.bias
visual.blocks.15.norm1.bias:visual.blocks.15.norm1.bias
visual.blocks.15.norm1.weight
visual.blocks.15.norm1.weight:visual.blocks.15.norm1.weight
visual.blocks.15.norm2.bias
visual.blocks.15.norm2.bias:visual.blocks.15.norm2.bias
visual.blocks.15.norm2.weight
visual.blocks.15.norm2.weight:visual.blocks.15.norm2.weight
visual.blocks.16.attn.proj.bias
visual.blocks.16.attn.proj.bias:visual.blocks.16.attn.proj.bias
visual.blocks.16.attn.proj.weight
visual.blocks.16.attn.proj.weight:visual.blocks.16.attn.proj.weight
visual.blocks.16.attn.qkv.bias
visual.blocks.16.attn.qkv.bias:visual.blocks.16.attn.qkv.bias
visual.blocks.16.attn.qkv.weight
visual.blocks.16.attn.qkv.weight:visual.blocks.16.attn.qkv.weight
visual.blocks.16.mlp.linear_fc1.bias
visual.blocks.16.mlp.linear_fc1.bias:visual.blocks.16.mlp.linear_fc1.bias
visual.blocks.16.mlp.linear_fc1.weight
visual.blocks.16.mlp.linear_fc1.weight:visual.blocks.16.mlp.linear_fc1.weight
visual.blocks.16.mlp.linear_fc2.bias
visual.blocks.16.mlp.linear_fc2.bias:visual.blocks.16.mlp.linear_fc2.bias
visual.blocks.16.mlp.linear_fc2.weight
visual.blocks.16.mlp.linear_fc2.weight:visual.blocks.16.mlp.linear_fc2.weight
visual.blocks.16.norm1.bias
visual.blocks.16.norm1.bias:visual.blocks.16.norm1.bias
visual.blocks.16.norm1.weight
visual.blocks.16.norm1.weight:visual.blocks.16.norm1.weight
visual.blocks.16.norm2.bias
visual.blocks.16.norm2.bias:visual.blocks.16.norm2.bias
visual.blocks.16.norm2.weight
visual.blocks.16.norm2.weight:visual.blocks.16.norm2.weight
visual.blocks.17.attn.proj.bias
visual.blocks.17.attn.proj.bias:visual.blocks.17.attn.proj.bias
visual.blocks.17.attn.proj.weight
visual.blocks.17.attn.proj.weight:visual.blocks.17.attn.proj.weight
visual.blocks.17.attn.qkv.bias
visual.blocks.17.attn.qkv.bias:visual.blocks.17.attn.qkv.bias
visual.blocks.17.attn.qkv.weight
visual.blocks.17.attn.qkv.weight:visual.blocks.17.attn.qkv.weight
visual.blocks.17.mlp.linear_fc1.bias
visual.blocks.17.mlp.linear_fc1.bias:visual.blocks.17.mlp.linear_fc1.bias
visual.blocks.17.mlp.linear_fc1.weight
visual.blocks.17.mlp.linear_fc1.weight:visual.blocks.17.mlp.linear_fc1.weight
visual.blocks.17.mlp.linear_fc2.bias
visual.blocks.17.mlp.linear_fc2.bias:visual.blocks.17.mlp.linear_fc2.bias
visual.blocks.17.mlp.linear_fc2.weight
visual.blocks.17.mlp.linear_fc2.weight:visual.blocks.17.mlp.linear_fc2.weight
visual.blocks.17.norm1.bias
visual.blocks.17.norm1.bias:visual.blocks.17.norm1.bias
visual.blocks.17.norm1.weight
visual.blocks.17.norm1.weight:visual.blocks.17.norm1.weight
visual.blocks.17.norm2.bias
visual.blocks.17.norm2.bias:visual.blocks.17.norm2.bias
visual.blocks.17.norm2.weight
visual.blocks.17.norm2.weight:visual.blocks.17.norm2.weight
visual.blocks.18.attn.proj.bias
visual.blocks.18.attn.proj.bias:visual.blocks.18.attn.proj.bias
visual.blocks.18.attn.proj.weight
visual.blocks.18.attn.proj.weight:visual.blocks.18.attn.proj.weight
visual.blocks.18.attn.qkv.bias
visual.blocks.18.attn.qkv.bias:visual.blocks.18.attn.qkv.bias
visual.blocks.18.attn.qkv.weight
visual.blocks.18.attn.qkv.weight:visual.blocks.18.attn.qkv.weight
visual.blocks.18.mlp.linear_fc1.bias
visual.blocks.18.mlp.linear_fc1.bias:visual.blocks.18.mlp.linear_fc1.bias
visual.blocks.18.mlp.linear_fc1.weight
visual.blocks.18.mlp.linear_fc1.weight:visual.blocks.18.mlp.linear_fc1.weight
visual.blocks.18.mlp.linear_fc2.bias
visual.blocks.18.mlp.linear_fc2.bias:visual.blocks.18.mlp.linear_fc2.bias
visual.blocks.18.mlp.linear_fc2.weight
visual.blocks.18.mlp.linear_fc2.weight:visual.blocks.18.mlp.linear_fc2.weight
visual.blocks.18.norm1.bias
visual.blocks.18.norm1.bias:visual.blocks.18.norm1.bias
visual.blocks.18.norm1.weight
visual.blocks.18.norm1.weight:visual.blocks.18.norm1.weight
visual.blocks.18.norm2.bias
visual.blocks.18.norm2.bias:visual.blocks.18.norm2.bias
visual.blocks.18.norm2.weight
visual.blocks.18.norm2.weight:visual.blocks.18.norm2.weight
visual.blocks.19.attn.proj.bias
visual.blocks.19.attn.proj.bias:visual.blocks.19.attn.proj.bias
visual.blocks.19.attn.proj.weight
visual.blocks.19.attn.proj.weight:visual.blocks.19.attn.proj.weight
visual.blocks.19.attn.qkv.bias
visual.blocks.19.attn.qkv.bias:visual.blocks.19.attn.qkv.bias
visual.blocks.19.attn.qkv.weight
visual.blocks.19.attn.qkv.weight:visual.blocks.19.attn.qkv.weight
visual.blocks.19.mlp.linear_fc1.bias
visual.blocks.19.mlp.linear_fc1.bias:visual.blocks.19.mlp.linear_fc1.bias
visual.blocks.19.mlp.linear_fc1.weight
visual.blocks.19.mlp.linear_fc1.weight:visual.blocks.19.mlp.linear_fc1.weight
visual.blocks.19.mlp.linear_fc2.bias
visual.blocks.19.mlp.linear_fc2.bias:visual.blocks.19.mlp.linear_fc2.bias
visual.blocks.19.mlp.linear_fc2.weight
visual.blocks.19.mlp.linear_fc2.weight:visual.blocks.19.mlp.linear_fc2.weight
visual.blocks.19.norm1.bias
visual.blocks.19.norm1.bias:visual.blocks.19.norm1.bias
visual.blocks.19.norm1.weight
visual.blocks.19.norm1.weight:visual.blocks.19.norm1.weight
visual.blocks.19.norm2.bias
visual.blocks.19.norm2.bias:visual.blocks.19.norm2.bias
visual.blocks.19.norm2.weight
visual.blocks.19.norm2.weight:visual.blocks.19.norm2.weight
visual.blocks.2.attn.proj.bias
visual.blocks.2.attn.proj.bias:visual.blocks.2.attn.proj.bias
visual.blocks.2.attn.proj.weight
visual.blocks.2.attn.proj.weight:visual.blocks.2.attn.proj.weight
visual.blocks.2.attn.qkv.bias
visual.blocks.2.attn.qkv.bias:visual.blocks.2.attn.qkv.bias
visual.blocks.2.attn.qkv.weight
visual.blocks.2.attn.qkv.weight:visual.blocks.2.attn.qkv.weight
visual.blocks.2.mlp.linear_fc1.bias
visual.blocks.2.mlp.linear_fc1.bias:visual.blocks.2.mlp.linear_fc1.bias
visual.blocks.2.mlp.linear_fc1.weight
visual.blocks.2.mlp.linear_fc1.weight:visual.blocks.2.mlp.linear_fc1.weight
visual.blocks.2.mlp.linear_fc2.bias
visual.blocks.2.mlp.linear_fc2.bias:visual.blocks.2.mlp.linear_fc2.bias
visual.blocks.2.mlp.linear_fc2.weight
visual.blocks.2.mlp.linear_fc2.weight:visual.blocks.2.mlp.linear_fc2.weight
visual.blocks.2.norm1.bias
visual.blocks.2.norm1.bias:visual.blocks.2.norm1.bias
visual.blocks.2.norm1.weight
visual.blocks.2.norm1.weight:visual.blocks.2.norm1.weight
visual.blocks.2.norm2.bias
visual.blocks.2.norm2.bias:visual.blocks.2.norm2.bias
visual.blocks.2.norm2.weight
visual.blocks.2.norm2.weight:visual.blocks.2.norm2.weight
visual.blocks.20.attn.proj.bias
visual.blocks.20.attn.proj.bias:visual.blocks.20.attn.proj.bias
visual.blocks.20.attn.proj.weight
visual.blocks.20.attn.proj.weight:visual.blocks.20.attn.proj.weight
visual.blocks.20.attn.qkv.bias
visual.blocks.20.attn.qkv.bias:visual.blocks.20.attn.qkv.bias
visual.blocks.20.attn.qkv.weight
visual.blocks.20.attn.qkv.weight:visual.blocks.20.attn.qkv.weight
visual.blocks.20.mlp.linear_fc1.bias
visual.blocks.20.mlp.linear_fc1.bias:visual.blocks.20.mlp.linear_fc1.bias
visual.blocks.20.mlp.linear_fc1.weight
visual.blocks.20.mlp.linear_fc1.weight:visual.blocks.20.mlp.linear_fc1.weight
visual.blocks.20.mlp.linear_fc2.bias
visual.blocks.20.mlp.linear_fc2.bias:visual.blocks.20.mlp.linear_fc2.bias
visual.blocks.20.mlp.linear_fc2.weight
visual.blocks.20.mlp.linear_fc2.weight:visual.blocks.20.mlp.linear_fc2.weight
visual.blocks.20.norm1.bias
visual.blocks.20.norm1.bias:visual.blocks.20.norm1.bias
visual.blocks.20.norm1.weight
visual.blocks.20.norm1.weight:visual.blocks.20.norm1.weight
visual.blocks.20.norm2.bias
visual.blocks.20.norm2.bias:visual.blocks.20.norm2.bias
visual.blocks.20.norm2.weight
visual.blocks.20.norm2.weight:visual.blocks.20.norm2.weight
visual.blocks.21.attn.proj.bias
visual.blocks.21.attn.proj.bias:visual.blocks.21.attn.proj.bias
visual.blocks.21.attn.proj.weight
visual.blocks.21.attn.proj.weight:visual.blocks.21.attn.proj.weight
visual.blocks.21.attn.qkv.bias
visual.blocks.21.attn.qkv.bias:visual.blocks.21.attn.qkv.bias
visual.blocks.21.attn.qkv.weight
visual.blocks.21.attn.qkv.weight:visual.blocks.21.attn.qkv.weight
visual.blocks.21.mlp.linear_fc1.bias
visual.blocks.21.mlp.linear_fc1.bias:visual.blocks.21.mlp.linear_fc1.bias
visual.blocks.21.mlp.linear_fc1.weight
visual.blocks.21.mlp.linear_fc1.weight:visual.blocks.21.mlp.linear_fc1.weight
visual.blocks.21.mlp.linear_fc2.bias
visual.blocks.21.mlp.linear_fc2.bias:visual.blocks.21.mlp.linear_fc2.bias
visual.blocks.21.mlp.linear_fc2.weight
visual.blocks.21.mlp.linear_fc2.weight:visual.blocks.21.mlp.linear_fc2.weight
visual.blocks.21.norm1.bias
visual.blocks.21.norm1.bias:visual.blocks.21.norm1.bias
visual.blocks.21.norm1.weight
visual.blocks.21.norm1.weight:visual.blocks.21.norm1.weight
visual.blocks.21.norm2.bias
visual.blocks.21.norm2.bias:visual.blocks.21.norm2.bias
visual.blocks.21.norm2.weight
visual.blocks.21.norm2.weight:visual.blocks.21.norm2.weight
visual.blocks.22.attn.proj.bias
visual.blocks.22.attn.proj.bias:visual.blocks.22.attn.proj.bias
visual.blocks.22.attn.proj.weight
visual.blocks.22.attn.proj.weight:visual.blocks.22.attn.proj.weight
visual.blocks.22.attn.qkv.bias
visual.blocks.22.attn.qkv.bias:visual.blocks.22.attn.qkv.bias
visual.blocks.22.attn.qkv.weight
visual.blocks.22.attn.qkv.weight:visual.blocks.22.attn.qkv.weight
visual.blocks.22.mlp.linear_fc1.bias
visual.blocks.22.mlp.linear_fc1.bias:visual.blocks.22.mlp.linear_fc1.bias
visual.blocks.22.mlp.linear_fc1.weight
visual.blocks.22.mlp.linear_fc1.weight:visual.blocks.22.mlp.linear_fc1.weight
visual.blocks.22.mlp.linear_fc2.bias
visual.blocks.22.mlp.linear_fc2.bias:visual.blocks.22.mlp.linear_fc2.bias
visual.blocks.22.mlp.linear_fc2.weight
visual.blocks.22.mlp.linear_fc2.weight:visual.blocks.22.mlp.linear_fc2.weight
visual.blocks.22.norm1.bias
visual.blocks.22.norm1.bias:visual.blocks.22.norm1.bias
visual.blocks.22.norm1.weight
visual.blocks.22.norm1.weight:visual.blocks.22.norm1.weight
visual.blocks.22.norm2.bias
visual.blocks.22.norm2.bias:visual.blocks.22.norm2.bias
visual.blocks.22.norm2.weight
visual.blocks.22.norm2.weight:visual.blocks.22.norm2.weight
visual.blocks.23.attn.proj.bias
visual.blocks.23.attn.proj.bias:visual.blocks.23.attn.proj.bias
visual.blocks.23.attn.proj.weight
visual.blocks.23.attn.proj.weight:visual.blocks.23.attn.proj.weight
visual.blocks.23.attn.qkv.bias
visual.blocks.23.attn.qkv.bias:visual.blocks.23.attn.qkv.bias
visual.blocks.23.attn.qkv.weight
visual.blocks.23.attn.qkv.weight:visual.blocks.23.attn.qkv.weight
visual.blocks.23.mlp.linear_fc1.bias
visual.blocks.23.mlp.linear_fc1.bias:visual.blocks.23.mlp.linear_fc1.bias
visual.blocks.23.mlp.linear_fc1.weight
visual.blocks.23.mlp.linear_fc1.weight:visual.blocks.23.mlp.linear_fc1.weight
visual.blocks.23.mlp.linear_fc2.bias
visual.blocks.23.mlp.linear_fc2.bias:visual.blocks.23.mlp.linear_fc2.bias
visual.blocks.23.mlp.linear_fc2.weight
visual.blocks.23.mlp.linear_fc2.weight:visual.blocks.23.mlp.linear_fc2.weight
visual.blocks.23.norm1.bias
visual.blocks.23.norm1.bias:visual.blocks.23.norm1.bias
visual.blocks.23.norm1.weight
visual.blocks.23.norm1.weight:visual.blocks.23.norm1.weight
visual.blocks.23.norm2.bias
visual.blocks.23.norm2.bias:visual.blocks.23.norm2.bias
visual.blocks.23.norm2.weight
visual.blocks.23.norm2.weight:visual.blocks.23.norm2.weight
visual.blocks.3.attn.proj.bias
visual.blocks.3.attn.proj.bias:visual.blocks.3.attn.proj.bias
visual.blocks.3.attn.proj.weight
visual.blocks.3.attn.proj.weight:visual.blocks.3.attn.proj.weight
visual.blocks.3.attn.qkv.bias
visual.blocks.3.attn.qkv.bias:visual.blocks.3.attn.qkv.bias
visual.blocks.3.attn.qkv.weight
visual.blocks.3.attn.qkv.weight:visual.blocks.3.attn.qkv.weight
visual.blocks.3.mlp.linear_fc1.bias
visual.blocks.3.mlp.linear_fc1.bias:visual.blocks.3.mlp.linear_fc1.bias
visual.blocks.3.mlp.linear_fc1.weight
visual.blocks.3.mlp.linear_fc1.weight:visual.blocks.3.mlp.linear_fc1.weight
visual.blocks.3.mlp.linear_fc2.bias
visual.blocks.3.mlp.linear_fc2.bias:visual.blocks.3.mlp.linear_fc2.bias
visual.blocks.3.mlp.linear_fc2.weight
visual.blocks.3.mlp.linear_fc2.weight:visual.blocks.3.mlp.linear_fc2.weight
visual.blocks.3.norm1.bias
visual.blocks.3.norm1.bias:visual.blocks.3.norm1.bias
visual.blocks.3.norm1.weight
visual.blocks.3.norm1.weight:visual.blocks.3.norm1.weight
visual.blocks.3.norm2.bias
visual.blocks.3.norm2.bias:visual.blocks.3.norm2.bias
visual.blocks.3.norm2.weight
visual.blocks.3.norm2.weight:visual.blocks.3.norm2.weight
visual.blocks.4.attn.proj.bias
visual.blocks.4.attn.proj.bias:visual.blocks.4.attn.proj.bias
visual.blocks.4.attn.proj.weight
visual.blocks.4.attn.proj.weight:visual.blocks.4.attn.proj.weight
visual.blocks.4.attn.qkv.bias
visual.blocks.4.attn.qkv.bias:visual.blocks.4.attn.qkv.bias
visual.blocks.4.attn.qkv.weight
visual.blocks.4.attn.qkv.weight:visual.blocks.4.attn.qkv.weight
visual.blocks.4.mlp.linear_fc1.bias
visual.blocks.4.mlp.linear_fc1.bias:visual.blocks.4.mlp.linear_fc1.bias
visual.blocks.4.mlp.linear_fc1.weight
visual.blocks.4.mlp.linear_fc1.weight:visual.blocks.4.mlp.linear_fc1.weight
visual.blocks.4.mlp.linear_fc2.bias
visual.blocks.4.mlp.linear_fc2.bias:visual.blocks.4.mlp.linear_fc2.bias
visual.blocks.4.mlp.linear_fc2.weight
visual.blocks.4.mlp.linear_fc2.weight:visual.blocks.4.mlp.linear_fc2.weight
visual.blocks.4.norm1.bias
visual.blocks.4.norm1.bias:visual.blocks.4.norm1.bias
visual.blocks.4.norm1.weight
visual.blocks.4.norm1.weight:visual.blocks.4.norm1.weight
visual.blocks.4.norm2.bias
visual.blocks.4.norm2.bias:visual.blocks.4.norm2.bias
visual.blocks.4.norm2.weight
visual.blocks.4.norm2.weight:visual.blocks.4.norm2.weight
visual.blocks.5.attn.proj.bias
visual.blocks.5.attn.proj.bias:visual.blocks.5.attn.proj.bias
visual.blocks.5.attn.proj.weight
visual.blocks.5.attn.proj.weight:visual.blocks.5.attn.proj.weight
visual.blocks.5.attn.qkv.bias
visual.blocks.5.attn.qkv.bias:visual.blocks.5.attn.qkv.bias
visual.blocks.5.attn.qkv.weight
visual.blocks.5.attn.qkv.weight:visual.blocks.5.attn.qkv.weight
visual.blocks.5.mlp.linear_fc1.bias
visual.blocks.5.mlp.linear_fc1.bias:visual.blocks.5.mlp.linear_fc1.bias
visual.blocks.5.mlp.linear_fc1.weight
visual.blocks.5.mlp.linear_fc1.weight:visual.blocks.5.mlp.linear_fc1.weight
visual.blocks.5.mlp.linear_fc2.bias
visual.blocks.5.mlp.linear_fc2.bias:visual.blocks.5.mlp.linear_fc2.bias
visual.blocks.5.mlp.linear_fc2.weight
visual.blocks.5.mlp.linear_fc2.weight:visual.blocks.5.mlp.linear_fc2.weight
visual.blocks.5.norm1.bias
visual.blocks.5.norm1.bias:visual.blocks.5.norm1.bias
visual.blocks.5.norm1.weight
visual.blocks.5.norm1.weight:visual.blocks.5.norm1.weight
visual.blocks.5.norm2.bias
visual.blocks.5.norm2.bias:visual.blocks.5.norm2.bias
visual.blocks.5.norm2.weight
visual.blocks.5.norm2.weight:visual.blocks.5.norm2.weight
visual.blocks.6.attn.proj.bias
visual.blocks.6.attn.proj.bias:visual.blocks.6.attn.proj.bias
visual.blocks.6.attn.proj.weight
visual.blocks.6.attn.proj.weight:visual.blocks.6.attn.proj.weight
visual.blocks.6.attn.qkv.bias
visual.blocks.6.attn.qkv.bias:visual.blocks.6.attn.qkv.bias
visual.blocks.6.attn.qkv.weight
visual.blocks.6.attn.qkv.weight:visual.blocks.6.attn.qkv.weight
visual.blocks.6.mlp.linear_fc1.bias
visual.blocks.6.mlp.linear_fc1.bias:visual.blocks.6.mlp.linear_fc1.bias
visual.blocks.6.mlp.linear_fc1.weight
visual.blocks.6.mlp.linear_fc1.weight:visual.blocks.6.mlp.linear_fc1.weight
visual.blocks.6.mlp.linear_fc2.bias
visual.blocks.6.mlp.linear_fc2.bias:visual.blocks.6.mlp.linear_fc2.bias
visual.blocks.6.mlp.linear_fc2.weight
visual.blocks.6.mlp.linear_fc2.weight:visual.blocks.6.mlp.linear_fc2.weight
visual.blocks.6.norm1.bias
visual.blocks.6.norm1.bias:visual.blocks.6.norm1.bias
visual.blocks.6.norm1.weight
visual.blocks.6.norm1.weight:visual.blocks.6.norm1.weight
visual.blocks.6.norm2.bias
visual.blocks.6.norm2.bias:visual.blocks.6.norm2.bias
visual.blocks.6.norm2.weight
visual.blocks.6.norm2.weight:visual.blocks.6.norm2.weight
visual.blocks.7.attn.proj.bias
visual.blocks.7.attn.proj.bias:visual.blocks.7.attn.proj.bias
visual.blocks.7.attn.proj.weight
visual.blocks.7.attn.proj.weight:visual.blocks.7.attn.proj.weight
visual.blocks.7.attn.qkv.bias
visual.blocks.7.attn.qkv.bias:visual.blocks.7.attn.qkv.bias
visual.blocks.7.attn.qkv.weight
visual.blocks.7.attn.qkv.weight:visual.blocks.7.attn.qkv.weight
visual.blocks.7.mlp.linear_fc1.bias
visual.blocks.7.mlp.linear_fc1.bias:visual.blocks.7.mlp.linear_fc1.bias
visual.blocks.7.mlp.linear_fc1.weight
visual.blocks.7.mlp.linear_fc1.weight:visual.blocks.7.mlp.linear_fc1.weight
visual.blocks.7.mlp.linear_fc2.bias
visual.blocks.7.mlp.linear_fc2.bias:visual.blocks.7.mlp.linear_fc2.bias
visual.blocks.7.mlp.linear_fc2.weight
visual.blocks.7.mlp.linear_fc2.weight:visual.blocks.7.mlp.linear_fc2.weight
visual.blocks.7.norm1.bias
visual.blocks.7.norm1.bias:visual.blocks.7.norm1.bias
visual.blocks.7.norm1.weight
visual.blocks.7.norm1.weight:visual.blocks.7.norm1.weight
visual.blocks.7.norm2.bias
visual.blocks.7.norm2.bias:visual.blocks.7.norm2.bias
visual.blocks.7.norm2.weight
visual.blocks.7.norm2.weight:visual.blocks.7.norm2.weight
visual.blocks.8.attn.proj.bias
visual.blocks.8.attn.proj.bias:visual.blocks.8.attn.proj.bias
visual.blocks.8.attn.proj.weight
visual.blocks.8.attn.proj.weight:visual.blocks.8.attn.proj.weight
visual.blocks.8.attn.qkv.bias
visual.blocks.8.attn.qkv.bias:visual.blocks.8.attn.qkv.bias
visual.blocks.8.attn.qkv.weight
visual.blocks.8.attn.qkv.weight:visual.blocks.8.attn.qkv.weight
visual.blocks.8.mlp.linear_fc1.bias
visual.blocks.8.mlp.linear_fc1.bias:visual.blocks.8.mlp.linear_fc1.bias
visual.blocks.8.mlp.linear_fc1.weight
visual.blocks.8.mlp.linear_fc1.weight:visual.blocks.8.mlp.linear_fc1.weight
visual.blocks.8.mlp.linear_fc2.bias
visual.blocks.8.mlp.linear_fc2.bias:visual.blocks.8.mlp.linear_fc2.bias
visual.blocks.8.mlp.linear_fc2.weight
visual.blocks.8.mlp.linear_fc2.weight:visual.blocks.8.mlp.linear_fc2.weight
visual.blocks.8.norm1.bias
visual.blocks.8.norm1.bias:visual.blocks.8.norm1.bias
visual.blocks.8.norm1.weight
visual.blocks.8.norm1.weight:visual.blocks.8.norm1.weight
visual.blocks.8.norm2.bias
visual.blocks.8.norm2.bias:visual.blocks.8.norm2.bias
visual.blocks.8.norm2.weight
visual.blocks.8.norm2.weight:visual.blocks.8.norm2.weight
visual.blocks.9.attn.proj.bias
visual.blocks.9.attn.proj.bias:visual.blocks.9.attn.proj.bias
visual.blocks.9.attn.proj.weight
visual.blocks.9.attn.proj.weight:visual.blocks.9.attn.proj.weight
visual.blocks.9.attn.qkv.bias
visual.blocks.9.attn.qkv.bias:visual.blocks.9.attn.qkv.bias
visual.blocks.9.attn.qkv.weight
visual.blocks.9.attn.qkv.weight:visual.blocks.9.attn.qkv.weight
visual.blocks.9.mlp.linear_fc1.bias
visual.blocks.9.mlp.linear_fc1.bias:visual.blocks.9.mlp.linear_fc1.bias
visual.blocks.9.mlp.linear_fc1.weight
visual.blocks.9.mlp.linear_fc1.weight:visual.blocks.9.mlp.linear_fc1.weight
visual.blocks.9.mlp.linear_fc2.bias
visual.blocks.9.mlp.linear_fc2.bias:visual.blocks.9.mlp.linear_fc2.bias
visual.blocks.9.mlp.linear_fc2.weight
visual.blocks.9.mlp.linear_fc2.weight:visual.blocks.9.mlp.linear_fc2.weight
visual.blocks.9.norm1.bias
visual.blocks.9.norm1.bias:visual.blocks.9.norm1.bias
visual.blocks.9.norm1.weight
visual.blocks.9.norm1.weight:visual.blocks.9.norm1.weight
visual.blocks.9.norm2.bias
visual.blocks.9.norm2.bias:visual.blocks.9.norm2.bias
visual.blocks.9.norm2.weight
visual.blocks.9.norm2.weight:visual.blocks.9.norm2.weight
visual.deepstack_merger_list.0.linear_fc1.bias
visual.deepstack_merger_list.0.linear_fc1.bias:visual.deepstack_merger_list.0.linear_fc1.bias
visual.deepstack_merger_list.0.linear_fc1.weight
visual.deepstack_merger_list.0.linear_fc1.weight:visual.deepstack_merger_list.0.linear_fc1.weight
visual.deepstack_merger_list.0.linear_fc2.bias
visual.deepstack_merger_list.0.linear_fc2.bias:visual.deepstack_merger_list.0.linear_fc2.bias
visual.deepstack_merger_list.0.linear_fc2.weight
visual.deepstack_merger_list.0.linear_fc2.weight:visual.deepstack_merger_list.0.linear_fc2.weight
visual.deepstack_merger_list.0.norm.bias
visual.deepstack_merger_list.0.norm.bias:visual.deepstack_merger_list.0.norm.bias
visual.deepstack_merger_list.0.norm.weight
visual.deepstack_merger_list.0.norm.weight:visual.deepstack_merger_list.0.norm.weight
visual.deepstack_merger_list.1.linear_fc1.bias
visual.deepstack_merger_list.1.linear_fc1.bias:visual.deepstack_merger_list.1.linear_fc1.bias
visual.deepstack_merger_list.1.linear_fc1.weight
visual.deepstack_merger_list.1.linear_fc1.weight:visual.deepstack_merger_list.1.linear_fc1.weight
visual.deepstack_merger_list.1.linear_fc2.bias
visual.deepstack_merger_list.1.linear_fc2.bias:visual.deepstack_merger_list.1.linear_fc2.bias
visual.deepstack_merger_list.1.linear_fc2.weight
visual.deepstack_merger_list.1.linear_fc2.weight:visual.deepstack_merger_list.1.linear_fc2.weight
visual.deepstack_merger_list.1.norm.bias
visual.deepstack_merger_list.1.norm.bias:visual.deepstack_merger_list.1.norm.bias
visual.deepstack_merger_list.1.norm.weight
visual.deepstack_merger_list.1.norm.weight:visual.deepstack_merger_list.1.norm.weight
visual.deepstack_merger_list.2.linear_fc1.bias
visual.deepstack_merger_list.2.linear_fc1.bias:visual.deepstack_merger_list.2.linear_fc1.bias
visual.deepstack_merger_list.2.linear_fc1.weight
visual.deepstack_merger_list.2.linear_fc1.weight:visual.deepstack_merger_list.2.linear_fc1.weight
visual.deepstack_merger_list.2.linear_fc2.bias
visual.deepstack_merger_list.2.linear_fc2.bias:visual.deepstack_merger_list.2.linear_fc2.bias
visual.deepstack_merger_list.2.linear_fc2.weight
visual.deepstack_merger_list.2.linear_fc2.weight:visual.deepstack_merger_list.2.linear_fc2.weight
visual.deepstack_merger_list.2.norm.bias
visual.deepstack_merger_list.2.norm.bias:visual.deepstack_merger_list.2.norm.bias
visual.deepstack_merger_list.2.norm.weight
visual.deepstack_merger_list.2.norm.weight:visual.deepstack_merger_list.2.norm.weight
visual.merger.linear_fc1.bias
visual.merger.linear_fc1.bias:visual.merger.linear_fc1.bias
visual.merger.linear_fc1.weight
visual.merger.linear_fc1.weight:visual.merger.linear_fc1.weight
visual.merger.linear_fc2.bias
visual.merger.linear_fc2.bias:visual.merger.linear_fc2.bias
visual.merger.linear_fc2.weight
visual.merger.linear_fc2.weight:visual.merger.linear_fc2.weight
visual.merger.norm.bias
visual.merger.norm.bias:visual.merger.norm.bias
visual.merger.norm.weight
visual.merger.norm.weight:visual.merger.norm.weight
visual.patch_embed.proj.bias
visual.patch_embed.proj.bias:visual.patch_embed.proj.bias
visual.patch_embed.proj.weight
visual.patch_embed.proj.weight:visual.patch_embed.proj.weight
visual.pos_embed.weight
visual.pos_embed.weight:visual.pos_embed.weight