CondViT-B16-txt / model.safetensors.index.json
Slep's picture
Upload CondViTForEmbedding
fa2f5fd verified
{
"metadata": {
"total_size": 5311558660
},
"weight_map": {
"condvit.c_pos_embedding": "model-00001-of-00002.safetensors",
"condvit.class_embedding": "model-00001-of-00002.safetensors",
"condvit.conv1.weight": "model-00001-of-00002.safetensors",
"condvit.ln_post.bias": "model-00001-of-00002.safetensors",
"condvit.ln_post.weight": "model-00001-of-00002.safetensors",
"condvit.ln_pre.bias": "model-00001-of-00002.safetensors",
"condvit.ln_pre.weight": "model-00001-of-00002.safetensors",
"condvit.logit_scale": "model-00001-of-00002.safetensors",
"condvit.positional_embedding": "model-00001-of-00002.safetensors",
"condvit.proj.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.0.attn.in_proj_bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.0.attn.in_proj_weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.0.attn.out_proj.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.0.attn.out_proj.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.0.ln_1.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.0.ln_1.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.0.ln_2.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.0.ln_2.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.1.attn.in_proj_bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.1.attn.in_proj_weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.1.attn.out_proj.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.1.attn.out_proj.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.1.ln_1.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.1.ln_1.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.1.ln_2.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.1.ln_2.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.10.attn.in_proj_bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.10.attn.in_proj_weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.10.attn.out_proj.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.10.attn.out_proj.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.10.ln_1.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.10.ln_1.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.10.ln_2.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.10.ln_2.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.11.attn.in_proj_bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.11.attn.in_proj_weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.11.attn.out_proj.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.11.attn.out_proj.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.11.ln_1.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.11.ln_1.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.11.ln_2.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.11.ln_2.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.2.attn.in_proj_bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.2.attn.in_proj_weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.2.attn.out_proj.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.2.attn.out_proj.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.2.ln_1.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.2.ln_1.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.2.ln_2.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.2.ln_2.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.3.attn.in_proj_bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.3.attn.in_proj_weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.3.attn.out_proj.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.3.attn.out_proj.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.3.ln_1.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.3.ln_1.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.3.ln_2.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.3.ln_2.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.4.attn.in_proj_bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.4.attn.in_proj_weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.4.attn.out_proj.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.4.attn.out_proj.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.4.ln_1.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.4.ln_1.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.4.ln_2.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.4.ln_2.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.5.attn.in_proj_bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.5.attn.in_proj_weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.5.attn.out_proj.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.5.attn.out_proj.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.5.ln_1.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.5.ln_1.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.5.ln_2.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.5.ln_2.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.6.attn.in_proj_bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.6.attn.in_proj_weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.6.attn.out_proj.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.6.attn.out_proj.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.6.ln_1.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.6.ln_1.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.6.ln_2.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.6.ln_2.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.7.attn.in_proj_bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.7.attn.in_proj_weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.7.attn.out_proj.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.7.attn.out_proj.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.7.ln_1.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.7.ln_1.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.7.ln_2.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.7.ln_2.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.8.attn.in_proj_bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.8.attn.in_proj_weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.8.attn.out_proj.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.8.attn.out_proj.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.8.ln_1.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.8.ln_1.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.8.ln_2.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.8.ln_2.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.9.attn.in_proj_bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.9.attn.in_proj_weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.9.attn.out_proj.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.9.attn.out_proj.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.9.ln_1.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.9.ln_1.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.9.ln_2.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.9.ln_2.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
"condvit.transformer.resblocks.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.0.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.1.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.10.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.11.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.12.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.13.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.14.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.15.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.15.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.15.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.15.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.16.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.16.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.16.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.16.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.16.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.16.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.16.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.17.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.17.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.17.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.17.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.17.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.17.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.17.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.18.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.18.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.18.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.18.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.18.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.18.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.18.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.19.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.19.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.19.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.19.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.19.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.19.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.19.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.2.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.20.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.20.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.20.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.20.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.20.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.20.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.20.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.21.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.21.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.21.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.21.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.21.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.21.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.21.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.22.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.22.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.22.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.22.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.22.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.22.layer.1.DenseReluDense.wi.weight": "model-00002-of-00002.safetensors",
"lm.0.auto_model.encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"lm.0.auto_model.encoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"lm.0.auto_model.encoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"lm.0.auto_model.encoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"lm.0.auto_model.encoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"lm.0.auto_model.encoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"lm.0.auto_model.encoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"lm.0.auto_model.encoder.block.23.layer.1.DenseReluDense.wi.weight": "model-00002-of-00002.safetensors",
"lm.0.auto_model.encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"lm.0.auto_model.encoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"lm.0.auto_model.encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.3.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.4.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.5.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.6.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.7.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.8.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.9.layer.1.DenseReluDense.wi.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"lm.0.auto_model.encoder.final_layer_norm.weight": "model-00002-of-00002.safetensors",
"lm.0.auto_model.shared.weight": "model-00001-of-00002.safetensors",
"lm.2.linear.weight": "model-00002-of-00002.safetensors"
}
}