I
This commit is contained in:
smthemex
@@ -1 +1,33 @@
|
||||
|
||||
{
|
||||
"architectures": [
|
||||
"UMT5EncoderModel"
|
||||
],
|
||||
"classifier_dropout": 0.0,
|
||||
"d_ff": 10240,
|
||||
"d_kv": 64,
|
||||
"d_model": 4096,
|
||||
"decoder_start_token_id": 0,
|
||||
"dense_act_fn": "gelu_new",
|
||||
"dropout_rate": 0.1,
|
||||
"eos_token_id": 1,
|
||||
"feed_forward_proj": "gated-gelu",
|
||||
"initializer_factor": 1.0,
|
||||
"is_encoder_decoder": true,
|
||||
"is_gated_act": true,
|
||||
"layer_norm_epsilon": 1e-06,
|
||||
"model_type": "umt5",
|
||||
"num_decoder_layers": 24,
|
||||
"num_heads": 64,
|
||||
"num_layers": 24,
|
||||
"output_past": true,
|
||||
"pad_token_id": 0,
|
||||
"relative_attention_max_distance": 128,
|
||||
"relative_attention_num_buckets": 32,
|
||||
"scalable_attention": true,
|
||||
"tie_word_embeddings": false,
|
||||
"tokenizer_class": "T5Tokenizer",
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.51.3",
|
||||
"use_cache": true,
|
||||
"vocab_size": 256384
|
||||
}
|
||||
|
||||
@@ -0,0 +1,249 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 22723641344
|
||||
},
|
||||
"weight_map": {
|
||||
"encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00005.safetensors",
|
||||
"encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00005.safetensors",
|
||||
"encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00005.safetensors",
|
||||
"encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00005.safetensors",
|
||||
"encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00005.safetensors",
|
||||
"encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00005.safetensors",
|
||||
"encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00005.safetensors",
|
||||
"encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00005.safetensors",
|
||||
"encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00005.safetensors",
|
||||
"encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00005.safetensors",
|
||||
"encoder.block.1.layer.0.SelfAttention.k.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.1.layer.0.SelfAttention.o.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.1.layer.0.SelfAttention.q.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.1.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.1.layer.0.SelfAttention.v.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.1.layer.0.layer_norm.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.1.layer.1.layer_norm.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.10.layer.0.SelfAttention.k.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.10.layer.0.SelfAttention.o.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.10.layer.0.SelfAttention.q.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.10.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.10.layer.0.SelfAttention.v.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.10.layer.0.layer_norm.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.10.layer.1.layer_norm.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.11.layer.0.SelfAttention.k.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.11.layer.0.SelfAttention.o.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.11.layer.0.SelfAttention.q.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.11.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.11.layer.0.SelfAttention.v.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.11.layer.0.layer_norm.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.11.layer.1.layer_norm.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.12.layer.0.SelfAttention.k.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.12.layer.0.SelfAttention.o.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.12.layer.0.SelfAttention.q.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.12.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.12.layer.0.SelfAttention.v.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.12.layer.0.layer_norm.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.12.layer.1.layer_norm.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.13.layer.0.SelfAttention.k.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.13.layer.0.SelfAttention.o.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.13.layer.0.SelfAttention.q.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.13.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.13.layer.0.SelfAttention.v.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.13.layer.0.layer_norm.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.13.layer.1.layer_norm.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.14.layer.0.SelfAttention.k.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.14.layer.0.SelfAttention.o.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.14.layer.0.SelfAttention.q.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.14.layer.0.SelfAttention.relative_attention_bias.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.14.layer.0.SelfAttention.v.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.14.layer.0.layer_norm.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.14.layer.1.layer_norm.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.15.layer.0.SelfAttention.k.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.15.layer.0.SelfAttention.o.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.15.layer.0.SelfAttention.q.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.15.layer.0.SelfAttention.relative_attention_bias.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.15.layer.0.SelfAttention.v.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.15.layer.0.layer_norm.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.15.layer.1.layer_norm.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.16.layer.0.SelfAttention.k.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.16.layer.0.SelfAttention.o.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.16.layer.0.SelfAttention.q.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.16.layer.0.SelfAttention.relative_attention_bias.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.16.layer.0.SelfAttention.v.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.16.layer.0.layer_norm.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.16.layer.1.layer_norm.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.17.layer.0.SelfAttention.k.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.17.layer.0.SelfAttention.o.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.17.layer.0.SelfAttention.q.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.17.layer.0.SelfAttention.relative_attention_bias.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.17.layer.0.SelfAttention.v.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.17.layer.0.layer_norm.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.17.layer.1.layer_norm.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.18.layer.0.SelfAttention.k.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.18.layer.0.SelfAttention.o.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.18.layer.0.SelfAttention.q.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.18.layer.0.SelfAttention.relative_attention_bias.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.18.layer.0.SelfAttention.v.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.18.layer.0.layer_norm.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.18.layer.1.layer_norm.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.19.layer.0.SelfAttention.k.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.19.layer.0.SelfAttention.o.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.19.layer.0.SelfAttention.q.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.19.layer.0.SelfAttention.relative_attention_bias.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.19.layer.0.SelfAttention.v.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.19.layer.0.layer_norm.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.19.layer.1.layer_norm.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.2.layer.0.SelfAttention.k.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.2.layer.0.SelfAttention.o.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.2.layer.0.SelfAttention.q.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.2.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.2.layer.0.SelfAttention.v.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.2.layer.0.layer_norm.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.2.layer.1.layer_norm.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.20.layer.0.SelfAttention.k.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.20.layer.0.SelfAttention.o.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.20.layer.0.SelfAttention.q.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.20.layer.0.SelfAttention.relative_attention_bias.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.20.layer.0.SelfAttention.v.weight": "model-00004-of-00005.safetensors",
|
||||
"encoder.block.20.layer.0.layer_norm.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.20.layer.1.layer_norm.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.21.layer.0.SelfAttention.k.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.21.layer.0.SelfAttention.o.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.21.layer.0.SelfAttention.q.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.21.layer.0.SelfAttention.relative_attention_bias.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.21.layer.0.SelfAttention.v.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.21.layer.0.layer_norm.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.21.layer.1.layer_norm.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.22.layer.0.SelfAttention.k.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.22.layer.0.SelfAttention.o.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.22.layer.0.SelfAttention.q.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.22.layer.0.SelfAttention.relative_attention_bias.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.22.layer.0.SelfAttention.v.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.22.layer.0.layer_norm.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.22.layer.1.layer_norm.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.23.layer.0.SelfAttention.k.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.23.layer.0.SelfAttention.o.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.23.layer.0.SelfAttention.q.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.23.layer.0.SelfAttention.relative_attention_bias.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.23.layer.0.SelfAttention.v.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.23.layer.0.layer_norm.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.23.layer.1.layer_norm.weight": "model-00005-of-00005.safetensors",
|
||||
"encoder.block.3.layer.0.SelfAttention.k.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.3.layer.0.SelfAttention.o.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.3.layer.0.SelfAttention.q.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.3.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.3.layer.0.SelfAttention.v.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.3.layer.0.layer_norm.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.3.layer.1.layer_norm.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.4.layer.0.SelfAttention.k.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.4.layer.0.SelfAttention.o.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.4.layer.0.SelfAttention.q.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.4.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.4.layer.0.SelfAttention.v.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.4.layer.0.layer_norm.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.4.layer.1.layer_norm.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.5.layer.0.SelfAttention.k.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.5.layer.0.SelfAttention.o.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.5.layer.0.SelfAttention.q.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.5.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.5.layer.0.SelfAttention.v.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.5.layer.0.layer_norm.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.5.layer.1.layer_norm.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.6.layer.0.SelfAttention.k.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.6.layer.0.SelfAttention.o.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.6.layer.0.SelfAttention.q.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.6.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.6.layer.0.SelfAttention.v.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.6.layer.0.layer_norm.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.6.layer.1.layer_norm.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.7.layer.0.SelfAttention.k.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.7.layer.0.SelfAttention.o.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.7.layer.0.SelfAttention.q.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.7.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.7.layer.0.SelfAttention.v.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.7.layer.0.layer_norm.weight": "model-00002-of-00005.safetensors",
|
||||
"encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.7.layer.1.layer_norm.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.8.layer.0.SelfAttention.k.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.8.layer.0.SelfAttention.o.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.8.layer.0.SelfAttention.q.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.8.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.8.layer.0.SelfAttention.v.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.8.layer.0.layer_norm.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.8.layer.1.layer_norm.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.9.layer.0.SelfAttention.k.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.9.layer.0.SelfAttention.o.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.9.layer.0.SelfAttention.q.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.9.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.9.layer.0.SelfAttention.v.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.9.layer.0.layer_norm.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.block.9.layer.1.layer_norm.weight": "model-00003-of-00005.safetensors",
|
||||
"encoder.final_layer_norm.weight": "model-00005-of-00005.safetensors",
|
||||
"shared.weight": "model-00001-of-00005.safetensors"
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user