Upload OPTForCausalLM

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "/data/yuxian/MiniLLM_dir/results/opt/train/minillm/1.3B-init-13B-sft",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 8192,
+  "hidden_size": 2048,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 2048
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.42.0.dev0"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e58d5af2f92535fb67c449d8dfaf33591d7531159a905086586a18c90400fccb
+size 4994592214

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aecd4bc25000e598b4374d8fb65c14b33f8a80bd6809d4ce43caa2814d65ed05
+size 268573906

pytorch_model.bin.index.json

@@ -0,0 +1,396 @@
+{
+  "metadata": {
+    "total_size": 5263032320
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.embed_positions.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.0.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.1.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.10.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.11.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.12.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.13.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.14.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.15.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.16.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.17.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.18.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.19.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.2.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.20.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.21.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.22.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.22.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.22.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.23.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.23.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.23.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.23.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.23.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.23.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.23.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.23.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.3.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.3.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.4.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.5.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.6.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.7.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.8.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.9.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}