Upload 8 files

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "/mnt/bn/trung-nas/ppo_paper_final_new/_models_outputs_sft/gsm8k_python_sdp_galactica/global_step_308_epoch_2/",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 16384,
+  "hidden_size": 4096,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "learned_embeddings": true,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 1,
+  "scale_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.1",
+  "use_cache": true,
+  "vocab_size": 50000,
+  "word_embed_proj_dim": 4096
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.34.1"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c415459544341349b4bafcd4661f276f22c015e8e1d6272f38ff15265b27d233
+size 9958533335

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dda345f25daad330fc77976b046d285efc91cd994adf1b86e163654fdf5df3e
+size 3765973616

pytorch_model.bin.index.json

@@ -0,0 +1,526 @@
+{
+  "metadata": {
+    "total_size": 13724327938
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00002-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-00001-of-00002.bin",
+    "model.decoder.layers.22.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.final_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.22.final_layer_norm.weight": "pytorch_model-00001-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-00001-of-00002.bin",
+    "model.decoder.layers.23.fc1.weight": "pytorch_model-00001-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-00001-of-00002.bin",
+    "model.decoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.23.self_attn_layer_norm.bias": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.23.self_attn_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.decoder.layers.24.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.24.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.24.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.24.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.24.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.24.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.24.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.24.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.24.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.24.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.24.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.24.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.24.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.25.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.25.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.25.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.25.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.25.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.25.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.25.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.25.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.25.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.25.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.25.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.25.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.25.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.26.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.26.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.26.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.26.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.26.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.26.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.26.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.26.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.26.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.26.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.26.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.26.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.26.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.27.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.27.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.27.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.27.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.27.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.27.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.27.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.27.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.27.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.27.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.27.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.27.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.27.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.28.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.28.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.28.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.28.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.28.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.28.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.28.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.28.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.28.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.28.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.28.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.28.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.28.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.29.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.29.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.29.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.29.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.29.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.29.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.29.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.29.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.29.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.29.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.29.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.29.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.29.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.30.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.30.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.30.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.30.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.30.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.30.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.30.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.30.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.30.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.30.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.30.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.30.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.30.self_attn_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.31.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.31.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.31.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.31.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.31.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.31.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.31.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.31.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.31.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.31.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.31.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.31.self_attn_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.decoder.layers.31.self_attn_layer_norm.weight": "pytorch_model-00002-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",
+    "v_head.summary.bias": "pytorch_model-00002-of-00002.bin",
+    "v_head.summary.weight": "pytorch_model-00002-of-00002.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,4 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>"
+}

tokenizer_config.json

@@ -0,0 +1,193 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[START_REF]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[END_REF]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "[IMAGE]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<fragments>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "</fragments>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<work>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "</work>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "[START_SUP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "[END_SUP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "[START_SUB]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "[END_SUB]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "[START_DNA]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "[END_DNA]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "[START_AMINO]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "[END_AMINO]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "19": {
+      "content": "[START_SMILES]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "20": {
+      "content": "[END_SMILES]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "21": {
+      "content": "[START_I_SMILES]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "22": {
+      "content": "[END_I_SMILES]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}