RobCzikkel/DoctorGPT

README.md

@@ -0,0 +1,72 @@
+---
+license: mit
+base_model: microsoft/BioGPT-Large
+tags:
+- generated_from_trainer
+model-index:
+- name: bioGPT
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# bioGPT
+
+This model is a fine-tuned version of [microsoft/BioGPT-Large](https://huggingface.co/microsoft/BioGPT-Large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1114
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0005
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 0.25  | 51   | 1.2418          |
+| 1.3267        | 0.5   | 102  | 1.1900          |
+| 1.3267        | 0.75  | 153  | 1.1348          |
+| 1.1237        | 0.99  | 204  | 1.0887          |
+| 1.1237        | 1.24  | 255  | 1.1018          |
+| 0.7527        | 1.49  | 306  | 1.0770          |
+| 0.7527        | 1.74  | 357  | 1.0464          |
+| 0.7281        | 1.99  | 408  | 1.0233          |
+| 0.7281        | 2.24  | 459  | 1.1212          |
+| 0.4262        | 2.49  | 510  | 1.1177          |
+| 0.4262        | 2.73  | 561  | 1.1125          |
+| 0.4124        | 2.98  | 612  | 1.1114          |
+
+
+### Framework versions
+
+- Transformers 4.36.0.dev0
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "microsoft/BioGPT-Large",
+  "activation_dropout": 0.0,
+  "architectures": [
+    "BioGptForCausalLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1600,
+  "initializer_range": 0.02,
+  "intermediate_size": 6400,
+  "layer_norm_eps": 1e-12,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "biogpt",
+  "num_attention_heads": 25,
+  "num_hidden_layers": 48,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0.dev0",
+  "use_cache": true,
+  "vocab_size": 57717
+}

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": "4.36.0.dev0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54f92216522fc38305c12fc209a57bcb1398fca10569ea760ccf7c285003c09c
+size 4973212608

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faf26193008f3ef153cacf8e6bdd281d81647e8dcb0d68ac66e53015c6aac144
+size 1311627992

model.safetensors.index.json

@@ -0,0 +1,779 @@
+{
+  "metadata": {
+    "total_size": 6284755200
+  },
+  "weight_map": {
+    "biogpt.embed_positions.weight": "model-00001-of-00002.safetensors",
+    "biogpt.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layer_norm.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.0.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.0.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.0.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.0.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.1.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.1.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.1.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.1.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.10.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.10.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.10.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.10.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.11.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.11.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.11.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.11.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.12.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.12.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.12.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.12.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.13.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.13.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.13.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.13.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.14.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.14.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.14.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.14.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.15.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.15.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.15.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.15.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.16.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.16.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.16.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.16.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.17.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.17.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.17.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.17.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.18.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.18.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.18.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.18.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.19.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.19.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.19.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.19.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.2.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.2.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.2.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.2.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.20.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.20.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.20.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.20.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.20.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.20.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.21.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.21.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.21.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.21.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.21.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.21.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.21.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.21.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.22.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.22.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.22.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.22.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.22.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.22.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.22.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.22.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.23.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.23.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.23.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.23.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.23.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.23.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.23.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.23.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.24.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.24.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.24.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.24.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.24.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.24.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.24.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.24.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.25.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.25.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.25.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.25.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.25.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.25.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.25.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.25.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.26.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.26.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.26.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.26.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.26.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.26.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.26.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.26.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.27.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.27.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.27.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.27.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.27.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.27.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.27.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.27.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.27.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.27.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.28.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.28.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.28.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.28.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.28.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.28.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.28.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.28.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.28.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.28.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.29.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.29.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.29.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.29.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.29.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.29.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.29.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.29.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.29.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.29.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.3.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.3.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.3.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.3.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.30.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.30.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.30.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.30.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.30.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.30.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.30.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.30.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.30.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.30.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.30.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.31.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.31.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.31.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.31.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.31.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.31.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.31.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.31.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.31.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.31.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.31.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.32.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.32.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.32.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.32.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.32.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.32.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.32.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.32.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.32.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.32.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.32.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.32.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.32.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.33.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.33.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.33.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.33.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.33.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.33.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.33.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.33.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.33.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.33.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.33.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.33.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.33.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.34.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.34.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.34.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.34.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.34.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.34.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.34.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.34.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.34.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.34.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.34.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.34.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.34.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.35.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.35.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.35.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.35.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.35.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.35.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.35.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.35.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.35.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.35.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.35.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.35.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.35.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.36.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.36.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.36.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.36.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.36.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.36.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.36.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.36.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.36.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.36.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.36.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.36.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.36.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.36.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.36.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.36.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.37.fc1.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.37.fc1.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.37.fc2.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.37.fc2.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.37.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.37.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.37.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.37.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.37.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.37.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.37.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.37.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.37.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.37.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.37.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.37.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.38.fc1.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.38.fc1.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.38.fc2.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.38.fc2.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.38.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.38.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.38.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.38.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.38.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.38.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.38.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.38.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.38.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.38.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.38.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.38.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.39.fc1.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.39.fc1.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.39.fc2.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.39.fc2.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.39.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.39.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.39.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.39.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.39.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.39.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.39.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.39.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.39.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.39.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.39.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.39.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.4.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.4.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.4.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.4.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.40.fc1.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.40.fc1.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.40.fc2.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.40.fc2.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.40.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.40.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.40.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.40.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.40.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.40.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.40.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.40.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.40.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.40.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.40.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.40.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.41.fc1.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.41.fc1.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.41.fc2.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.41.fc2.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.41.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.41.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.41.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.41.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.41.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.41.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.41.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.41.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.41.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.41.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.41.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.41.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.42.fc1.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.42.fc1.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.42.fc2.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.42.fc2.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.42.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.42.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.42.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.42.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.42.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.42.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.42.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.42.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.42.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.42.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.42.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.42.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.43.fc1.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.43.fc1.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.43.fc2.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.43.fc2.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.43.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.43.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.43.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.43.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.43.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.43.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.43.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.43.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.43.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.43.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.43.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.43.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.44.fc1.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.44.fc1.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.44.fc2.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.44.fc2.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.44.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.44.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.44.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.44.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.44.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.44.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.44.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.44.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.44.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.44.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.44.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.44.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.45.fc1.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.45.fc1.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.45.fc2.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.45.fc2.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.45.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.45.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.45.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.45.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.45.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.45.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.45.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.45.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.45.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.45.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.45.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.45.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.46.fc1.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.46.fc1.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.46.fc2.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.46.fc2.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.46.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.46.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.46.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.46.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.46.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.46.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.46.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.46.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.46.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.46.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.46.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.46.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.47.fc1.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.47.fc1.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.47.fc2.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.47.fc2.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.47.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.47.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.47.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.47.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.47.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.47.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.47.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.47.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.47.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.47.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.47.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "biogpt.layers.47.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "biogpt.layers.5.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.5.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.5.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.5.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.6.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.6.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.6.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.6.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.7.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.7.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.7.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.7.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.8.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.8.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.8.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.8.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.9.fc1.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.9.fc1.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.9.fc2.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.9.fc2.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "biogpt.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "biogpt.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors"
+  }
+}

runs/Nov24_21-12-11_87f33704e632/events.out.tfevents.1700860339.87f33704e632.744.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a139af5106613741933bc9c25c82632d32c944610a58b4bbfba1f2545e50150c
+size 4184

runs/Nov24_21-16-03_87f33704e632/events.out.tfevents.1700860578.87f33704e632.4122.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e3a4603165954e4d101cfb2b293f655c0f335e1e148510def532da50b34a42c
+size 4973

runs/Nov24_23-16-13_87f33704e632/events.out.tfevents.1700867787.87f33704e632.35427.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10f9b36e5ae656cf188726306c8c750b96dff40128059f1caee800577f0fefd5
+size 8839

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BioGptTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d495149e84a000bbf952efd319d25afd9808a22d0f9eb1785cdaf8db4d7d8a1a
+size 4600