初始化项目，由ModelHub XC社区提供模型

Model: BAAI/OPI-Galactica-6.7B
Source: Original Platform

.gitattributes

@@ -0,0 +1,49 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+OPI_demo.gif filter=lfs diff=lfs merge=lfs -text
+model_comparison/Task3.png filter=lfs diff=lfs merge=lfs -text
+model_comparison/Task5.png filter=lfs diff=lfs merge=lfs -text
+model_comparison/Task6.png filter=lfs diff=lfs merge=lfs -text
+model_comparison/Task7.png filter=lfs diff=lfs merge=lfs -text
+model_compare/task2_fold_type.png filter=lfs diff=lfs merge=lfs -text
+model_compare/task3_subcell_loc.png filter=lfs diff=lfs merge=lfs -text
+model_compare/task5_GO.png filter=lfs diff=lfs merge=lfs -text
+model_compare/task6_function.png filter=lfs diff=lfs merge=lfs -text
+model_compare/task7_gsymbol2tissue.png filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
+demo_figures/OPI_demo.gif filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,228 @@
+---
+license: apache-2.0
+datasets:
+- BAAI/OPI
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- Life Science
+- AI4Science
+- Biology
+- Protein
+- LLM
+- Instruction
+base_model: facebook/galactica-6.7b
+---
+![OPI_logo](demo_figures/OPI_logo.png)
+
+# Github: 
+  https://github.com/baaihealth/opi
+# Paper: 
+  [OPI: An Open Instruction Dataset for Adapting Large Language Models to Protein-Related Tasks](https://neurips.cc/virtual/2024/105921) has been accepted by [NeurIPS 2024 Workshop: Foundation Models for Science: Progress, Opportunities, and Challenges](https://neurips.cc/virtual/2024/workshop/84714).
+
+# Model Card of OPI-Galactica-6.7B
+OPI-Galactica-6.7B was fine-tuned from the Galactica-6.7B model using the complete OPI training set (i.e.,[OPI_full_1.61M_train.json](https://huggingface.co/datasets/BAAI/OPI/blob/main/OPI_DATA/OPI_full_1.61M_train.json)).
+For more details of training and testing, please visit [https://github.com/baaihealth/opi](https://github.com/baaihealth/opi).
+
+![Overview](demo_figures/OPI_experiment_outline.png)
+
+# Evaluation of OPI-Galactica-6.7B model on 9 tasks 
+Each testing result is derived from the Galactica-6.7B model that has been fine-tuned using [OPI_full_1.61M.json](https://huggingface.co/datasets/BAAI/OPI/blob/main/OPI_DATA/OPI_full_1.61M_train.json) and subsequently evaluated on the respective testing set for each specific task.
+
+<table border="1" style="text-align:center; border-collapse:collapse; width: 100%;">
+  <thead>
+    <tr>
+      <th style="text-align:center;">Task Type</th>
+      <th style="text-align:center;">Task Name</th>
+      <th style="text-align:center;">Testing file</th>
+      <th style="text-align:center;">Accuracy</th>
+      <th style="text-align:center;">Precision</th>
+      <th style="text-align:center;">Recall</th>
+      <th style="text-align:center;">F1</th>
+      <th style="text-align:center;">Rouge-L</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td rowspan="6">Sequence Understanding</td>
+      <td rowspan="2">EC Number Prediction (split100)</td>
+      <td>CLEAN_EC_number_new_test</td>
+      <td>-</td>
+      <td>0.2700</td>
+      <td>0.2663</td>
+      <td>0.2596</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td>CLEAN_EC_number_price_test</td>
+      <td>-</td>
+      <td>0.0268</td>
+      <td>0.0268</td>
+      <td>0.0268</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td rowspan="3">Fold Type Prediction</td>
+      <td>fold_type_test_Fold_Holdout</td>
+      <td>0.0808</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td>fold_type_test_Superfamily_Holdout</td>
+      <td>0.1348</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td>fold_type_test_Family_Holdout</td>
+      <td>0.4854</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td>Subcellular Localization Prediction</td>
+      <td>subcell_loc_test</td>
+      <td>0.7771</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td rowspan="9">Annotation Prediction</td>
+      <td>Function Keywords Prediction</td>
+      <td>CASPSimilarSeq_keywords_test</td>
+      <td>-</td>
+      <td>0.8120</td>
+      <td>0.7360</td>
+      <td>0.7643</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td>Function Keywords Prediction</td>
+      <td>IDFilterSeq_keywords_test</td>
+      <td>-</td>
+      <td>0.8377</td>
+      <td>0.8019</td>
+      <td>0.8070</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td>Function Keywords Prediction</td>
+      <td>UniProtSeq_keywords_test</td>
+      <td>-</td>
+      <td>0.8596</td>
+      <td>0.8196</td>
+      <td>0.8276</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td>Gene Ontology (GO) Terms Prediction</td>
+      <td>CASPSimilarSeq_go_terms_test</td>
+      <td>-</td>
+      <td>0.7613</td>
+      <td>0.7492</td>
+      <td>0.7476</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td>Gene Ontology (GO) Terms Prediction</td>
+      <td>IDFilterSeq_go_terms_test</td>
+      <td>-</td>
+      <td>0.7404</td>
+      <td>0.7274</td>
+      <td>0.7207</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td>Gene Ontology (GO) Terms Prediction</td>
+      <td>UniProtSeq_go_terms_test</td>
+      <td>-</td>
+      <td>0.7638</td>
+      <td>0.7373</td>
+      <td>0.7358</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td>Function Description Prediction</td>
+      <td>CASPSimilarSeq_function_test</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>0.7430</td>
+    </tr>
+    <tr>
+      <td>Function Description Prediction</td>
+      <td>IDFilterSeq_function_test</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>0.7014</td>
+    </tr>
+    <tr>
+      <td>Function Description Prediction</td>
+      <td>UniProtSeq_function_test</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>-</td>
+      <td>0.7133</td>
+    </tr>
+    <tr>
+      <td rowspan="3">Knowledge Mining</td>
+      <td>Tissue Location Prediction from Gene Symbol</td>
+      <td>gene_symbol_to_tissue_test</td>
+      <td>-</td>
+      <td>0.3917</td>
+      <td>0.9077</td>
+      <td>0.5303</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td>Cancer Prediction from Gene Symbol</td>
+      <td>gene_symbol_to_cancer_test</td>
+      <td>-</td>
+      <td>0.3555</td>
+      <td>0.3189</td>
+      <td>0.3229</td>
+      <td>-</td>
+    </tr>
+    <tr>
+      <td>Cancer Prediction from Gene Name</td>
+      <td>gene_name_to_cancer_test</td>
+      <td>-</td>
+      <td>0.2728</td>
+      <td>0.2554</td>
+      <td>0.2533</td>
+      <td>-</td>
+    </tr>
+  </tbody>
+</table>
+
+# Prediction comparison with SOTA mdoels
+
+![model_compare](model_compare/task1_EC_number.png)
+![model_compare](model_compare/task2_fold_type.png)
+![model_compare](model_compare/task3_subcell_loc.png)
+![model_compare](model_compare/task4_keywords.png)
+![model_compare](model_compare/task5_GO.png)
+![model_compare](model_compare/task6_function.png)
+![model_compare](model_compare/task7_gsymbol2tissue.png)
+![model_compare](model_compare/task8_gsymbol2cancer.png)
+![model_compare](model_compare/task9_gname2cancer.png)
+
+
+# Demo
+We use the [FastChat](https://github.com/lm-sys/FastChat) platform to visually demonstrate the ability of OPI-Galactica-6.7B model on various evaluation tasks.
+
+![OPI Demo](./demo_figures/OPI_demo.gif)

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "Galactica/Galactica-6.7B",
+  "_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": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 50000,
+  "word_embed_proj_dim": 4096
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

demo_figures/OPI_demo.gif

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fc93bf77a9534652de153adab1802b81c64ece0d107f21614bc93d0ea986845
+size 12177117

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": "4.41.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:013c4e5a554615a3adb99f22d36df4336e8df07f89cf1c0a4537a83050eed446
+size 4991055896

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a42f8640c0c9342eb5ab1ff70cfa04718d14519f80c9e58414d905c3bcf734d
+size 4967389800

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a71687ebcfc6020bfe46529c225643d33153308fa65260d7454d68373ea87f8c
+size 3356335456

model.safetensors.index.json

@@ -0,0 +1,523 @@
+{
+  "metadata": {
+    "total_size": 13314719744
+  },
+  "weight_map": {
+    "model.decoder.embed_positions.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.11.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.11.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.11.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.11.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.11.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.11.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.12.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.12.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.13.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.14.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.15.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.16.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.17.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.18.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.19.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.2.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.20.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.20.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.21.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.22.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.23.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.23.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.23.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.23.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.23.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.23.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.23.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.23.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "model.decoder.layers.24.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.24.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.25.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.26.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.27.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.28.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.29.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.3.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.30.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.30.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.31.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "model.decoder.layers.4.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "model.decoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors"
+  }
+}

model_compare/task2_fold_type.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:193b26b37a41a24b76f299bf9a43bf8844e2f5ff531fa26c6f1dba4b747d4e42
+size 1010702

model_compare/task3_subcell_loc.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef07b3e2e048ad1428e6c597a363762fcb38f211c3de2b22edac13d37adc45ac
+size 1744696

model_compare/task5_GO.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ed0be683af9a094854fe50b88c576b20a95235789901e767f9db73347455396
+size 1418606

model_compare/task6_function.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc84d5e01ea43834a3f4252bb7365e629c5e81adb4b2abacce54822b71b9dd8b
+size 1291815

model_compare/task7_gsymbol2tissue.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02cdb5908a5f16b60e9c7a07c92a2f3dc4f946d3700876826efbfa846923b4dd
+size 1034061

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,196 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c460c595918ce5a624a2d42df379d8529b14f35a23f2bc3850a6486052fecbfd
+size 6904