jellyconsumer/new_model_falcon_large

README.md

@@ -0,0 +1,55 @@
+---
+license: apache-2.0
+base_model: vilsonrodrigues/falcon-7b-instruct-sharded
+tags:
+- generated_from_trainer
+model-index:
+- name: new_model_falcon_large
+  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. -->
+
+# new_model_falcon_large
+
+This model is a fine-tuned version of [vilsonrodrigues/falcon-7b-instruct-sharded](https://huggingface.co/vilsonrodrigues/falcon-7b-instruct-sharded) on an unknown dataset.
+
+## 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: 0.0002
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_ratio: 0.03
+- training_steps: 1000
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.32.1
+- Pytorch 2.0.1+cu117
+- Datasets 2.12.0
+- Tokenizers 0.13.2

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "vilsonrodrigues/falcon-7b-instruct-sharded",
+  "alibi": false,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "FalconForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "vilsonrodrigues/falcon-7b-instruct-sharded--configuration_falcon.FalconConfig",
+    "AutoModel": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconModel",
+    "AutoModelForCausalLM": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconForCausalLM",
+    "AutoModelForQuestionAnswering": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconForQuestionAnswering",
+    "AutoModelForSequenceClassification": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconForSequenceClassification",
+    "AutoModelForTokenClassification": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconForTokenClassification"
+  },
+  "bias": false,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4544,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "falcon",
+  "multi_query": true,
+  "new_decoder_architecture": false,
+  "num_attention_heads": 71,
+  "num_hidden_layers": 32,
+  "num_kv_heads": 71,
+  "parallel_attn": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.1",
+  "use_cache": false,
+  "vocab_size": 65024
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "transformers_version": "4.32.1"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c0485cb92e628697ba86bb3bb0939e1c22c0f0e62dc9193dc430ccd983cb6f3
+size 9962579523

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97c0d8221f47eeadaddc727d129b998ea1e1ec96963cb1c722159c69371a11aa
+size 9939389791

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2923be316140365b4b64d70d0a7ef5c0c291d32ed15744cc3f22fa442042f92
+size 7784983641

pytorch_model.bin.index.json

@@ -0,0 +1,203 @@
+{
+  "metadata": {
+    "total_size": 27686882816
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.10.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.11.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.11.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.2.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.20.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.22.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "transformer.h.23.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.23.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.28.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.28.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.29.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.29.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.3.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.30.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.30.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.31.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.31.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.h.4.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "transformer.ln_f.bias": "pytorch_model-00003-of-00003.bin",
+    "transformer.ln_f.weight": "pytorch_model-00003-of-00003.bin",
+    "transformer.word_embeddings.weight": "pytorch_model-00001-of-00003.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "add_prefix_space": false,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:241aec731f97bbcc6e23153507421428a483871e0e842756774b33de68a38246
+size 4091