commit from qyj

README.md

@@ -1,3 +1,48 @@
 ---
-license: apache-2.0
+license: llama2
+datasets:
+- ACE05
+- conll2003
+- conll2012_ontonotesv5
+- rams
+- tacred
+- fewrel
+- MAVEN
+language:
+- en
+metrics:
+- f1
+pipeline_tag: text-generation
+tags:
+- text-generation-inference
+- Information Extraction
+- IE
+- Named Entity Recogniton
+- Event Extraction
+- Relation Extraction
+- LLaMA
 ---
+
+# Model Card for ADELIE-DPO
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+<p align="justify">
+We introduce <b>ADELIE</b> (<b>A</b>ligning large language mo<b>DEL</b>s on <b>I</b>nformation <b>E</b>xtraction), an aligned LLM that effectively solves various IE tasks, including closed IE, open IE, and on-demand IE. We first collect and construct a high-quality alignment corpus <font face="Verdana">IEInstruct</font> for IE. Then we train ADELIE<sub>SFT</sub> using instruction tuning on <font face="Verdana">IEInstruct</font>. We further train ADELIE<sub>SFT</sub> with direct preference optimization (DPO) objective, resulting in ADELIE<sub>DPO</sub>. Extensive experiments on various held-out IE datasets demonstrate that our models (ADELIE<sub>SFT</sub> and ADELIE<sub>DPO</sub>) achieve state-of-the-art (SoTA) performance among open-source models. We further explore the general capabilities of ADELIE, and experimental results reveal that their general capabilities do not exhibit a noticeable decline.
+
+- 📖 Paper: [ADELIE: Aligning Large Language Models on Information Extraction](https://arxiv.org/abs/2405.05008)
+</p>
+
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** Yunjia Qi, Hao Peng, Xiaozhi Wang, Bin Xu, Lei Hou, Juanzi Li
+- **Model type:** Text Generation
+- **Language(s) (NLP):** English
+- **License:** LLaMA2 License for the base model. 
+- **Finetuned from model [optional]:** LLaMA2-7B
+

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/data1/ph/open-instruct/output/llama_v2_7B/full/rate_0.2_plus_2",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.36.2"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4835f97b994be52e71282e4106f7000f385eeaffff34749f8c81a4ab16f7209
+size 4939016818

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fec8ff8cd23e750be376c7ddd12b713a4d257b0e6228cbcb5fc046b5a3e434cf
+size 4947415002

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf09a0491b58be3c716231db1398548cc8a1edcb67b1331defab518d60b8822d
+size 3590513913

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.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "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
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}