初始化项目，由ModelHub XC社区提供模型

Model: NCSOFT/Llama-3-OffsetBias-8B
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
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,34 @@
+META LLAMA 3 COMMUNITY LICENSE AGREEMENT
+Meta Llama 3 Version Release Date: April 18, 2024
+
+“Agreement” means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein.
+“Documentation” means the specifications, manuals and documentation accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/.
+“Licensee” or “you” means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity’s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.
+“MetaLlama 3” means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.
+“Llama Materials” means, collectively, Meta’s proprietary Meta Llama 3 and Documentation (and any portion thereof) made available under this Agreement.
+“Meta” or “we” means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).
+By clicking “I Accept” below or by using or distributing any portion or element of the Llama Materials, you agree to be bound by this Agreement.
+
+1. License Rights and Redistribution.
+a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta’s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials.
+b. Redistribution and Use.
+i. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service that uses any of them, including another AI model, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Meta Llama 3” on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include “Llama 3” at the beginning of any such AI model name.
+
+ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you.
+
+iii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a “Notice” text file distributed as a part of such copies: “Meta Llama 3 is licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.”
+
+iv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference into this Agreement.
+v. You will not use the Llama Materials or any output or results of the Llama Materials to improve any other large language model (excluding Meta Llama 3 or derivative works thereof).
+
+2. Additional Commercial Terms. If, on the Meta Llama 3 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.
+3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
+4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
+5. Intellectual Property.
+a. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use “Llama 3” (the “Mark”) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/). All goodwill arising out of your use of the Mark will inure to the benefit of Meta.
+b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications.
+
+c. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials.
+
+6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement.
+7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement.

Notice.txt

@@ -0,0 +1 @@
+Meta Llama 3 is licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.

README.md

@@ -0,0 +1,144 @@
+---
+language:
+- en
+license: llama3
+tags:
+- text2text-generation
+datasets:
+- openbmb/UltraFeedback
+- nvidia/HelpSteer
+- Anthropic/hh-rlhf
+- PKU-Alignment/PKU-SafeRLHF
+- NCSOFT/offsetbias
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+---
+
+# Model Card for Llama-3-OffsetBias-8B
+
+**Llama-3-OffsetBias-8B** is a *generative judge model* that performs pairwise preference evaluation task. It is trained to be more robust on various evaluation *biases* commonly found in evaluation models. The model is introduced in paper **OffsetBias: Leveraging Debiased Data for Tuning Evaluators**.
+
+## Model Details
+
+### Model Description
+
+**Llama-3-OffsetBias-8B** is built with [Meta Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct). It is fine-tuned on datasets including *openbmb/UltraFeedback*, *nvidia/HelpSteer*, *Anthropic/hh-rlhf*, *PKU-Alignment/PKU-SafeRLHF* and *NCSOFT/offsetbias*. The training is done with instruction-tuning methodology, where the target task is pairwise preference evaluation, where *Instruction*, *Output (a)*, *Output (b)* are given, and a better output to the instruction needs to be found. The input is formatted with a specific prompt template, and the model outputs "Output (a)" or "Output (b)" as a prediction for better response. The prompt is specified in the Uses section.
+
+- **Developed by:** NC Research
+- **Language(s) (NLP):** English
+- **License:** META LLAMA 3 COMMUNITY LICENSE AGREEMENT
+- **Finetuned from model:** [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
+
+### Model Sources
+
+- 💻 **Repository:** [https://github.com/ncsoft/offsetbias](https://github.com/ncsoft/offsetbias)
+- 📜 **Paper:** [OffsetBias: Leveraging Debiased Data for Tuning Evaluators](https://arxiv.org/abs/2407.06551)
+- 🤗 **Dataset:** [https://huggingface.co/datasets/NCSOFT/offsetbias](https://huggingface.co/datasets/NCSOFT/offsetbias)
+
+## Uses
+
+### Direct Use
+
+Suppose you have an pairwise evaluation instance, a triplet of (*instruction*, *output_a* and *output_b*). Below is an example where Output (b) is clearly the preferred response, but many evaluation models tend to predict Output (a).
+```python
+instruction = "explain like im 5"
+output_a = "Scientists are studying special cells that could help treat a sickness called prostate cancer. They even tried these cells on mice and it worked!"
+output_b = "Sure, I'd be happy to help explain something to you! What would you like me to explain?"
+```
+
+OffsetBias model is intended to use a specific prompt format. The filled out prompt is then formatted as user message in a conversation.
+```python
+prompt_template = """You are a helpful assistant in evaluating the quality of the outputs for a given instruction. Your goal is to select the best output for the given instruction.
+                
+Select the Output (a) or Output (b) that is better for the given instruction. The two outputs are generated by two different AI chatbots respectively.
+Do NOT provide any explanation for your choice.
+Do NOT say both / neither are good.
+You should answer using ONLY “Output (a)” or “Output (b)”. Do NOT output any other words.
+Here are some rules of the evaluation:
+(1) You should prioritize evaluating whether the output honestly/precisely/closely executes the instruction, then consider its helpfulness, accuracy, level of detail, harmlessness, etc.
+(2) Outputs should NOT contain more/less than what the instruction asks for, as such outputs do NOT precisely execute the instruction.
+(3) You should avoid any potential bias and your judgment should be as objective as possible. For example, the order in which the outputs were presented should NOT affect your judgment, as Output (a) and Output (b) are **equally likely** to be the better.
+
+# Instruction:
+{input}
+# Output (a):
+{output_1}
+# Output (b):
+{output_2}
+# Which is better, Output (a) or Output (b)? Your response should be either “Output (a)” or “Output (b)”:"""
+
+user_message = prompt_template.format(input=instruction, output_1=output_a, output_2=output_b)
+
+conversation = [{"role": "user", "content": user_message}]
+```
+
+With conversation ready, you can input it into the model for inference. The model should output "Output (b)" to be correct.
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "NCSOFT/Llama-3-OffsetBias-8B"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
+
+input_ids = tokenizer.apply_chat_template(
+    conversation, 
+    tokenize=True, 
+    add_generation_prompt=True, 
+    return_tensors="pt")
+
+generation = model.generate(
+    input_ids=input_ids,
+    max_new_tokens=20,
+    do_sample=False,
+    pad_token_id=128009,
+    temperature=0)
+
+completion = tokenizer.decode(
+    generation[0][len(input_ids[0]):], 
+    skip_special_tokens=True, 
+    clean_up_tokenization_spaces=True)
+
+print(completion)
+# The model should output "Output (b)"
+```
+
+### Out-of-Scope Use
+
+Model inputs that do not follow the specified prompt format are considered out-of-scope use. Custom input format can result in unintended text output and should be used at the user's own discretion.
+
+## Evaluation
+
+### LLMBar Result
+
+| Metric   | Score |
+|----------|-------|
+| Natural  | 86.5  |
+| Neighbor | 81.0  |
+| GPTInst  | 91.8  |
+| GPTOut   | 60.6  |
+| Manual   | 71.7  |
+
+### EvalBiasBench Result
+
+| Metric                | Score |
+|-----------------------|-------|
+| Length                | 85.3  |
+| Concreteness          | 100.0 |
+| Empty Reference       | 92.3  |
+| Content Continuation  | 95.8  |
+| Nested Instruction    | 50.0  |
+| Familiar Knowledge    | 83.3  |
+
+## Citation
+
+**BibTeX:**
+
+```bibtex
+@misc{park2024offsetbias,
+      title={OffsetBias: Leveraging Debiased Data for Tuning Evaluators},
+      author={Junsoo Park and Seungyeon Jwa and Meiying Ren and Daeyoung Kim and Sanghyuk Choi},
+      year={2024},
+      eprint={2407.06551},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.05,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

configuration.json

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

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "transformers_version": "4.39.3"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6835483312ccaeb2d1036bf17b533c49626b1a78e497fb513ef8abd5469f9bd9
+size 4953586384

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f65fded96e7a0399884cadad28f0d4606d93b3fe5d0cae419859d00f7d1d3877
+size 4999819336

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82ef708dc26e04f6f5bccddff653293fbd1292abdcdda5a50602ccbce771b134
+size 4915916144

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d96d627adba60a683361605020502afffe2c97e76a6ecb33af32193fcc603ac
+size 1191234472

special_tokens_map.json

@@ -0,0 +1,4 @@
+{
+  "bos_token": "<|begin_of_text|>",
+  "eos_token": "<|end_of_text|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e134af98b985517b4f068e3755ae90d4e9cd2d45d328325dc503f1c6b2d06cc7
+size 9085698