Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,6 @@
-*.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
+OpenBioLLM-Llama3-70B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+OpenBioLLM-Llama3-70B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+OpenBioLLM-Llama3-70B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+OpenBioLLM-Llama3-70B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+OpenBioLLM-Llama3-70B-Q6_K.gguf-part-a filter=lfs diff=lfs merge=lfs -text
+OpenBioLLM-Llama3-70B-Q6_K.gguf-part-b filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,117 @@
+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.
+
+“Meta Llama 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.

OpenBioLLM-Llama3-70B-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e835921631f2493bdb86f9c0cca5a6514c79cf955d96029b7fe0484cfc07b195
+size 26375108096

OpenBioLLM-Llama3-70B-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcad924e18213963d0666a7f57b51e3ea8468f2a165284eaf248380288f841af
+size 37140592128

OpenBioLLM-Llama3-70B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96a4b835e27a96fcf4f5dff84aee63a7a5c0d59dc65aa4474209751911ee4dfe
+size 42520393216

OpenBioLLM-Llama3-70B-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05b270ca54ae7fb823f7d2283c7a14b8ab0aaf12d74934aa922884acb4591ae8
+size 49949816320

OpenBioLLM-Llama3-70B-Q6_K.gguf-part-a

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e4c5aeb10e7382eb605282ebf455d55dde91fba20e52b2edce46c58ad9cbf1a
+size 28944071424

OpenBioLLM-Llama3-70B-Q6_K.gguf-part-b

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96b10b17f43494f4db69d755c6776377eb9a30e953662d66636232daaa01a5b5
+size 28944071424

README.md

@@ -0,0 +1,366 @@
+---
+base_model: meta-llama/Meta-Llama-3-70B-Instruct
+tags:
+- llama-3
+- llama
+- Mixtral
+- instruct
+- finetune
+- chatml
+- DPO
+- RLHF
+- gpt4
+- distillation
+model-index:
+- name: OpenBioLLM-70B
+  results: []
+license: llama3
+language:
+- en
+widget:
+- example_title: OpenBioLLM-70B 
+  messages:
+  - role: system
+    content: >-
+      You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience.
+  - role: user
+    content: How long does it take for newborn jaundice to go away?
+  output:
+    text: >-
+      Newborn jaundice, also known as neonatal jaundice, is a common condition in newborns where the yellowing of the skin and eyes occurs due to an elevated level of bilirubin in the blood. Bilirubin is a yellow pigment that forms when red blood cells break down. In most cases, newborn jaundice resolves on its own without any specific treatment.
+
+      The duration of newborn jaundice can vary depending on several factors such as the underlying cause, gestational age at birth, and individual variations in bilirubin metabolism. Here are some general guidelines:
+
+      1. Physiological jaundice: This is the most common type of newborn jaundice and usually appears within 24-72 hours after birth. It tends to peak between the second and fifth day of life and gradually improves over the next week or two. By the time the baby is one week old, the jaundice should have mostly resolved.
+      2. Breast milk jaundice: This type of jaundice occurs in breastfed babies and may appear later than physiological jaundice, typically between the fifth and fourteenth day of life. It tends to persist for a longer duration but usually resolves within six weeks after birth.
+      3. Pathological jaundice: This type of jaundice is less common and occurs due to an underlying medical condition that affects bilirubin metabolism or liver function. The duration of pathological jaundice depends on the specific cause and may require treatment.
+
+      It's important for parents to monitor their newborn's jaundice closely and seek medical advice if the jaundice progresses rapidly, becomes severe, or is accompanied by other symptoms such as poor feeding, lethargy, or excessive sleepiness. In these cases, further evaluation and management may be necessary.
+      Remember that each baby is unique, and the timing of jaundice resolution can vary. If you have concerns about your newborn's jaundice, it's always best to consult with a healthcare professional for personalized advice and guidance.
+---
+
+
+<div align="center">
+<img width="260px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/BrQCb95lmEIFz79QAmoNA.png"></div>
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/fJIOPJnY6Ff6fUiSIuMEt.png)
+
+
+
+
+<div align="center">
+  
+  <h1>Advancing Open-source Large Language Models in Medical Domain</h1>
+</div>
+
+<p align="center" style="margin-top: 0px;">
+  <a href="https://colab.research.google.com/drive/1F5oV20InEYeAJGmBwYF9NM_QhLmjBkKJ?usp=sharing">
+    <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="OpenChat Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/>
+    <span class="link-text" style=" margin-right: 5px;">Online Demo</span>
+  </a> |
+  <a href="https://github.com/openlifescience-ai">
+    <img src="https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png" alt="GitHub Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/>
+    <span class="link-text" style=" margin-right: 5px;">GitHub</span>
+  </a> |
+  <a href="#">
+    <img src="https://github.com/alpayariyak/openchat/blob/master/assets/arxiv-logomark-small-square-border.png?raw=true" alt="ArXiv Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/>
+    <span class="link-text" style="margin-right: 5px;">Paper</span>
+  </a> |
+  <a href="https://discord.gg/A5Fjf5zC69">
+    <img src="https://cloud.githubusercontent.com/assets/6291467/26705903/96c2d66e-477c-11e7-9f4e-f3c0efe96c9a.png" alt="Discord Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/>
+    <span class="link-text">Discord</span>
+  </a>
+</p>
+
+![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/KGmRE5w2sepNtwsEu8t7K.jpeg)
+
+Introducing OpenBioLLM-70B: A State-of-the-Art Open Source Biomedical Large Language Model
+
+
+OpenBioLLM-70B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks.
+
+🏥 **Biomedical Specialization**: OpenBioLLM-70B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency.
+
+🎓 **Superior Performance**: With 70 billion parameters, OpenBioLLM-70B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-4,  Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 on biomedical benchmarks.
+
+🧠 **Advanced Training Techniques**: OpenBioLLM-70B builds upon the powerful foundations of the **Meta-Llama-3-70B-Instruct** and [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct) models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include:
+
+<div align="center">
+<img width="1200px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/oPchsJsEpQoGcGXVbh7YS.png">
+</div>
+
+
+- **Policy Optimization**: [Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)](https://arxiv.org/abs/2305.18290)
+- **Fine-tuning dataset**: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated)
+
+This combination of cutting-edge techniques enables OpenBioLLM-70B to align with key capabilities and preferences for biomedical applications.
+
+⚙️ **Release Details**:
+
+- **Model Size**: 70 billion parameters
+- **Quantization**: Optimized quantized versions available [Here](https://huggingface.co/aaditya/OpenBioLLM-70B-GGUF)
+- **Language(s) (NLP):** en
+- **Developed By**: [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) from Saama AI Labs 
+- **License:** Meta-Llama License 
+- **Fine-tuned from models:** [Meta-Llama-3-70B-Instruct](meta-llama/Meta-Llama-3-70B-Instruct)
+- **Resources for more information:**
+    - Paper: Coming soon
+
+The model can be fine-tuned for more specialized tasks and datasets as needed.
+
+OpenBioLLM-70B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences.
+
+We are excited to share OpenBioLLM-70B with researchers and developers around the world.
+
+
+### Use with transformers
+
+**Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.**
+
+See the snippet below for usage with Transformers:
+
+```python
+import transformers
+import torch
+
+model_id = "aaditya/OpenBioLLM-Llama3-70B"
+
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model_id,
+    model_kwargs={"torch_dtype": torch.bfloat16},
+    device="auto",
+)
+
+messages = [
+    {"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. Your name is OpenBioLLM, and you were developed by Saama AI Labs. who's willing to help answer the user's query with explanation. In your explanation, leverage your deep medical expertise such as relevant anatomical structures, physiological processes, diagnostic criteria, treatment guidelines, or other pertinent medical concepts. Use precise medical terminology while still aiming to make the explanation clear and accessible to a general audience."},
+    {"role": "user", "content": "How can i split a 3mg or 4mg waefin pill so i can get a 2.5mg pill?"},
+]
+
+prompt = pipeline.tokenizer.apply_chat_template(
+		messages, 
+		tokenize=False, 
+		add_generation_prompt=True
+)
+
+terminators = [
+    pipeline.tokenizer.eos_token_id,
+    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
+
+outputs = pipeline(
+    prompt,
+    max_new_tokens=256,
+    eos_token_id=terminators,
+    do_sample=True,
+    temperature=0.0,
+    top_p=0.9,
+)
+print(outputs[0]["generated_text"][len(prompt):])
+```
+
+## **Training procedure**
+
+### **Training hyperparameters**
+
+<details>
+  <summary>Click to see details</summary>
+
+- learning_rate: 0.0002
+- lr_scheduler: cosine
+- train_batch_size: 12
+- eval_batch_size: 8
+- GPU: H100 80GB SXM5
+- num_devices: 8
+- optimizer: adamw_bnb_8bit
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 4
+</details>
+
+  
+### **Peft hyperparameters**
+
+<details>
+  <summary>Click to see details</summary>
+
+- adapter: qlora
+- lora_r: 128
+- lora_alpha: 256
+- lora_dropout: 0.05
+- lora_target_linear: true
+  
+-lora_target_modules:
+  - q_proj
+  - v_proj
+  - k_proj
+  - o_proj
+  - gate_proj
+  - down_proj
+  - up_proj
+</details>
+
+
+
+### **Training results**
+
+### **Framework versions**
+
+- Transformers 4.39.3
+- Pytorch 2.1.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.1
+- Axolotl
+- Lm harness for evaluation
+
+
+# Benchmark Results
+
+🔥 OpenBioLLM-70B demonstrates superior performance compared to larger models, such as GPT-4,  Gemini, Meditron-70B, Med-PaLM-1 & Med-PaLM-2 across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 86.06%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge.
+
+🚨 The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy.
+
+|                    | Clinical KG | Medical Genetics | Anatomy | Pro Medicine | College Biology | College Medicine | MedQA 4 opts | PubMedQA | MedMCQA | Avg   |
+|--------------------|-------------|------------------|---------|--------------|-----------------|------------------|--------------|----------|---------|-------|
+| **OpenBioLLM-70B** | **92.93**       | **93.197**           | **83.904**  | 93.75       | 93.827          | **85.749**           | 78.162       | 78.97    | **74.014**  | **86.05588** |
+| Med-PaLM-2 (5-shot)            | 88.3        | 90               | 77.8    | **95.2**         | 94.4            | 80.9             | **79.7**         | **79.2**     | 71.3    | 84.08 |
+| **GPT-4**              | 86.04       | 91               | 80      | 93.01        | **95.14**           | 76.88            | 78.87        | 75.2     | 69.52   | 82.85 |
+| Med-PaLM-1 (Flan-PaLM, 5-shot) | 80.4        | 75               | 63.7    | 83.8         | 88.9            | 76.3             | 67.6         | 79       | 57.6    | 74.7  |
+| **OpenBioLLM-8B**    | 76.101      | 86.1               | 69.829  | 78.21        | 84.213         | 68.042           | 58.993       | 74.12     | 56.913  | 72.502 |
+| Gemini-1.0             | 76.7        | 75.8             | 66.7    | 77.7         | 88              | 69.2             | 58          | 70.7     | 54.3    | 70.79 |
+| GPT-3.5 Turbo 1106     | 74.71       | 74               | 72.79   | 72.79        | 72.91           | 64.73            | 57.71        | 72.66    | 53.79   | 66    |
+| Meditron-70B           | 66.79       | 69               | 53.33   | 71.69        | 76.38           | 63               | 57.1         | 76.6     | 46.85   | 64.52 |
+| gemma-7b               | 69.81       | 70               | 59.26   | 66.18        | 79.86           | 60.12            | 47.21        | 76.2     | 48.96   | 64.18 |
+| Mistral-7B-v0.1        | 68.68       | 71               | 55.56   | 68.38        | 68.06           | 59.54            | 50.82        | 75.4     | 48.2    | 62.85 |
+| Apollo-7B              | 62.26       | 72               | 61.48   | 69.12        | 70.83           | 55.49            | 55.22        | 39.8     | 53.77   | 60    |
+| MedAlpaca-7b           | 57.36       | 69               | 57.04   | 67.28        | 65.28           | 54.34            | 41.71        | 72.8     | 37.51   | 58.03 |
+| BioMistral-7B          | 59.9        | 64               | 56.5    | 60.4         | 59              | 54.7             | 50.6         | 77.5     | 48.1    | 57.3  |
+| AlpaCare-llama2-7b     | 49.81       | 49               | 45.92   | 33.82        | 50              | 43.35            | 29.77        | 72.2     | 34.42   | 45.36 |
+| ClinicalGPT            | 30.56       | 27               | 30.37   | 19.48        | 25              | 24.27            | 26.08        | 63.8     | 28.18   | 30.52 |
+
+<div align="center">
+<img width="1600px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_SzdcJSBjZyo8RS1bTEkP.png">
+</div>
+
+## Detailed Medical Subjectwise accuracy
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/UXF-V0col0Z0sS6BGPBkE.png)
+
+# Use Cases & Examples
+
+🚨 **Below results are from the quantized version of OpenBioLLM-70B
+
+
+# Summarize Clinical Notes
+
+OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/xdwdBgOxNi_TfML0hKlI8.png)
+
+# Answer Medical Questions
+
+OpenBioLLM-70B can provide answers to a wide range of medical questions.
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/zO95GlwOQEZqCKQF69mE6.png)
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/OKBczKw7gWeW5xsuDpc27.png)
+
+<details>
+  <summary>Click to see details</summary>
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/eJGHT5khppYvJb8fQ-YW4.png)
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Cnbwrqa_-ORHRuNRC2P6Y.png)
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/J9DhdcvukAc9mnnW9fj2C.png)
+
+</details>
+
+# Clinical Entity Recognition
+
+OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research.
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_69BW4k9LVABFwtxixL45.png)
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/DKy5wYCoPhoPPUc1-x8_J.png)
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/7WD9zCCBZT4-4XlfnIQjl.png)
+
+# Biomarkers Extraction
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/ZttoM4AiteT7gFYVhjIpN.png)
+
+
+# Classification
+
+OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Bf5MW1d75qT-1F_TR_hC0.png)
+
+# De-Identification
+
+OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA.
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/hKX4kzm--Tw5bj6K78msy.png)
+
+
+
+**Advisory Notice!** 
+
+While OpenBioLLM-70B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments.
+
+Therefore, we strongly advise against using OpenBioLLM-70B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations.
+OpenBioLLM-70B is intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor.
+
+Appropriately adapting and validating OpenBioLLM-70B for specific medical use cases would require significant additional work, potentially including:
+
+- Thorough testing and evaluation in relevant clinical scenarios
+- Alignment with evidence-based guidelines and best practices
+- Mitigation of potential biases and failure modes
+- Integration with human oversight and interpretation
+- Compliance with regulatory and ethical standards
+
+Always consult a qualified healthcare provider for personal medical needs.
+
+
+
+# Citation
+
+If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows:
+
+```
+@misc{OpenBioLLMs,
+  author = {Ankit Pal, Malaikannan Sankarasubbu},
+  title = {OpenBioLLMs: Advancing Open-Source Large Language Models for Healthcare and Life Sciences},
+  year = {2024},
+  publisher = {Hugging Face},
+  journal = {Hugging Face repository},
+  howpublished = {\url{https://huggingface.co/aaditya/OpenBioLLM-Llama3-70B}}
+}
+```
+
+The accompanying paper is currently in progress and will be released soon.
+
+<div align="center">
+<h2> 💌 Contact </h2>
+</div>
+
+We look forward to hearing you and collaborating on this exciting project!
+
+**Contributors:**
+- [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) [aadityaura at gmail dot com]
+- Saama AI Labs
+- Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset.
+
+
+# References
+
+We thank the [Meta Team](meta-llama/Meta-Llama-3-70B-Instruct) for their amazing models!
+
+
+Result sources
+
+- [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (https://arxiv.org/abs/2303.13375) 
+- [2] Med-PaLM-1 [Large Language Models Encode Clinical Knowledge](https://arxiv.org/abs/2212.13138)
+- [3] Med-PaLM-2 [Towards Expert-Level Medical Question Answering with Large Language Models](https://arxiv.org/abs/2305.09617)
+- [4] Gemini-1.0 [Gemini Goes to Med School](https://arxiv.org/abs/2402.07023)