Initial Commit

README.md

@@ -1,3 +1,87 @@
 ---
 license: cc
+language:
+- en
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- medical
 ---
+# Medguanaco LoRA 33b 8bit
+
+
+## Table of Contents
+
+[Model Description](#model-description)  
+- [Architecture](#architecture)    
+- [Training Data](#trainig-data)  
+[Model Usage](#model-usage)  
+[Limitations](#limitations)  
+
+## Model Description
+### Architecture
+`nmitchko/medguanaco-lora-33b-8bit` is a large language model LoRa specifically fine-tuned for medical domain tasks.
+It is based on the Guanaco LORA of LLaMA weighing in at 33B parameters. 
+The primary goal of this model is to improve question-answering and medical dialogue tasks.
+It was trained using [LoRA](https://arxiv.org/abs/2106.09685) and reduced to 8bit, to reduce memory footprint. 
+
+Steps to load this model:
+1. Load Guanaco-33b-merged https://huggingface.co/timdettmers/guanaco-33b-merged **in 8-bit**
+    * I recommend using text-generation-ui to test it out: https://github.com/oobabooga/text-generation-webui/tree/main
+2. Apply this LoRA to the model, this was trainied in 8-bit mode and results may vary in higher dimensions.
+
+
+```python
+# Some llama or alpaca model 65b
+base_model = "timdettmers/guanaco-33b-merged"
+model = LlamaForCausalLM.from_pretrained(
+    base_model,    
+    load_in_8bit=load_8bit,
+    torch_dtype=torch.float16
+)
+# Load the LORA on top
+lora_weights = "nmitchko/medguanaco-lora-33b-8bit"
+model = PeftModel.from_pretrained(
+    model,
+    lora_weights,
+    torch_dtype=torch.float16
+)
+```
+
+---
+
+> The following README is taken from the source page [medalpaca](https://huggingface.co/medalpaca/medalpaca-lora-13b-8bit)
+
+### Training Data
+The training data for this project was sourced from various resources. 
+Firstly, we used Anki flashcards to automatically generate questions, 
+from the front of the cards and anwers from the back of the card. 
+Secondly, we generated medical question-answer pairs from [Wikidoc](https://www.wikidoc.org/index.php/Main_Page). 
+We extracted paragraphs with relevant headings, and used Chat-GPT 3.5 
+to generate questions from the headings and using the corresponding paragraphs 
+as answers. This dataset is still under development and we believe 
+that approximately 70% of these question answer pairs are factual correct. 
+Thirdly, we used StackExchange to extract question-answer pairs, taking the 
+top-rated question from five categories: Academia, Bioinformatics, Biology, 
+Fitness, and Health. Additionally, we used a dataset from [ChatDoctor](https://arxiv.org/abs/2303.14070) 
+consisting of 200,000 question-answer pairs, available at https://github.com/Kent0n-Li/ChatDoctor.
+
+| Source                      | n items |
+|------------------------------|--------|
+| ChatDoc large                | 200000 |
+| wikidoc                      | 67704  |
+| Stackexchange academia       | 40865  |
+| Anki flashcards              | 33955  |
+| Stackexchange biology        | 27887  |
+| Stackexchange fitness        | 9833   |
+| Stackexchange health         | 7721   |
+| Wikidoc patient information  | 5942   |
+| Stackexchange bioinformatics | 5407   |
+
+
+## Limitations
+The model may not perform effectively outside the scope of the medical domain.
+The training data primarily targets the knowledge level of medical students, 
+which may result in limitations when addressing the needs of board-certified physicians.
+The model has not been tested in real-world applications, so its efficacy and accuracy are currently unknown. 
+It should never be used as a substitute for a doctor's opinion and must be treated as a research tool only.

adapter_config.json

@@ -0,0 +1,17 @@
+{
+  "base_model_name_or_path": "models/timdettmers_guanaco-33b-merged",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f71cefb236fb5a3e0037e473243fa21d7f02b7a6e113cea25528d8b155e34a13
+size 204559498

training_parameters.json

@@ -0,0 +1 @@
+{"lora_name": "medguanaco-33b-lora-8bit", "always_override": false, "save_steps": 0.0, "micro_batch_size": 1, "batch_size": 128, "epochs": 3.0, "learning_rate": "3e-4", "lr_scheduler_type": "linear", "lora_rank": 32, "lora_alpha": 64, "lora_dropout": 0.05, "cutoff_len": 256, "dataset": "medical_meadow_small", "eval_dataset": "None", "format": "alpaca-format", "eval_steps": 100.0, "raw_text_file": "None", "overlap_len": 128, "newline_favor_len": 128, "higher_rank_limit": false, "warmup_steps": 100.0, "optimizer": "adamw_torch", "hard_cut_string": "\\n\\n\\n", "train_only_after": ""}