You can deploy this model and start earning money today!

RichardErkhov/
AdaptLLM_-_medicine-LLM-13B-gguf

Name: AdaptLLM_-_medicine-LLM-13B-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

medicine-LLM-13B - GGUF

Model creator: https://huggingface.co/AdaptLLM/
Original model: https://huggingface.co/AdaptLLM/medicine-LLM-13B/

Name	Quant method	Size
medicine-LLM-13B.Q2_K.gguf	Q2_K	4.52GB
medicine-LLM-13B.IQ3_XS.gguf	IQ3_XS	4.99GB
medicine-LLM-13B.IQ3_S.gguf	IQ3_S	5.27GB
medicine-LLM-13B.Q3_K_S.gguf	Q3_K_S	5.27GB
medicine-LLM-13B.IQ3_M.gguf	IQ3_M	5.57GB
medicine-LLM-13B.Q3_K.gguf	Q3_K	5.9GB
medicine-LLM-13B.Q3_K_M.gguf	Q3_K_M	5.9GB
medicine-LLM-13B.Q3_K_L.gguf	Q3_K_L	6.45GB
medicine-LLM-13B.IQ4_XS.gguf	IQ4_XS	6.54GB
medicine-LLM-13B.Q4_0.gguf	Q4_0	6.86GB
medicine-LLM-13B.IQ4_NL.gguf	IQ4_NL	6.9GB
medicine-LLM-13B.Q4_K_S.gguf	Q4_K_S	6.91GB
medicine-LLM-13B.Q4_K.gguf	Q4_K	7.33GB
medicine-LLM-13B.Q4_K_M.gguf	Q4_K_M	7.33GB
medicine-LLM-13B.Q4_1.gguf	Q4_1	7.61GB
medicine-LLM-13B.Q5_0.gguf	Q5_0	8.36GB
medicine-LLM-13B.Q5_K_S.gguf	Q5_K_S	8.36GB
medicine-LLM-13B.Q5_K.gguf	Q5_K	8.6GB
medicine-LLM-13B.Q5_K_M.gguf	Q5_K_M	8.6GB
medicine-LLM-13B.Q5_1.gguf	Q5_1	9.1GB
medicine-LLM-13B.Q6_K.gguf	Q6_K	9.95GB
medicine-LLM-13B.Q8_0.gguf	Q8_0	12.88GB

Original model description:

language:

en datasets:
Open-Orca/OpenOrca
GAIR/lima
WizardLM/WizardLM_evol_instruct_V2_196k
EleutherAI/pile metrics:
accuracy pipeline_tag: text-generation tags:
biology
medical license: apache-2.0

Adapting Large Language Models to Domains via Continual Pre-Training

This repo contains the domain-specific base model developed from LLaMA-1-13B, using the method in our ICLR 2024 paper Adapting Large Language Models via Reading Comprehension.

We explore continued pre-training on domain-specific corpora for large language models. While this approach enriches LLMs with domain knowledge, it significantly hurts their prompting ability for question answering. Inspired by human learning via reading comprehension, we propose a simple method to transform large-scale pre-training corpora into reading comprehension texts, consistently improving prompting performance across tasks in biomedicine, finance, and law domains. Our 7B model competes with much larger domain-specific models like BloombergGPT-50B.

🤗 [2024/6/21] We release the 2nd version of AdaptLLM at Instruction-Pretrain 🤗

**************************** Updates ****************************

2024/6/22: Released the benchmarking code.
2024/6/21: Released the 2nd version of AdaptLLM at Instruction-Pretrain.
2024/1/16: Our research paper has been accepted by ICLR 2024.
2023/12/19: Released our 13B base models developed from LLaMA-1-13B.
2023/12/8: Released our chat models developed from LLaMA-2-Chat-7B.
2023/9/18: Released our paper, code, data, and base models developed from LLaMA-1-7B.

Domain-Specific LLaMA-1

LLaMA-1-7B

In our paper, we develop three domain-specific models from LLaMA-1-7B, which are also available in Huggingface: Biomedicine-LLM, Finance-LLM and Law-LLM, the performances of our AdaptLLM compared to other domain-specific LLMs are:

LLaMA-1-13B

Moreover, we scale up our base model to LLaMA-1-13B to see if our method is similarly effective for larger-scale models, and the results are consistently positive too: Biomedicine-LLM-13B, Finance-LLM-13B and Law-LLM-13B.

Domain-Specific LLaMA-2-Chat

Our method is also effective for aligned models! LLaMA-2-Chat requires a specific data format, and our reading comprehension can perfectly fit the data format by transforming the reading comprehension into a multi-turn conversation. We have also open-sourced chat models in different domains: Biomedicine-Chat, Finance-Chat and Law-Chat

For example, to chat with the biomedicine model (💗 An amazing usage example):

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("AdaptLLM/medicine-LLM-13B")
tokenizer = AutoTokenizer.from_pretrained("AdaptLLM/medicine-LLM-13B", use_fast=False)

# Put your input here:
user_input = '''Question: Which of the following is an example of monosomy?
Options:
- 46,XX
- 47,XXX
- 69,XYY
- 45,X

Please provide your choice first and then provide explanations if possible.'''

# Simply use your input as the prompt for base models
prompt = user_input

inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).input_ids.to(model.device)
outputs = model.generate(input_ids=inputs, max_length=2048)[0]

answer_start = int(inputs.shape[-1])
pred = tokenizer.decode(outputs[answer_start:], skip_special_tokens=True)

print(f'### User Input:\n{user_input}\n\n### Assistant Output:\n{pred}')

Domain-Specific Tasks

To easily reproduce our results, we have uploaded the filled-in zero/few-shot input instructions and output completions of each domain-specific task: biomedicine-tasks, finance-tasks, and law-tasks.

Note: those filled-in instructions are specifically tailored for models before alignment and do NOT fit for the specific data format required for chat models.

Citation

If you find our work helpful, please cite us:

bibtex

@inproceedings{
cheng2024adapting,
title={Adapting Large Language Models via Reading Comprehension},
author={Daixuan Cheng and Shaohan Huang and Furu Wei},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=y886UXPEZ0}
}

RichardErkhov/AdaptLLM_-_medicine-LLM-13B-gguf