23171
Admin: @Raminmousa ID: @Machine_learn link: https://t.me/Machine_learn
Applied Mathematics of the Future
📚 Book
@Machine_learn
This repository contains a collection of resources in the form of eBooks related to Data Science, Machine Learning, and similar topics.
📖 book
💠@Machine_learn
📃 Plant-based anti-cancer drug discovery using computational approaches
📎 Study the paper
@Machine_learn
Smol TTS models are here! OuteTTS-0.1-350M - Zero shot voice cloning, built on LLaMa architecture, CC-BY license! 🔥
> Pure language modeling approach to TTS
> Zero-shot voice cloning
> LLaMa architecture w/ Audio tokens (WavTokenizer)
> BONUS: Works on-device w/ llama.cpp ⚡
Three-step approach to TTS:
> Audio tokenization using WavTokenizer (75 tok per second).
> CTC forced alignment for word-to-audio token mapping.
> Structured prompt creation w/ transcription, duration, audio tokens.
https://huggingface.co/OuteAI/OuteTTS-0.1-350M
@Machine_learn
Machine Learning with PyTorch and Scikit-Learn Book
📚 book
@Machine_learn
❤️ اکستنشن ChatGPT Search برای مرورگرهای کرومیوم منتشر شد
از طریق این لینک میتونید این افزونه رو دانلود کنید
فقط جایگاه دوم از این مقاله باقی مونده
Читать полностью…
👩💻 Python Notes for Professionals book
🔗 Book
@Machine_learn
💠Title:BERTCaps: BERT Capsule for persian Multi-domain Sentiment Analysis.
🔺Abstract:
Sentiment classification is widely known as a domain-dependent problem. In order to learn an accurate domain-specific sentiment classifier, a large number of labeled samples are needed, which are expensive and time-consuming to annotate. Multi-domain sentiment analysis based on multi-task learning can leverage labeled samples in each single domain, which can alleviate the need for large amount of labeled data in all domains. In this article, the purpose is BERTCaps to provide a multi-domain classifier. In this model, BERT was used for Instance Representation and Capsule was used for instance learning. In the evaluation dataset, the model was able to achieve an accuracy of 0.9712 in polarity classification and an accuracy of 0.8509 in domain classification.
journal: https://www.sciencedirect.com/journal/array
If:2.3
جايگاه ٢ و ٤ اين مقاله رو نياز داريم.
دوستاني كه مايل به شركت هستن مي تونن به ايدي بنده پيام بدن.
@Raminmousa
@Paper4money
@Machine_learn
📑A Survey of Deep Learning Methods for Estimating the Accuracy of Protein Quaternary Structure Models
📎 Study the paper
@Machine_learn
💠Title:BERTCaps: BERT Capsule for persian Multi-domain Sentiment Analysis.
🔺Abstract:
Sentiment classification is widely known as a domain-dependent problem. In order to learn an accurate domain-specific sentiment classifier, a large number of labeled samples are needed, which are expensive and time-consuming to annotate. Multi-domain sentiment analysis based on multi-task learning can leverage labeled samples in each single domain, which can alleviate the need for large amount of labeled data in all domains. In this article, the purpose is BERTCaps to provide a multi-domain classifier. In this model, BERT was used for Instance Representation and Capsule was used for instance learning. In the evaluation dataset, the model was able to achieve an accuracy of 0.9712 in polarity classification and an accuracy of 0.8509 in domain classification.
journal: https://www.sciencedirect.com/journal/array
If:2.3
جايگاه ٢ و ٤ اين مقاله رو نياز داريم.
دوستاني كه مايل به شركت هستن مي تونن به ايدي بنده پيام بدن.
@Raminmousa
@Paper4money
@Machine_learn
SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree
🖥 Github: https://github.com/mark12ding/sam2long
📕 Paper: https://arxiv.org/abs/2410.16268v1
🤗 HF: https://huggingface.co/papers/2410.16268
@Machine_learn
🌟 Aya Expanse
🟢Aya Expanse 32B
🟢Aya Expanse 8B
🟠Aya Expanse 32B-GGUF
🟠Aya Expanse 8B-GGUF
Expanse 8B Transformers :from transformers import AutoTokenizer, AutoModelForCausalLM
model_id = "CohereForAI/aya-expanse-8b"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
# Format the message with the chat template
messages = [{"role": "user", "content": " %prompt% "}]
input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
## <BOS_TOKEN><|START_OF_TURN_TOKEN|><|USER_TOKEN|>%prompt%<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
gen_tokens = model.generate(
input_ids,
max_new_tokens=100,
do_sample=True,
temperature=0.3,
)
gen_text = tokenizer.decode(gen_tokens[0])
print(gen_text)
🟡GGUF 32B
🟡GGUF 8B
🟡Demo
@Machine_learn
با عرض سلام امروز اخرين وقت براي مشاركت در اين مقاله مي باشد...!
Читать полностью…
THINKING LLMS: GENERAL INSTRUCTION FOLLOWING WITH THOUGHT GENERATION
📚 Reed
@Machine_learn
با عرض سلام مقاله زیر در مرحله ی اولیه ارسال می باشد. نفرات ۱ تا ۳ جایگاه ها خالی می باشد. دوستانی که نیاز دارند می تونن به ایدی بنده پیام بدن.
💠💠
Title:
Automated Concrete Crack Detection and Geometry Measurement Using YOLOv8
Description:
This paper presents a comprehensive approach for automatic detection and quantification of concrete cracks using the YOLOv8 deep learning model. By leveraging advanced object detection capabilities, our system identifies concrete cracks in real-time with high accuracy, addressing challenges of complex backgrounds and varying crack patterns. Following crack detection, we employ image processing techniques to measure key geometric parameters such as width, length, and area. This integrated system enables rapid, precise analysis of structural integrity, offering a scalable solution for infrastructure monitoring and maintenance.
Target Journal:
Nature, Scientific Reports
@Raminmousa
@Machine_learn
/channel/+SP9l58Ta_zZmYmY0
🔸برترین کانالهای آموزشی در زمینه های هوشمصنوعی, پایتون و یادگیری ماشین
❯ هوش مصنوعی:
1️⃣ @Ai_Tv
2⃣ @HomeAI
3⃣ @ai_in_research
4⃣ @eventai
5⃣ @Ai_NewsTv
❯ علم داده :
1️⃣ @DataPlusScience
❯ یادگیری ماشین :
1️⃣ @Machine_learn
❯ آموزش پایتون و یادگیری ماشین:
1⃣ @Python4all_pro
❯ منابع و کتابهای پایتون ، علم داده و یادگیری ماشین :
1⃣ @programmers_street
Constrained Diffusion Implicit Models!
We use diffusion models to solve noisy inverse problems like inpainting, sparse-recovery, and colorization. 10-50x faster than previous methods!
Paper: arxiv.org/pdf/2411.00359
Demo: https://t.co/m6o9GLnnZF
@Machine_learn
📕 Machine Learning for Absolute Beginners
▪️Link
@Machine_learn
AutoWebGLM: Bootstrap And Reinforce A Large Language Model-based Web Navigating Agent
🖥 Github: https://github.com/thudm/autowebglm
📕 Paper: https://arxiv.org/abs/2404.03648v1
🔥Dataset: https://paperswithcode.com/dataset/mind2web
@Machine_learn
Conformal prediction under ambiguous ground truth
Paper: https://arxiv.org/pdf/2307.09302v2.pdf
Codes:
https://github.com/google-deepmind/uncertain_ground_truth
https://github.com/alaalab/webcp
Dataset: Dermatology ddx dataset
@Machine_learn
الحمدالله تو اين بازه ٣ ماه تونستيم مقالات مشاركتي رو تحت وظايف زير انجام بديم:
🔹ثبت ٤ مقاله در حوزه Multi-modal wond classification
🔹ارائه ی دو مقاله در حوزه ی breast cancer segmentation
🔹 ارائه ی سه مقاله در حوزه ی cancer detection
که ۸۰٪ مراحل این مقالات هم تموم شده.
به زودی پس از اتمام این مقالات لیستی از مقالات مشارکتی رو خواهیم داشت .
/channel/+SP9l58Ta_zZmYmY0
📖 LLM-Agent-Paper-List is a repository of papers on the topic of agents based on large language models (LLM)! The papers are divided into categories such as LLM agent architectures, autonomous LLM agents, reinforcement learning (RL), natural language processing methods, multimodal approaches and tools for developing LLM agents, and more.
🖥 Github
/channel/deep_learning_proj
Data Pipelines with Apache Airflow
📘 book
@Machine_learn
Ms - SmolLM2 1.7B - beats Qwen 2.5 1.5B & Llama 3.21B, Apache 2.0 licensed, trained on 11 Trillion tokens 🔥
> 135M, 360M, 1.7B parameter model
> Trained on FineWeb-Edu, DCLM, The Stack, along w/ new mathematics and coding datasets
> Specialises in Text rewriting, Summarization & Function Calling
> Integrated with transformers & model on the hub!
You can run the 1.7B in less than 2GB VRAM on a Q4 👑
Fine-tune, run inference, test, train, repeat - intelligence is just 5 lines of code away!
https://huggingface.co/collections/HuggingFaceTB/smollm2-6723884218bcda64b34d7db9
@Machine_learn
تخفيف ٥٠٪🔹
دو پكيچ كدنويسي پايه يادگيري ماشين و يادگيري عميق به همراه ٣٦ بروژه عملي با پشتيباني ٢ ماهه .
جهت سفارش به ايدي بنده پيام بدين.
🔺
هزینه هر دو پک با تخفيف ۱۵۰۰ هزار ميباشد.
@Raminmousa
Intermediate Python
📖 Book
@Machine_learn
⚡️ Stable Diffusion 3.5 Large.# install Diffusers
pip install -U diffusers
# Inference
import torch
from diffusers import StableDiffusion3Pipeline
pipe = StableDiffusion3Pipeline.from_pretrained("stabilityai/stable-diffusion-3.5-large", torch_dtype=torch.bfloat16)
pipe = pipe.to("cuda")
image = pipe(
"A happy woman laying on a grass",
num_inference_steps=28,
guidance_scale=3.5,
).images[0]
image.save("woman.png")
🟡Arxiv
@Machine_learn
Title:
Advanced Classification of Drug-Drug Interactions for Assessing Adverse Effect Risks of Fluvoxamine and Curcumin Using Deep Learning in COVID-19
———————————————————————
Keywords:
Drug–Drug Interactions; Deep Neural Network; Fluvoxamine; Curcumin; Machine Learning.
———————————————————————
Journal of Infrastructure, Policy and Development
نفر اول پرشده
نفر دوم و سوم و چهارم خالی هست.
مقاله در اخرین ریوایزد خود می باشد.
@Raminmousa
@Machine_learn
/channel/+SP9l58Ta_zZmYmY0
📕 Applied Causal #Inference Powered by #MachineLearning
📌Book
@Machine_learn