Machinelearning
Погружаемся в машинное обучение и Data Science Показываем как запускать любые LLm на пальцах. По всем вопросам - @haarrp @itchannels_telegram -🔥best channels Реестр РКН: clck.ru/3Fmqri
Show more📈 Analytical overview of Telegram channel Machinelearning
Channel Machinelearning (@ai_machinelearning_big_data) in the Russian language segment is an active participant. Currently, the community unites 296 030 subscribers, ranking 329 in the Technologies & Applications category and 1 275 in the Russia region.
📊 Audience metrics and dynamics
Since its creation on невідомо, the project has demonstrated rapid growth, gathering an audience of 296 030 subscribers.
According to the latest data from 21 June, 2026, the channel demonstrates stable activity. Although there has been a change in the number of participants by -6 159 over the last 30 days and by -192 over the last 24 hours, overall reach remains high.
- Verification status: Not verified
- Engagement rate (ER): The average audience engagement rate is 8.12%. Within the first 24 hours after publication, content typically collects 5.73% reactions from the total number of subscribers.
- Post reach: On average, each post receives 24 037 views. Within the first day, a publication typically gains 16 970 views.
- Reactions and interaction: The audience actively supports content: the average number of reactions per post is 191.
- Thematic interests: Content is focused on key topics such as openai, claude, api, gemini, контекст.
📝 Description and content policy
The author describes the resource as a platform for expressing subjective opinions:
“Погружаемся в машинное обучение и Data Science
Показываем как запускать любые LLm на пальцах.
По всем вопросам - @haarrp
@itchannels_telegram -🔥best channels
Реестр РКН: clck.ru/3Fmqri”
Thanks to the high frequency of updates (latest data received on 22 June, 2026), the channel maintains relevance and a high level of publication reach. Analytics show that the audience actively interacts with content, making it an important point of influence in the Technologies & Applications category.
paligemma2-10b-ft-docci-448 на Transformers:
from transformers import AutoProcessor, PaliGemmaForConditionalGeneration
from PIL import Image
import requests
model_id = "google/paligemma2-10b-ft-docci-448"
model = PaliGemmaForConditionalGeneration.from_pretrained(model_id)
model = model.to("cuda")
processor = AutoProcessor.from_pretrained(model_id)
prompt = "<image>caption en"
image_file = "% link_to_target_file%"
raw_image = Image.open(requests.get(image_file, stream=True).raw).convert("RGB")
inputs = processor(prompt, raw_image, return_tensors="pt").to("cuda")
output = model.generate(**inputs, max_new_tokens=20)
print(processor.decode(output[0], skip_special_tokens=True)[len(prompt):])
📌Лицензирование: Gemma License.
🟡Статья
🟡Коллекция на HF
🟡Arxiv
@ai_machinelearning_big_data
#AI #ML #VLM #Google #PaliGemma# Install via PyPI
pip install pydantic-ai
# Set Gemini API key
export GEMINI_API_KEY=your-api-key
# Run example
from pydantic_ai import Agent
agent = Agent(
'gemini-1.5-flash',
system_prompt='Be concise, reply with one sentence.',
)
result = agent.run_sync('Where does "hello world" come from?')
print(result.data)
"""
The first known use of "hello, world" was in a 1974 textbook about the C programming language.
"""
📌Лицензирование: MIT License.
🟡Документация
🟡Demo
🖥GitHub
@ai_machinelearning_big_data
#AI #ML #LLM #Agents #Framework #PydanticAImamba или micromamba, поскольку conda может работать значительно медленнее при разрешении зависимостей в environment.yaml.
▶️ Установка и использование на примере ASE калькулятора:
# Install package with the latest version
pip install git+https://github.com/microsoft/mattersim.git
# Create env via mamba
mamba env create -f environment.yaml
mamba activate mattersim
uv pip install -e .
python setup.py build_ext --inplace
# Minimal example using ASE calculator
import torch
from ase.build import bulk
from ase.units import GPa
from mattersim.forcefield import MatterSimCalculator
device = "cuda" if torch.cuda.is_available() else "cpu"
print(f"Running MatterSim on {device}")
si = bulk("Si", "diamond", a=5.43)
si.calc = MatterSimCalculator(device=device)
print(f"Energy (eV) = {si.get_potential_energy()}")
print(f"Energy per atom (eV/atom) = {si.get_potential_energy()/len(si)}")
print(f"Forces of first atom (eV/A) = {si.get_forces()[0]}")
print(f"Stress[0][0] (eV/A^3) = {si.get_stress(voigt=False)[0][0]}")
print(f"Stress[0][0] (GPa) = {si.get_stress(voigt=False)[0][0] / GPa}")
📌Лицензирование: MIT License.
🟡Модель
🟡Документация
🟡Arxiv
🖥GitHub
@ai_machinelearning_big_data
#AI #ML #DL #Mattersim #Microsoftbathroom:
# Clone repo:
git clone https://github.com/caiyuanhao1998/HDR-GS --recursive
# Windows only
SET DISTUTILS_USE_SDK=1
# install environment of 3DGS
cd HDR-GS
conda env create --file environment.yml
conda activate hdr_gs
# Synthetic scenes
python3 train_synthetic.py --config config/bathroom.yaml --eval --gpu_id 0 --syn --load_path output/mlp/bathroom/exp-time/point_cloud/interation_x --test_only
📌Лицензирование: MIT License.
🟡Arxiv
🟡Датасет и веса
🖥GitHub
@ai_machinelearning_big_data
#AI #ML #HDR-GS #Gaussian# Clone repo:
git clone https://github.com/tencent/HunyuanVideo
cd HunyuanVideo
# Prepare conda environment
conda env create -f environment.yml
conda activate HunyuanVideo
# Install pip dependencies
python -m pip install -r requirements.txt
# Install flash attention v2
python -m pip install git+https://github.com/Dao-AILab/flash-attention.git@v2.5.9.post1
# Inference
python3 sample_video.py \
--video-size 720 \
--video-length 129 \
--infer-steps 50 \
--prompt "%prompt%" \
--flow-reverse \
--use-cpu-offload \
--save-path ./results
📌Лицензирование: Tencent Hunyuan Community License.
🟡Страница проекта
🟡Модель HunyuanVideo
🟡Модель HunyuanVideo-PromptRewrite
🟡Техотчет
🖥 GitHub
@ai_machinelearning_big_data
#AI #ML #Text2Video #Tencent #HunyuanVideo# Clone the repository
pip install 'git+https://github.com/apple/ml-aim.git#subdirectory=aim-v2'
# Example Using PyTorch
from PIL import Image
from aim.v2.utils import load_pretrained
from aim.v1.torch.data import val_transforms
img = Image.open(...)
model = load_pretrained("aimv2-large-patch14-336", backend="torch")
transform = val_transforms(img_size=336)
inp = transform(img).unsqueeze(0)
features = model(inp)
📌Лицензирование: Apple Sample Code License.
🟡Коллекция на HF
🟡Arxiv
🖥GitHub
@ai_machinelearning_big_data
#AI #ML #Vision #Apple #AIMv2
Available now! Telegram Research 2025 — the year's key insights 
