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
显示更多📈 Telegram 频道 Machinelearning 的分析概览
频道 Machinelearning (@ai_machinelearning_big_data) 俄语 语言赛道中的 是活跃参与者。目前社区聚集了 295 712 名订阅者,在 技术与应用 类别中位列第 332,并在 俄罗斯 地区排名第 1 273 位。
📊 受众指标与增长动态
自 невідомо 创建以来,项目保持高速增长,吸引了 295 712 名订阅者。
根据 23 六月, 2026 的最新数据,频道保持稳定运转。过去 30 天订阅人数变化为 -6 330,过去 24 小时变化为 -217,整体触达仍然可观。
- 认证状态: 未认证
- 互动率 (ER): 平均受众互动率为 7.94%。内容发布后 24 小时内通常能获得 5.68% 的反应,占订阅者总量。
- 帖子覆盖: 每篇帖子平均可获得 23 490 次浏览,首日通常累积 16 791 次浏览。
- 互动与反馈: 受众积极参与,单帖平均反应数为 190。
- 主题关注点: 内容集中在 openai, claude, api, gemini, контекст 等核心主题上。
📝 描述与内容策略
作者将该频道定位为表达主观观点的平台:
“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”
凭借高频更新(最新数据采集于 24 六月, 2026),频道始终保持新鲜度与高覆盖。分析显示受众积极互动,使其成为 技术与应用 类别中的关键影响点。
omni_speech/infer/examples, а затем обратитесь скрипту omni_speech/infer/run.sh.
▶️Установка :
# Clone repository
git clone https://github.com/ictnlp/LLaMA-Omni
cd LLaMA-Omni
# Install packages
conda create -n llama-omni python=3.10
conda activate llama-omni
pip install pip==24.0
pip install -e .
# Install fairseq
git clone https://github.com/pytorch/fairseq
cd fairseq
pip install -e . --no-build-isolation
# Install flash-attention
pip install flash-attn --no-build-isolation
▶️ Выполните команды, описанные в разделах Quick Start и Gradio Demo. Интерфейс будет доступен в вашем браузере по адресу http://localhost:8000/
📌Лицензирование : Apache 2.0 License.
🟡Модель
🟡Arxiv
🖥Github
@ai_machinelearning_big_data
#AI #ML #LLM #Llama #SpeechToSpeech# Graph Reasoning installation
pip install git+https://github.com/lamm-mit/GraphReasoning
# wkhtmltopdf installation
sudo apt-get install wkhtmltopdf
# Graph file
from huggingface_hub import hf_hub_download
graph_name='large_graph_simple_giant.graphml'
filename = f"{graph_name}"
file_path = hf_hub_download(repo_id='lamm-mit/bio-graph-1K', filename=filename, local_dir='./graph_giant_component')
# Embeddings
from huggingface_hub import hf_hub_download
embedding_name='embeddings_simple_giant_ge-large-en-v1.5.pkl'
filename = f"{embedding_name}"
file_path = hf_hub_download(repo_id='lamm-mit/bio-graph-1K', filename=filename, local_dir='./graph_giant_component')
# Clone SciAgents
git clone https://github.com/lamm-mit/SciAgentsDiscovery.git
# Insatll reqs
cd SciAgentsDiscovery
pip install -e .
🟡Arxiv
🖥Github
@ai_machinelearning_big_data
#AI #ML #Alents #Research #SciAgentsDiscovery# Clone repo
git clone https://github.com/Vchitect/VEnhancer.git
cd VEnhancer
# Create environment
conda create -n venhancer python=3.10
conda activate venhancer
# Install requirments:
pip install torch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2
pip install -r requirements.txt
▶️Установка пакета ffmpeg:
sudo apt-get update && apt-get install ffmpeg libsm6 libxext6 -y
▶️Инференс с помощью CLI:
bash run_VEnhancer.sh
▶️Инференс с помощью GradioUI:
python gradio_app.py
🟡Страница проекта
🟡Arxiv
🟡Модель
🟡Demo Video
🖥Github [ Stars: 224 | Issues: 8 | Forks: 13]
@ai_machinelearning_big_data
#AI #Text2Video #VEnchancer #ML# Clone repo & crate venv
git clone https://github.com/efeslab/Nanoflow.git
cd Nanoflow
chmod +x ./installAnaconda.sh
./installAnaconda.sh
# Install dependencies
yes | ./setup.sh
# Download model
./modelDownload.sh
# Serving datasets
./serve.sh
📌Лицензирование : Apache 2.0 License.
🟡Arxiv
🖥Github [ Stars: 282 | Issues: 5 | Forks: 8]
@ai_machinelearning_big_data
#AI #Framework #MLTool #NanoFlow #LLM# NOTE! Install the `transformers` & `torch` libraries first
from transformers import OlmoeForCausalLM, AutoTokenizer
import torch
DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
# Load different ckpts via passing e.g. `revision=step10000-tokens41B`
# also check allenai/OLMoE-1B-7B-0924-SFT & allenai/OLMoE-1B-7B-0924-Instruct
model = OlmoeForCausalLM.from_pretrained("allenai/OLMoE-1B-7B-0924").to(DEVICE)
tokenizer = AutoTokenizer.from_pretrained("allenai/OLMoE-1B-7B-0924")
inputs = tokenizer("Bitcoin is", return_tensors="pt")
inputs = {k: v.to(DEVICE) for k, v in inputs.items()}
out = model.generate(**inputs, max_length=64)
print(tokenizer.decode(out[0]))
# > # Bitcoin is a digital currency that is created and held electronically.
#No one controls it. Bitcoins aren’t printed, like dollars or euros – they’re produced by people and businesses running computers all around the world, using software that solves mathematical
📌Лицензирование : Apache 2.0 License.
🟡Arxiv
🟡Dataset
🟡Набор моделей
🖥Github
@ai_machinelearning_big_data
#AI #ML #LLM #MoE# Create & activate venv
conda create -n omni python=3.10
conda activate omni
# Clone the Repository
git clone https://github.com/gpt-omni/mini-omni.git
cd mini-omni
# Install required packages
pip install -r requirements.txt
# start server
python3 server.py --ip '0.0.0.0' --port 60808
Запуск с Streamlit UI:
# run streamlit with PyAudio
pip install PyAudio==0.2.14
API_URL=http://0.0.0.0:60808/chat streamlit run webui/omni_streamlit.py
Запуск с Gradio UI:
API_URL=http://0.0.0.0:60808/chat python3 webui/omni_gradio.py
📌Лицензирование : MIT License.
🟡Arxiv
🟡Demo
🟡Модель
🖥Github
@ai_machinelearning_big_data
#AI #ML #MMLM #Speech2Speech #MiniOmni
现已上线!2025 年 Telegram 研究 — 年度关键洞察 
