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 295 549 subscribers, ranking 332 in the Technologies & Applications category and 1 273 in the Russia region.
📊 Audience metrics and dynamics
Since its creation on невідомо, the project has demonstrated rapid growth, gathering an audience of 295 549 subscribers.
According to the latest data from 23 June, 2026, the channel demonstrates stable activity. Although there has been a change in the number of participants by -6 330 over the last 30 days and by -217 over the last 24 hours, overall reach remains high.
- Verification status: Not verified
- Engagement rate (ER): The average audience engagement rate is 7.94%. Within the first 24 hours after publication, content typically collects 5.68% reactions from the total number of subscribers.
- Post reach: On average, each post receives 23 490 views. Within the first day, a publication typically gains 16 791 views.
- Reactions and interaction: The audience actively supports content: the average number of reactions per post is 190.
- 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 24 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.
# Сlone and install
git clone https://github.com/Zyphra/Zamba2.git
cd Zamba2
pip install -e
# Install core mamba dependencies
pip install -U mamba-ssm causal-conv1d
# Inference
from mamba_model import MambaModel
from mamba_config import MambaConfig
import torch
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
input_text = 'A funny prompt would be '
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")["input_ids"].transpose(0,1)
model = MambaModel.from_pretrained(model_name = "Zyphra/Zamba2-2.7B").cuda().half()
tokens_to_generate = 20
model.eval()
with torch.no_grad():
for _ in range(tokens_to_generate):
out = model(input_ids)
out_last = out[:, -1]
idx = torch.argmax(out_last)[None, None]
input_ids = torch.cat((input_ids, idx), dim=0)
input_ids = input_ids.transpose(0, 1)[0]
print(repr(tokenizer.decode(input_ids.cpu().numpy().tolist())))
📌Лицензирование : Apache 2.0 license
🟡Страница проекта
🟡Arxiv
🟡Модель на HF
🖥Github [ Stars: 10 | Issues: 0 | Forks: 0]
@ai_machinelearning_big_data
#AI #ML #SLM #Mamba# Сlone and install
git clone https://github.com/Zyphra/Zamba2.git
cd Zamba2
pip install -e
# Install core mamba dependencies
pip install -U mamba-ssm causal-conv1d
# Inference
from mamba_model import MambaModel
from mamba_config import MambaConfig
import torch
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B")
input_text = 'A funny prompt would be '
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")["input_ids"].transpose(0,1)
model = MambaModel.from_pretrained(model_name = "Zyphra/Zamba2-2.7B").cuda().half()
tokens_to_generate = 20
model.eval()
with torch.no_grad():
for _ in range(tokens_to_generate):
out = model(input_ids)
out_last = out[:, -1]
idx = torch.argmax(out_last)[None, None]
input_ids = torch.cat((input_ids, idx), dim=0)
input_ids = input_ids.transpose(0, 1)[0]
print(repr(tokenizer.decode(input_ids.cpu().numpy().tolist())))
📌Лицензирование : Apache 2.0 license
🟡Страница проекта
🟡Arxiv
🟡Модель на HF
🖥Github [ Stars: 10 | Issues: 0 | Forks: 0]
@ai_machinelearning_big_data
#AI #ML #SLM #Mamba# Dependencies Installation
pip install -r requirements.txt
# Setup FastAPI Server
python -m mindsearch.app --lang en --model_format internlm_server
# Run with Gradio
python frontend/mindsearch_gradio.pyW
📌Лицензирование : Apache 2.0 license
🟡Страница проекта
🟡Arxiv
🟡Demo Video
🟡Demo на китайским языке
🖥Github [ Stars: 61 | Issues: 0 | Forks: 7]
@ai_machinelearning_big_data
#AI #ML #LLM #AgentSearch# # import from source
git clone https://github.com/zyushun/Adam-mini
cd Adam-mini
pip install -e .
# Then use Adam-mini optimizer as follows
from adam_mini import Adam_mini
optimizer = Adam_mini(
named_parameters = model.named_parameters(),
lr = lr,
betas = (beta1,beta2),
eps = eps,
weight_decay = weight_decay,
model_sharding = True,
dim = model_config.dim,
n_heads = model_config.n_heads,
n_kv_heads = model_config.n_kv_heads,
)
# all the hyperparameters, including learning rate (lr), weight_decay, beta1, beta2, eps, its recommend using the same values as for AdamW
🟡Arxiv
🖥Github [ Stars: 226 | Issues: 8 | Forks: 9]
@ai_machinelearning_big_data
#AI #ML #Adam #Pytorch #Train
Available now! Telegram Research 2025 — the year's key insights 
