💡 SAM2Long, a training-free enhancement to SAM 2 for long-term video segmentation


🟡Technical Report: https://huggingface.co/papers/2410.16268
🟡Github: https://github.com/Mark12Ding/SAM2Long
🟡Homepage: https://mark12ding.github.io/project/SAM2Long/



@Machine_learn

🌟 Zamba2-Instruct

В семействе 2 модели:

🟢Zamba2-1.2B-instruct;
🟠Zamba2-2.7B-instruct.



# Clone repo
git clone https://github.com/Zyphra/transformers_zamba2.git
cd transformers_zamba2

# Install the repository & accelerate:
pip install -e .
pip install accelerate

# Inference:
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Zyphra/Zamba2-2.7B-instruct")
model = AutoModelForCausalLM.from_pretrained("Zyphra/Zamba2-2.7B-instruct", device_map="cuda", torch_dtype=torch.bfloat16)

user_turn_1 = "user_prompt1."
assistant_turn_1 = "assistant_prompt."
user_turn_2 = "user_prompt2."
sample = [{'role': 'user', 'content': user_turn_1}, {'role': 'assistant', 'content': assistant_turn_1}, {'role': 'user', 'content': user_turn_2}]
chat_sample = tokenizer.apply_chat_template(sample, tokenize=False)

input_ids = tokenizer(chat_sample, return_tensors='pt', add_special_tokens=False).to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=150, return_dict_in_generate=False, output_scores=False, use_cache=True, num_beams=1, do_sample=False)
print((tokenizer.decode(outputs[0])))




🖥GitHub

https://t.iss.one/deep_learning_proj

⚡️ 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

🌟 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

💠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

📖 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

https://t.iss.one/deep_learning_proj