Lewdiculous/Datura_7B-GGUF-Imatrix
Updated
β’
85
β’
6
alves
alvesrt
AI & ML interests
None yet
Recent Activity
liked
a model
1 day ago
Lewdiculous/Datura_7B-GGUF-Imatrix
upvoted
an
article
1 day ago
Timm β€οΈ Transformers: Use any timm model with transformers
upvoted
a
paper
2 days ago
Llamba: Scaling Distilled Recurrent Models for Efficient Language
Processing
Organizations
alvesrt's activity
liked
a
model
1 day ago
upvoted
an
article
1 day ago
Article
Timm β€οΈ Transformers: Use any timm model with transformers
β’
44
upvoted
a
paper
2 days ago
liked
a
Space
2 days ago
upvoted
8
papers
2 days ago
The Mamba in the Llama: Distilling and Accelerating Hybrid Models
Paper
β’
2408.15237
β’
Published
β’
41
MambaByte: Token-free Selective State Space Model
Paper
β’
2401.13660
β’
Published
β’
56
Diffusion Models Without Attention
Paper
β’
2311.18257
β’
Published
β’
3
BlackMamba: Mixture of Experts for State-Space Models
Paper
β’
2402.01771
β’
Published
β’
25
Gated recurrent neural networks discover attention
Paper
β’
2309.01775
β’
Published
β’
10
RWKV: Reinventing RNNs for the Transformer Era
Paper
β’
2305.13048
β’
Published
β’
17
The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry
Paper
β’
2402.04347
β’
Published
β’
15
Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence
Paper
β’
2404.05892
β’
Published
β’
36
upvoted
a
collection
2 days ago
upvoted
a
paper
2 days ago
upvoted
an
article
2 days ago
Article
Bamba: Inference-Efficient Hybrid Mamba2 Model
β’
45
reacted to
Yehor's
post with π
2 days ago
Post
2778
Published a stable version of Ukrainian Text-to-Speech library on GitHub and PyPI.
Features:
- Multi-speaker model: 2 female (Tetiana, Lada) + 1 male (Mykyta) voices;
- Fine-grained control over speech parameters, including duration, fundamental frequency (F0), and energy;
- High-fidelity speech generation using the RAD-TTS++ acoustic model;
- Fast vocoding using Vocos;
- Synthesizes long sentences effectively;
- Supports a sampling rate of 44.1 kHz;
- Tested on Linux environments and Windows/WSL;
- Python API (requires Python 3.9 or later);
- CUDA-enabled for GPU acceleration.
Repository: https://github.com/egorsmkv/tts_uk
Features:
- Multi-speaker model: 2 female (Tetiana, Lada) + 1 male (Mykyta) voices;
- Fine-grained control over speech parameters, including duration, fundamental frequency (F0), and energy;
- High-fidelity speech generation using the RAD-TTS++ acoustic model;
- Fast vocoding using Vocos;
- Synthesizes long sentences effectively;
- Supports a sampling rate of 44.1 kHz;
- Tested on Linux environments and Windows/WSL;
- Python API (requires Python 3.9 or later);
- CUDA-enabled for GPU acceleration.
Repository: https://github.com/egorsmkv/tts_uk
reacted to
davidberenstein1957's
post with π
2 days ago
Post
4088
π₯ Epic Agent Framework Showdown! Available today!
π΅ In the blue corner, the versatile challenger with a proven track record of knowledge retrieval: LlamaIndex!
π In the red corner, the defender, weighing in with lightweight efficiency: Hugging Face smolagents!
π URL: https://huggingface.co./agents-course
We just published the LlamaIndex unit for the agents course, and it is set to offer a great contrast between the smolagents unit by looking at
- What makes llama-index stand-out
- How the LlamaHub is used for integrations
- Creating QueryEngine components
- Using agents and tools
- Agentic and multi-agent workflows
The team has been working flat-out on this for a few weeks. Supported by Logan Markewich and Laurie Voss over at LlamaIndex.
Who won? You decide!
π΅ In the blue corner, the versatile challenger with a proven track record of knowledge retrieval: LlamaIndex!
π In the red corner, the defender, weighing in with lightweight efficiency: Hugging Face smolagents!
π URL: https://huggingface.co./agents-course
We just published the LlamaIndex unit for the agents course, and it is set to offer a great contrast between the smolagents unit by looking at
- What makes llama-index stand-out
- How the LlamaHub is used for integrations
- Creating QueryEngine components
- Using agents and tools
- Agentic and multi-agent workflows
The team has been working flat-out on this for a few weeks. Supported by Logan Markewich and Laurie Voss over at LlamaIndex.
Who won? You decide!
reacted to
vincentg64's
post with π
2 days ago
Post
1845
LLM Challenge with Petabytes of Data to Prove Famous Number Theory Conjecture https://mltblog.com/3F3Y9Yd
In my recent article βPiercing the Deepest Mathematical Mysteryβ, I paved the way to proving a famous multi-century old conjecture: are the digits of major mathematical constant such as Ο, e, log 2, or β2 evenly distributed? No one before ever managed to prove even the most basic trivialities, such as whether the proportion of β0β or β1β exists in the binary expansions of any of these constants, or if it oscillates indefinitely between 0% and 100%.
Here I provide an overview of the new framework built to uncover deep results about the digit distribution of Eulerβs number e, discuss the latest developments, share a 10x faster version of the code, and feature new potential research areas in LLMs, AI, quantum dynamics, high performance computing, cryptography, dynamical systems, number theory and more, arising from my discovery. Perhaps the most interesting part is testing LLMs and other AI tools to assess their reasoning capabilities on a fascinating math problem with no solution posted anywhere.
β‘οΈ Read about the challenge at https://mltblog.com/3F3Y9Yd
In my recent article βPiercing the Deepest Mathematical Mysteryβ, I paved the way to proving a famous multi-century old conjecture: are the digits of major mathematical constant such as Ο, e, log 2, or β2 evenly distributed? No one before ever managed to prove even the most basic trivialities, such as whether the proportion of β0β or β1β exists in the binary expansions of any of these constants, or if it oscillates indefinitely between 0% and 100%.
Here I provide an overview of the new framework built to uncover deep results about the digit distribution of Eulerβs number e, discuss the latest developments, share a 10x faster version of the code, and feature new potential research areas in LLMs, AI, quantum dynamics, high performance computing, cryptography, dynamical systems, number theory and more, arising from my discovery. Perhaps the most interesting part is testing LLMs and other AI tools to assess their reasoning capabilities on a fascinating math problem with no solution posted anywhere.
β‘οΈ Read about the challenge at https://mltblog.com/3F3Y9Yd
reacted to
fdaudens's
post with π
2 days ago
Post
3668
AI will bring us "a country of yes-men on servers" instead of one of "Einsteins sitting in a data center" if we continue on current trends.
Must-read by @thomwolf deflating overblown AI promises and explaining what real scientific breakthroughs require.
https://thomwolf.io/blog/scientific-ai.html
Must-read by @thomwolf deflating overblown AI promises and explaining what real scientific breakthroughs require.
https://thomwolf.io/blog/scientific-ai.html
- 2 replies
reacted to
albertvillanova's
post with π€
2 days ago
Post
3184
π New smolagents update: Safer Local Python Execution! π¦Ύπ
With the latest release, we've added security checks to the local Python interpreter: every evaluation is now analyzed for dangerous builtins, modules, and functions. π
Here's why this matters & what you need to know! π§΅π
1οΈβ£ Why is local execution risky? β οΈ
AI agents that run arbitrary Python code can unintentionally (or maliciously) access system files, run unsafe commands, or exfiltrate data.
2οΈβ£ New Safety Layer in smolagents π‘οΈ
We now inspect every return value during execution:
β Allowed: Safe built-in types (e.g., numbers, strings, lists)
β Blocked: Dangerous functions/modules (e.g., os.system, subprocess, exec, shutil)
3οΈβ£ Immediate Benefits π‘
- Prevent agents from accessing unsafe builtins
- Block unauthorized file or network access
- Reduce accidental security vulnerabilities
4οΈβ£ Security Disclaimer β οΈ
π¨ Despite these improvements, local Python execution is NEVER 100% safe. π¨
If you need true isolation, use a remote sandboxed executor like Docker or E2B.
5οΈβ£ The Best Practice: Use Sandboxed Execution π
For production-grade AI agents, we strongly recommend running code in a Docker or E2B sandbox to ensure complete isolation.
6οΈβ£ Upgrade Now & Stay Safe! π
Check out the latest smolagents release and start building safer AI agents today.
π https://github.com/huggingface/smolagents
What security measures do you take when running AI-generated code? Letβs discuss! π
#AI #smolagents #Python #Security
With the latest release, we've added security checks to the local Python interpreter: every evaluation is now analyzed for dangerous builtins, modules, and functions. π
Here's why this matters & what you need to know! π§΅π
1οΈβ£ Why is local execution risky? β οΈ
AI agents that run arbitrary Python code can unintentionally (or maliciously) access system files, run unsafe commands, or exfiltrate data.
2οΈβ£ New Safety Layer in smolagents π‘οΈ
We now inspect every return value during execution:
β Allowed: Safe built-in types (e.g., numbers, strings, lists)
β Blocked: Dangerous functions/modules (e.g., os.system, subprocess, exec, shutil)
3οΈβ£ Immediate Benefits π‘
- Prevent agents from accessing unsafe builtins
- Block unauthorized file or network access
- Reduce accidental security vulnerabilities
4οΈβ£ Security Disclaimer β οΈ
π¨ Despite these improvements, local Python execution is NEVER 100% safe. π¨
If you need true isolation, use a remote sandboxed executor like Docker or E2B.
5οΈβ£ The Best Practice: Use Sandboxed Execution π
For production-grade AI agents, we strongly recommend running code in a Docker or E2B sandbox to ensure complete isolation.
6οΈβ£ Upgrade Now & Stay Safe! π
Check out the latest smolagents release and start building safer AI agents today.
π https://github.com/huggingface/smolagents
What security measures do you take when running AI-generated code? Letβs discuss! π
#AI #smolagents #Python #Security
- 2 replies