12 21

ll PRO

Etherll

AI & ML interests

None yet

Recent Activity

reacted to MrDragonFox's post with 👍 2 days ago

yet a other audio datasets pre classified for events + audio aestetics this time for german - 680h sampled from emilia yodas timestamps for asr training or other fancier things available as nc in the raw repo https://huggingface.co/datasets/MrDragonFox/DE_Emilia_Yodas_680h cc by 4.0 as by emilia yodas raw events / transcriptions are cc by NC 4.0 https://huggingface.co/datasets/MrDragonFox/DE_Emilia_Yodas_680h_raw_timestamps the coming days i should push about 600h english + some japanese too same format

reacted to MrDragonFox's post with 🔥 2 days ago

liked a dataset 2 days ago

MrDragonFox/DE_Emilia_Yodas_680h

View all activity

Organizations

Etherll's activity

reacted to MrDragonFox's post with 👍🔥 2 days ago

Post

2989

yet a other audio datasets pre classified for events + audio aestetics

this time for german - 680h sampled from emilia yodas

timestamps for asr training or other fancier things available as nc in the raw repo

MrDragonFox/DE_Emilia_Yodas_680h

cc by 4.0 as by emilia yodas

raw events / transcriptions are cc by NC 4.0

MrDragonFox/DE_Emilia_Yodas_680h_raw_timestamps

the coming days i should push about 600h english + some japanese too same format

liked 2 datasets 2 days ago

MrDragonFox/DE_Emilia_Yodas_680h

Viewer • Updated 1 day ago • 245k • 127 • 3

Etherll/CodeFIM-Data

Viewer • Updated 5 days ago • 238k • 42 • 1

New activity in Etherll/CodeFIM-Data 3 days ago

[bot] Conversion to Parquet

#1 opened 5 days ago by

parquet-converter

published a dataset 5 days ago

Etherll/CodeFIM-Data

Viewer • Updated 5 days ago • 238k • 42 • 1

updated a dataset 5 days ago

Etherll/CodeFIM-Data

Viewer • Updated 5 days ago • 238k • 42 • 1

liked a model 7 days ago

canopylabs/3b-de-pretrain-research_release

Text-to-Speech • Updated 7 days ago • 776 • 9

reacted to merterbak's post with 🔥 7 days ago

Post

4628

Qwen 3 can launch very soon. 👀

https://github.com/ggml-org/llama.cpp/pull/12828

3 replies

reacted to danielhanchen's post with 🚀❤️🔥🤗 8 days ago

Post

4531

You can now run Llama 4 on your own local device! 🦙
Run our Dynamic 1.78-bit and 2.71-bit Llama 4 GGUFs:
unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF

You can run them on llama.cpp and other inference engines. See our guide here: https://docs.unsloth.ai/basics/tutorial-how-to-run-and-fine-tune-llama-4

1 reply

liked a model 10 days ago

unsloth/Llama-4-Scout-17B-16E-Instruct-unsloth

Image-Text-to-Text • Updated 4 days ago • 2.24k • 14

reacted to hesamation's post with ❤️ 10 days ago

Post

2812

The best researchers from Yale, Stanford, Google DeepMind, and Microsoft laid out all we know about Agents in a 264-page paper [book],

Here are some of their key findings:

They build a mapping of different agent components, such as perception, memory, and world modelling, to different regions of the human brain and compare them:

- brain is much more energy-efficient
- no genuine experience in agents
- brain learns continuously, agent is static

An agent is broken down to:
- Perception: the agent's input mechanism. can be improved with multi-modality, feedback mechanisms (e.g., human corrections), etc.
- Cognition: learning, reasoning, planning, memory. LLMs are key in this part.
- Action: agent's output and tool use.

Agentic memory is represented as:
- Sensory memory or short-term holding of inputs which is not emphasized much in agents.
- Short-term memory which is the LLM context window
- Long-term memory which is the external storage such as RAG or knowledge graphs.

The memory in agents can be improved and researched in terms of:
- increasing the amount of stored information
- how to retrieve the most relevant info
- combining context-window memory with external memory
- deciding what to forget or update in memory

The agent must simulate or predict the future states of the environment for planning and decision-making.

ai world models are much simpler than the humans' with their causal reasoning (cause-and-effect) or physical intuition.

LLM world models are mostly implicit and embedded.

EMOTIONS are a deep aspect of humans, helping them with social interactions, decision-making, or learning.

Agents must understand emotions to better interact with us.

But rather than encoding the feeling of emotions, they have a surface-level modelling of emotions.

Perception is the process by which an agent receives and interprets raw data from its surroundings.

READ PAPER: Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems (2504.01990)

liked a model 11 days ago

unsloth/Llama-4-Scout-17B-16E-Instruct

Image-Text-to-Text • Updated 5 days ago • 8.88k • 56

liked a dataset 17 days ago

MohamedRashad/Quran-Recitations

Viewer • Updated 17 days ago • 125k • 1.55k • 38

reacted to MohamedRashad's post with 👀❤️ 17 days ago

Post

2210

I collected the recitations of the holy quran from 20 different reciters and uploaded the full dataset here:
MohamedRashad/Quran-Recitations

Check it out 🥷

liked a Space 19 days ago

Hi!

🦥