53 2 42

No Name

Ainonake

AI & ML interests

None yet

Recent Activity

new activity about 2 hours ago

microsoft/MAI-DS-R1:Report: Nice job, you've ruined a nice model with censorship no one wants or asks for

new activity 12 days ago

TheDrummer/Fallen-Command-A-111B-v1.1:🚩 Report: Illegal or restricted content

liked a model 23 days ago

canopylabs/orpheus-3b-0.1-ft

View all activity

Organizations

None yet

Ainonake's activity

New activity in microsoft/MAI-DS-R1 about 2 hours ago

Report: Nice job, you've ruined a nice model with censorship no one wants or asks for

#7 opened about 2 hours ago by

Ainonake

New activity in TheDrummer/Fallen-Command-A-111B-v1.1 12 days ago

🚩 Report: Illegal or restricted content

#1 opened 13 days ago by

clecho52

liked a model 23 days ago

canopylabs/orpheus-3b-0.1-ft

Text-to-Speech • Updated Mar 19 • 68.3k • 510

liked a model about 1 month ago

RekaAI/reka-flash-3

Updated Mar 13 • 2.75k • 362

reacted to tomaarsen's post with ❤️ about 1 month ago

Post

6659

An assembly of 18 European companies, labs, and universities have banded together to launch 🇪🇺 EuroBERT! It's a state-of-the-art multilingual encoder for 15 European languages, designed to be finetuned for retrieval, classification, etc.

🇪🇺 15 Languages: English, French, German, Spanish, Chinese, Italian, Russian, Polish, Portuguese, Japanese, Vietnamese, Dutch, Arabic, Turkish, Hindi
3️⃣ 3 model sizes: 210M, 610M, and 2.1B parameters - very very useful sizes in my opinion
➡️ Sequence length of 8192 tokens! Nice to see these higher sequence lengths for encoders becoming more common.
⚙️ Architecture based on Llama, but with bi-directional (non-causal) attention to turn it into an encoder. Flash Attention 2 is supported.
🔥 A new Pareto frontier (stronger *and* smaller) for multilingual encoder models
📊 Evaluated against mDeBERTa, mGTE, XLM-RoBERTa for Retrieval, Classification, and Regression (after finetuning for each task separately): EuroBERT punches way above its weight.
📝 Detailed paper with all details, incl. data: FineWeb for English and CulturaX for multilingual data, The Stack v2 and Proof-Pile-2 for code.

Check out the release blogpost here: https://huggingface.co/blog/EuroBERT/release
* EuroBERT/EuroBERT-210m
* EuroBERT/EuroBERT-610m
* EuroBERT/EuroBERT-2.1B

The next step is for researchers to build upon the 3 EuroBERT base models and publish strong retrieval, zero-shot classification, etc. models for all to use. I'm very much looking forward to it!

1 reply

New activity in Undi95/MistralThinker-v1.1 about 2 months ago

This shit is fire

#2 opened about 2 months ago by

Ainonake

liked a model about 2 months ago

tencent/HunyuanVideo-I2V

Image-to-Video • Updated Mar 13 • 3.11k • 297

replied to Undi95's post about 2 months ago

Then what if we do the same, but put whole conversation in first user input?

So it will be
System prompt
User: conversation history
Then ask R1 to generate thinking.

And the amount of messages in conversation history should be varied. Then, Bot reply will always contain thinking.

replied to Undi95's post about 2 months ago

What do you think about doing part of the dataset with replies from some context?

E.g. we have e.g. 50% of data with thinking from first user answer, and some parts of dataset with

User,
Bot (no thinking),
User
Bot (no thinking),
User, N times,
Then ask R1 to think here and train on it. So the model will understand long context better.

reacted to Undi95's post with 👍 about 2 months ago

Post

6356

Hi there!

If you want to create your own thinking model or do a better MistralThinker, I just uploaded my entire dataset made on Deepseek R1 and the axolotl config. (well I made them public)

Axolotl config : Undi95/MistralThinker-v1.1

The dataset : Undi95/R1-RP-ShareGPT3

You can also read all I did on those two discord screenshot from two days ago, I'm a little lazy to rewrite all kek.

Hope you will use them!