pseudolab (Pseudo Lab)

emre

posted an update about 3 hours ago

Post

87

having trouble with auto train
hello there this is the first time i am testing auto train with a 1.8k SFT dataset. Howevery i am not quite sure the training is going smooth. Logs seem quite confusing, token did not match can not auth, generates confusing train splits, do you know how i can check my running job properly?
what is being used for training as data?
any ideas?

Tonic

posted an update 17 days ago

Post

1147

🙋🏻‍♂️Hey there folks,

Did you know that you can use ModernBERT to detect model hallucinations ?

Check out the Demo : Tonic/hallucination-test

See here for Medical Context Demo : MultiTransformer/tonic-discharge-guard

check out the model from KRLabs : KRLabsOrg/lettucedect-large-modernbert-en-v1

and the library they kindly open sourced for it : https://github.com/KRLabsOrg/LettuceDetect

👆🏻if you like this topic please contribute code upstream 🚀

2 replies

·

Tonic

posted an update 18 days ago

Post

695

Powered by KRLabsOrg/lettucedect-large-modernbert-en-v1 from KRLabsOrg.

Detect hallucinations in answers based on context and questions using ModernBERT with 8192-token context support!

### Model Details
- **Model Name**: [lettucedect-large-modernbert-en-v1]( KRLabsOrg/lettucedect-large-modernbert-en-v1)
- **Organization**: [KRLabsOrg](https://huggingface.co/KRLabsOrg)
- **Github**: [https://github.com/KRLabsOrg/LettuceDetect](https://github.com/KRLabsOrg/LettuceDetect)
- **Architecture**: ModernBERT (Large) with extended context support up to 8192 tokens
- **Task**: Token Classification / Hallucination Detection
- **Training Dataset**: [RagTruth]( wandb/RAGTruth-processed)
- **Language**: English
- **Capabilities**: Detects hallucinated spans in answers, provides confidence scores, and calculates average confidence across detected spans.

LettuceDetect excels at processing long documents to determine if an answer aligns with the provided context, making it a powerful tool for ensuring factual accuracy.

Tonic

posted an update about 2 months ago

Post

2368

🙋🏻‍♂️hey there folks ,

Goedel's Theorem Prover is now being demo'ed on huggingface : Tonic/Math

give it a try !

Tonic

posted an update about 2 months ago

Post

2967

🙋🏻‍♂️ Hey there folks ,

our team made a game during the @mistral-game-jam and we're trying to win the community award !

try our game out and drop us a ❤️ like basically to vote for us !

Mistral-AI-Game-Jam/TextToSurvive

hope you like it !

Tonic

posted an update 2 months ago

Post

1893

🙋🏻‍♂️ Hey there folks ,

Facebook AI just released JASCO models that make music stems .

you can try it out here : Tonic/audiocraft

hope you like it

Tonic

posted an update 2 months ago

Post

2461

🙋🏻‍♂️Hey there folks , Open LLM Europe just released Lucie 7B-Instruct model , a billingual instruct model trained on open data ! You can check out my unofficial demo here while we wait for the official inference api from the group : Tonic/Lucie-7B hope you like it 🚀

Tonic

posted an update 2 months ago

Post

1721

microsoft just released Phi-4 , check it out here : Tonic/Phi-4

hope you like it :-)

peaceAsh

authored a paper 3 months ago

Maya: An Instruction Finetuned Multilingual Multimodal Model

Paper • 2412.07112 • Published Dec 10, 2024 • 27

scottsuk0306

authored a paper 4 months ago

Evaluating Language Models as Synthetic Data Generators

Paper • 2412.03679 • Published Dec 4, 2024 • 48

lunarflu

posted an update 4 months ago

Post

1863

great blogpost! 🔥@wolfram
https://huggingface.co/blog/wolfram/llm-comparison-test-2024-12-04

kinam0252

authored a paper 4 months ago

Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling

Paper • 2411.18664 • Published Nov 27, 2024 • 24

Tonic

posted an update 5 months ago

Post

3585

🙋🏻‍♂️hey there folks,

periodic reminder : if you are experiencing ⚠️500 errors ⚠️ or ⚠️ abnormal spaces behavior on load or launch ⚠️

we have a thread 👉🏻 https://discord.com/channels/879548962464493619/1295847667515129877

if you can record the problem and share it there , or on the forums in your own post , please dont be shy because i'm not sure but i do think it helps 🤗🤗🤗

2 replies

·

Tonic

posted an update 5 months ago

Post

1184

boomers still pick zenodo.org instead of huggingface ??? absolutely clownish nonsense , my random datasets have 30x more downloads and views than front page zenodos ... gonna write a comparison blog , but yeah... cringe.

1 reply

·

Tonic

posted an update 5 months ago

Post

856

🙋🏻‍♂️ hey there folks ,

really enjoying sharing cool genomics and protein datasets on the hub these days , check out our cool new org : https://huggingface.co/seq-to-pheno

scroll down for the datasets, still figuring out how to optimize for discoverability , i do think on that part it will be better than zenodo[dot}org , it would be nice to write a tutorial about that and compare : we already have more downloads than most zenodo datasets from famous researchers !

Tonic

posted an update 5 months ago

Post

1476

hey there folks,

twitter is aweful isnt it ? just getting into the habbit of using hf/posts for shares 🦙🦙

Tonic/on-device-granite-3.0-1b-a400m-instruct

new granite on device instruct model demo , hope you like it 🚀🚀

Tonic

posted an update 5 months ago

Post

1016

if you're encountering 500 errors on spaces that seem to work otherwise , kindly consider screenshotting and sharing the link here : https://discord.com/channels/879548962464493619/1295847667515129877

7 replies

·

Tonic

posted an update 6 months ago

Post

2758

🙋🏻‍♂️hey there folks ,

did you know that https://huggingface.co/lmms-lab released a new version of 🌋🌋Llava on thursday ? Now it has 🎥video understanding !
check it out 👇🏻

collection : lmms-lab/llava-video-661e86f5e8dabc3ff793c944
demo : Tonic/Llava-Video

Tonic

posted an update 6 months ago

Post

1869

🙋🏻‍♂️ Hey there folks ,

🦎Salamandra release by @mvillegas and team
@BSC_CNS https://huggingface.co/BSC-LT is absolutely impressive so far !

perhaps the largest single training dataset of high quality text to date of 7.8 trillion tokens in 35 European languages and code.

the best part : the data was correctly licenced so it's actually future-proof!

the completions model is really creative and instruct fine tuned version is very good also.

now you can use such models for multi-lingual enterprise applications with further finetunes , long response generation, structured outputs (coding) also works.

check out 👇🏻
the collection : BSC-LT/salamandra-66fc171485944df79469043a
the repo : https://github.com/langtech-bsc/salamandra
7B-Instruct demo : Tonic/Salamandra-7B

Tonic

posted an update 6 months ago

Post

1794

@mlabonne hey there 🙋🏻‍♂️ I kinda got obsessed with your great model , and i found the endpoint for it in lambda labs, but basically i got rate limited / banned for trying to make my DPO dataset project, i was wondering if you all had an open ai compatible solution for me to make a great "thinking" sft + dpo dataset with all the splits 🙏🏻🙏🏻 kinda desparate , it's true , but was looking forward to a nice write ups 🚀🚀🚀

1 reply

·

Pseudo Lab

AI & ML interests

pseudolab's activity

Maya: An Instruction Finetuned Multilingual Multimodal Model

Evaluating Language Models as Synthetic Data Generators

Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling

AI & ML interests

Team members 57

pseudolab's activity