Thanks
@nicolay-r
π€
The tiny transformers are used in production every day! π₯
Maziyar Panahi PRO
MaziyarPanahi
shafiqalibhai's profile picture
k3ybladewielder's profile picture
interstellarninja's profile picture
Β·
AI & ML interests
RLHF, RL, Model Merging, Quantizations, Synthetic datasets, Health x AI
Recent Activity
liked
a model
about 20 hours ago
OpenMed/OpenMed-NER-GenomeDetect-SuperClinical-434M
liked
a model
2 days ago
OpenMed/OpenMed-NER-BloodCancerDetect-BigMed-278M
liked
a model
2 days ago
OpenMed/OpenMed-NER-PathologyDetect-BigMed-278M
Organizations
replied to
their
post
7 days ago
posted
an
update
7 days ago
Post
6933
𧬠Breaking news in Clinical AI: Introducing the OpenMed NER Model Discovery App on Hugging Face π¬
OpenMed is back! π₯ Finding the right biomedical NER model just became as precise as a PCR assay!
I'm thrilled to unveil my comprehensive OpenMed Named Entity Recognition Model Discovery App that puts 384 specialized biomedical AI models at your fingertips.
π― Why This Matters in Healthcare AI:
Traditional clinical text mining required hours of manual model evaluation. My Discovery App instantly connects researchers, clinicians, and data scientists with the exact NER models they need for their biomedical entity extraction tasks.
π¬ What You Can Discover:
β Pharmacological Models - Extract "chemical compounds", "drug interactions", and "pharmaceutical" entities from clinical notes
β Genomics & Proteomics - Identify "DNA sequences", "RNA transcripts", "gene variants", "protein complexes", and "cell lines"
β Pathology & Disease Detection - Recognize "pathological formations", "cancer types", and "disease entities" in medical literature
β Anatomical Recognition - Map "anatomical systems", "tissue types", "organ structures", and "cellular components"
β Clinical Entity Extraction - Detect "organism species", "amino acids", 'protein families", and "multi-tissue structures"
π‘ Advanced Features:
π Intelligent Entity Search - Find models by specific biomedical entities (e.g., "Show me models detecting CHEM + DNA + Protein")
π₯ Domain-Specific Filtering - Browse by Oncology, Pharmacology, Genomics, Pathology, Hematology, and more
π Model Architecture Insights - Compare BERT, RoBERTa, and DeBERTa implementations
β‘ Real-Time Search - Auto-filtering as you type, no search buttons needed
π¨ Clinical-Grade UI - Beautiful, intuitive interface designed for medical professionals
Ready to revolutionize your biomedical NLP pipeline?
π Try it now: OpenMed/openmed-ner-models
𧬠Built with: Gradio, Transformers, Advanced Entity Mapping
OpenMed is back! π₯ Finding the right biomedical NER model just became as precise as a PCR assay!
I'm thrilled to unveil my comprehensive OpenMed Named Entity Recognition Model Discovery App that puts 384 specialized biomedical AI models at your fingertips.
π― Why This Matters in Healthcare AI:
Traditional clinical text mining required hours of manual model evaluation. My Discovery App instantly connects researchers, clinicians, and data scientists with the exact NER models they need for their biomedical entity extraction tasks.
π¬ What You Can Discover:
β Pharmacological Models - Extract "chemical compounds", "drug interactions", and "pharmaceutical" entities from clinical notes
β Genomics & Proteomics - Identify "DNA sequences", "RNA transcripts", "gene variants", "protein complexes", and "cell lines"
β Pathology & Disease Detection - Recognize "pathological formations", "cancer types", and "disease entities" in medical literature
β Anatomical Recognition - Map "anatomical systems", "tissue types", "organ structures", and "cellular components"
β Clinical Entity Extraction - Detect "organism species", "amino acids", 'protein families", and "multi-tissue structures"
π‘ Advanced Features:
π Intelligent Entity Search - Find models by specific biomedical entities (e.g., "Show me models detecting CHEM + DNA + Protein")
π₯ Domain-Specific Filtering - Browse by Oncology, Pharmacology, Genomics, Pathology, Hematology, and more
π Model Architecture Insights - Compare BERT, RoBERTa, and DeBERTa implementations
β‘ Real-Time Search - Auto-filtering as you type, no search buttons needed
π¨ Clinical-Grade UI - Beautiful, intuitive interface designed for medical professionals
Ready to revolutionize your biomedical NLP pipeline?
π Try it now: OpenMed/openmed-ner-models
𧬠Built with: Gradio, Transformers, Advanced Entity Mapping
-
- 5 replies
reacted to
prithivMLmods's
post with π
3 months ago
Post
3576
Dropping some image classification models for content moderation, balancers, and classifiers trained on synthetic datasetsβalong with others based on datasets available on the Hub. Also loaded a few low-rank datasets for realistic gender portrait classification and document-type classifiers, all fine-tuned on the SigLIP-2 Patch-16 224 backbone. Models and datasets are listed below:
π€Models & Datasets :
Realistic Gender Classification : prithivMLmods/Realistic-Gender-Classification
β prithivMLmods/Realistic-Portrait-Gender-1024px
Document Type Detection : prithivMLmods/Document-Type-Detection
β prithivMLmods/Document-Type-Detection
Face Mask Detection : prithivMLmods/Face-Mask-Detection
β DamarJati/Face-Mask-Detection
Alzheimer Stage Classifier : prithivMLmods/Alzheimer-Stage-Classifier
β SilpaCS/Augmented_alzheimer
Bone Fracture Detection : prithivMLmods/Bone-Fracture-Detection
β Hemg/bone-fracture-detection
GiD Land Cover Classification : prithivMLmods/GiD-Land-Cover-Classification
β jonathan-roberts1/GID
π€Collection : prithivMLmods/siglip2-05102025-681c2b0e406f0740a993fc1c
To know more about it, visit the model card of the respective model.
π€Models & Datasets :
Realistic Gender Classification : prithivMLmods/Realistic-Gender-Classification
β prithivMLmods/Realistic-Portrait-Gender-1024px
Document Type Detection : prithivMLmods/Document-Type-Detection
β prithivMLmods/Document-Type-Detection
Face Mask Detection : prithivMLmods/Face-Mask-Detection
β DamarJati/Face-Mask-Detection
Alzheimer Stage Classifier : prithivMLmods/Alzheimer-Stage-Classifier
β SilpaCS/Augmented_alzheimer
Bone Fracture Detection : prithivMLmods/Bone-Fracture-Detection
β Hemg/bone-fracture-detection
GiD Land Cover Classification : prithivMLmods/GiD-Land-Cover-Classification
β jonathan-roberts1/GID
π€Collection : prithivMLmods/siglip2-05102025-681c2b0e406f0740a993fc1c
To know more about it, visit the model card of the respective model.
replied to
sometimesanotion's
post
5 months ago
I am a fan of @jpacifico models! π₯
replied to
sometimesanotion's
post
5 months ago
Beautiful work! π€©
reacted to
sometimesanotion's
post with π₯βπ₯π
5 months ago
Post
4965
I'd like to draw your attention to a Lamarck-based experiment which uses Arcee AI's newly published arcee_fusion merge method for three out of its four merges. Yes, just four. This is a simple one, and its recipe is fully open:
sometimesanotion/Lamarck-14B-v0.7-Fusion
It unifies three branches, all of which feature models which bring Lamarck-14B-v0.7 and Qwenvergence-14B-v12-Prose together. One side features @jpacifico 's jpacifico/Chocolatine-2-14B-Instruct-v2.0.3 and the other features @suayptalha 's suayptalha/Lamarckvergence-14B paired with my models which were their merge ancestors.
A fusion merge - of a fusion merge and a SLERP of a fusion and older merge - should demonstrate the new merge method's behavior in interesting ways, especially in the first 1/4th of the model where the SLERP has less impact.
I welcome you to kick the tires and learn from it. It has prose quality near Qwenvergence v12's - as you'd expect.
Thank you, @mradermacher and @MaziyarPanahi , for the first-day quantizations! Your work helped get me started. https://huggingface.co/models?other=base_model:quantized:sometimesanotion/Lamarck-14B-v0.7-Fusion
sometimesanotion/Lamarck-14B-v0.7-Fusion
It unifies three branches, all of which feature models which bring Lamarck-14B-v0.7 and Qwenvergence-14B-v12-Prose together. One side features @jpacifico 's jpacifico/Chocolatine-2-14B-Instruct-v2.0.3 and the other features @suayptalha 's suayptalha/Lamarckvergence-14B paired with my models which were their merge ancestors.
A fusion merge - of a fusion merge and a SLERP of a fusion and older merge - should demonstrate the new merge method's behavior in interesting ways, especially in the first 1/4th of the model where the SLERP has less impact.
I welcome you to kick the tires and learn from it. It has prose quality near Qwenvergence v12's - as you'd expect.
Thank you, @mradermacher and @MaziyarPanahi , for the first-day quantizations! Your work helped get me started. https://huggingface.co/models?other=base_model:quantized:sometimesanotion/Lamarck-14B-v0.7-Fusion
-
- 10 replies
reacted to
ngxson's
post with π₯
6 months ago
Post
3728
Check out my collection of pre-made GGUF LoRA adapters!
This allow you to use both normal + abliterated version of popular models like llama, qwen, etc, without having to double to amount of VRAM usage.
ngxson/gguf_lora_collection
This allow you to use both normal + abliterated version of popular models like llama, qwen, etc, without having to double to amount of VRAM usage.
ngxson/gguf_lora_collection
-
- 5 replies
This is super cool!!! Would you mind sharing the process of these GGUF LoRA adapters? Did you convert the LoRA into GGUF or made LoRA from the GGUF itself?
reacted to
malhajar's
post with π₯β€οΈ
9 months ago
Post
5233
π«π· Lancement officiel de l'OpenLLM French Leaderboard : initiative open-source pour rΓ©fΓ©rencer lβΓ©valuation des LLMs francophones
AprΓ¨s beaucoup dβefforts et de sueurs avec Alexandre Lavallee, nous sommes ravis dβannoncer que le OpenLLMFrenchLeaderboard est en ligne sur Hugging Face (space url: le-leadboard/OpenLLMFrenchLeaderboard) la toute premiΓ¨re plateforme dΓ©diΓ©e Γ lβΓ©valuation des grands modΓ¨les de langage (LLM) en franΓ§ais. π«π·β¨
Ce projet de longue haleine est avant tout une Εuvre de passion mais surtout une nΓ©cessitΓ© absolue. Il devient urgent et vital d'oeuvrer Γ plus de transparence dans ce domaine stratΓ©gique des LLM dits multilingues. La premiΓ¨re piΓ¨ce Γ l'Γ©difice est donc la mise en place d'une Γ©valuation systΓ©matique et systΓ©mique des modΓ¨les actuels et futurs.
Votre modΓ¨le IA franΓ§ais est-il prΓͺt Γ se dΓ©marquer ? Soumettez le dans notre espace, et voyez comment vous vous comparez par rapport aux autres modΓ¨les.
β Comment Γ§a marche :
Soumettez votre LLM franΓ§ais pour Γ©valuation, et nous le testerons sur des benchmarks de rΓ©fΓ©rence spΓ©cifiquement adaptΓ©s pour la langue franΓ§aise β notre suite de benchmarks comprend :
- BBH-fr : Raisonnement complexe
- IFEval-fr : Suivi d'instructions
- GPQA-fr : Connaissances avancΓ©es
- MUSR-fr : Raisonnement narratif
- MATH_LVL5-fr : CapacitΓ©s mathΓ©matiques
- MMMLU-fr : ComprΓ©hension multitΓ’che
Le processus est encore manuel, mais nous travaillons sur son automatisation, avec le soutien de la communautΓ© Hugging Face.
@clem , on se prΓ©pare pour une mise Γ niveau de lβespace ? ππ
Ce n'est pas qu'une question de chiffresβil s'agit de crΓ©er une IA qui reflΓ¨te vraiment notre langue, notre culture et nos valeurs. OpenLLMFrenchLeaderboard est notre contribution personnelle pour faΓ§onner l'avenir des LLM en France.
AprΓ¨s beaucoup dβefforts et de sueurs avec Alexandre Lavallee, nous sommes ravis dβannoncer que le OpenLLMFrenchLeaderboard est en ligne sur Hugging Face (space url: le-leadboard/OpenLLMFrenchLeaderboard) la toute premiΓ¨re plateforme dΓ©diΓ©e Γ lβΓ©valuation des grands modΓ¨les de langage (LLM) en franΓ§ais. π«π·β¨
Ce projet de longue haleine est avant tout une Εuvre de passion mais surtout une nΓ©cessitΓ© absolue. Il devient urgent et vital d'oeuvrer Γ plus de transparence dans ce domaine stratΓ©gique des LLM dits multilingues. La premiΓ¨re piΓ¨ce Γ l'Γ©difice est donc la mise en place d'une Γ©valuation systΓ©matique et systΓ©mique des modΓ¨les actuels et futurs.
Votre modΓ¨le IA franΓ§ais est-il prΓͺt Γ se dΓ©marquer ? Soumettez le dans notre espace, et voyez comment vous vous comparez par rapport aux autres modΓ¨les.
β Comment Γ§a marche :
Soumettez votre LLM franΓ§ais pour Γ©valuation, et nous le testerons sur des benchmarks de rΓ©fΓ©rence spΓ©cifiquement adaptΓ©s pour la langue franΓ§aise β notre suite de benchmarks comprend :
- BBH-fr : Raisonnement complexe
- IFEval-fr : Suivi d'instructions
- GPQA-fr : Connaissances avancΓ©es
- MUSR-fr : Raisonnement narratif
- MATH_LVL5-fr : CapacitΓ©s mathΓ©matiques
- MMMLU-fr : ComprΓ©hension multitΓ’che
Le processus est encore manuel, mais nous travaillons sur son automatisation, avec le soutien de la communautΓ© Hugging Face.
@clem , on se prΓ©pare pour une mise Γ niveau de lβespace ? ππ
Ce n'est pas qu'une question de chiffresβil s'agit de crΓ©er une IA qui reflΓ¨te vraiment notre langue, notre culture et nos valeurs. OpenLLMFrenchLeaderboard est notre contribution personnelle pour faΓ§onner l'avenir des LLM en France.
- 1 reply
reacted to
MonsterMMORPG's
post with π₯π
10 months ago
Post
3011
Detailed Comparison of JoyCaption Alpha One vs JoyCaption Pre-Alpha β 10 Different Style Amazing Images β I think JoyCaption Alpha One is the very best image captioning model at the moment for model training β Works very fast and requires as low as 8.5 GB VRAM
Where To Download And Install
You can download our APP from here : https://www.patreon.com/posts/110613301
1-Click to install on Windows, RunPod and Massed Compute
Official APP is here where you can try : fancyfeast/joy-caption-alpha-one
Have The Following Features
Auto downloads meta-llama/Meta-Llama-3.1β8B into your Hugging Face cache folder and other necessary models into the installation folder
Use 4-bit quantization β Uses 8.5 GB VRAM Total
Overwrite existing caption file
Append new caption to existing caption
Remove newlines from generated captions
Cut off at last complete sentence
Discard repeating sentences
Donβt save processed image
Caption Prefix
Caption Suffix
Custom System Prompt (Optional)
Input Folder for Batch Processing
Output Folder for Batch Processing (Optional)
Fully supported Multi GPU captioning β GPU IDs (comma-separated, e.g., 0,1,2)
Batch Size β Batch captioning
Where To Download And Install
You can download our APP from here : https://www.patreon.com/posts/110613301
1-Click to install on Windows, RunPod and Massed Compute
Official APP is here where you can try : fancyfeast/joy-caption-alpha-one
Have The Following Features
Auto downloads meta-llama/Meta-Llama-3.1β8B into your Hugging Face cache folder and other necessary models into the installation folder
Use 4-bit quantization β Uses 8.5 GB VRAM Total
Overwrite existing caption file
Append new caption to existing caption
Remove newlines from generated captions
Cut off at last complete sentence
Discard repeating sentences
Donβt save processed image
Caption Prefix
Caption Suffix
Custom System Prompt (Optional)
Input Folder for Batch Processing
Output Folder for Batch Processing (Optional)
Fully supported Multi GPU captioning β GPU IDs (comma-separated, e.g., 0,1,2)
Batch Size β Batch captioning
reacted to
bartowski's
post with π₯πβ€οΈ
11 months ago
Post
35032
Reposting from twitter:
Just so you all know, I'll be on vacation for the following two weeks and away from home! I'm hoping to get on at least once a day to load up some quants, but I won't be as bleeding edge and on the ball :) feel free to shoot me a message if you see one I should make!
In the meantime if you need something bleeding edge make sure to check out @MaziyarPanahi or @bullerwins who both put out great work!
Just so you all know, I'll be on vacation for the following two weeks and away from home! I'm hoping to get on at least once a day to load up some quants, but I won't be as bleeding edge and on the ball :) feel free to shoot me a message if you see one I should make!
In the meantime if you need something bleeding edge make sure to check out @MaziyarPanahi or @bullerwins who both put out great work!
- 4 replies
reacted to
clem's
post with π₯
11 months ago
Post
1558
Shoutout to everyone who participated in BigScience! Doesn't get enough credit but IMO paved the way for open-source LLMs!
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model (2211.05100)
bigscience/bloom
bigscience/bloomz
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model (2211.05100)
bigscience/bloom
bigscience/bloomz
Thanks @bartowski for breaking this down! :)