Pathological Truth Bias in Vision-Language Models
Paper
•
2509.22674
•
Published
AI & ML interests
Open science and open source
thubZ9
authored
a
paper
3 months ago
osanseviero
authored
a
paper
3 months ago
ehristoforu
posted
an
update
4 months ago
Post
2292
🚀Hello from the Project Fluently team!
✨ We are happy to share with you our new universal LLM models based on Qwen3 1.7B and 4B — powerful, multilingual and ready to solve a wide range of problems!
🛠️ We have conducted additional training and carefully merged them to achieve even better results and maximize the potential of the models.
🆓 And most importantly — the models are completely open and free under the Apache-2.0 license!
🔗 Links to repositories:
- FluentlyQwen3-4B: fluently/FluentlyQwen3-4B
- FluentlyQwen3-1.7B: fluently/FluentlyQwen3-1.7B
😍 We will be very glad to hear your feedback and impressions! Your opinion is very important to us!
✨ We are happy to share with you our new universal LLM models based on Qwen3 1.7B and 4B — powerful, multilingual and ready to solve a wide range of problems!
🛠️ We have conducted additional training and carefully merged them to achieve even better results and maximize the potential of the models.
🆓 And most importantly — the models are completely open and free under the Apache-2.0 license!
🔗 Links to repositories:
- FluentlyQwen3-4B: fluently/FluentlyQwen3-4B
- FluentlyQwen3-1.7B: fluently/FluentlyQwen3-1.7B
😍 We will be very glad to hear your feedback and impressions! Your opinion is very important to us!
Post
4228
Hey all
Finally it's happening. DeepGit lite is back now, running on cpu only devices. Just smartly search across Github and spin up conversational agents in the background and have grounded conversation with repositories
Try it out now!!!! zamal/DeepGit
Finally it's happening. DeepGit lite is back now, running on cpu only devices. Just smartly search across Github and spin up conversational agents in the background and have grounded conversation with repositories
Try it out now!!!! zamal/DeepGit
- 1 reply
Post
1651
Say hallo to GermaNER 💪– a lightweight, high-accuracy NER model for German texts, powered by XLM-RoBERTa + LoRA adapters!
⚡ Fast, efficient, and open-source – perfect for tagging names, places & orgs in real-world German data.
Try it now on Hugging Face 👉 fau/GermaNER
⚡ Fast, efficient, and open-source – perfect for tagging names, places & orgs in real-world German data.
Try it now on Hugging Face 👉 fau/GermaNER
Post
4430
🚀 Videoxity is live on Hugging Face! 🎞️
A powerful, modular toolkit for intelligent video manipulation and scene editing.
With Videoxity, you can:
🖼️ Auto-caption keyframes with BLIP
🧠 Filter scenes using natural language (e.g. “remove dog scenes”)
✂️ Seamlessly trim videos with FFmpeg
📊 Generate frame-based summaries
Powered by Groq LLM + LangChain, OpenCV, BLIP, and SentenceTransformers, Videoxity bridges vision and language to give developers full control over video content.
🔧 Built for developers. Feedback welcome!
👉 Try it out here fau/videoxity
A powerful, modular toolkit for intelligent video manipulation and scene editing.
With Videoxity, you can:
🖼️ Auto-caption keyframes with BLIP
🧠 Filter scenes using natural language (e.g. “remove dog scenes”)
✂️ Seamlessly trim videos with FFmpeg
📊 Generate frame-based summaries
Powered by Groq LLM + LangChain, OpenCV, BLIP, and SentenceTransformers, Videoxity bridges vision and language to give developers full control over video content.
🔧 Built for developers. Feedback welcome!
👉 Try it out here fau/videoxity
Post
1996
🚀 DeepGit Lite is live! 🔍✨
Hey folks!
Just launched DeepGit Lite — a lighter version of DeepGit with fewer components under the hood.
It won’t perform quite like the full powerhouse, but it’s great for a quick peek and first-hand feel! ⚙️👀
Give it a spin and tell us what you think!
👉 Try it here https://huggingface.co/spaces/zamal/DeepGit-lite
#opensource #DeepGit #gradio #githubresearch
Hey folks!
Just launched DeepGit Lite — a lighter version of DeepGit with fewer components under the hood.
It won’t perform quite like the full powerhouse, but it’s great for a quick peek and first-hand feel! ⚙️👀
Give it a spin and tell us what you think!
👉 Try it here https://huggingface.co/spaces/zamal/DeepGit-lite
#opensource #DeepGit #gradio #githubresearch
- 3 replies
Post
2619
DeepGit: Your GitHub Gold Digger! 💰🚀
Hey Hugging Face gang! Meet DeepGit—my open-source sidekick that rips through GitHub to snag repos that fit you. Done with dead-end searches? Me too. Built it with LangGraph and some dope tricks:
Embeddings grab the good stuff (HF magic, baby!)
Re-ranking nails the best picks
Snoops docs, code, and buzz in one slick flow
Drops a clean list of hidden gems 💎
Unearth that sneaky ML lib or Python gem—run python app.py or langgraph dev and boom! Peek it at https://github.com/zamalali/DeepGit. Fork it, tweak it, love it—Docker’s in, HF vibes are strong. Drop a 🌟 or a crazy idea—I’m pumped to jam with you all! 🪂
Hey Hugging Face gang! Meet DeepGit—my open-source sidekick that rips through GitHub to snag repos that fit you. Done with dead-end searches? Me too. Built it with LangGraph and some dope tricks:
Embeddings grab the good stuff (HF magic, baby!)
Re-ranking nails the best picks
Snoops docs, code, and buzz in one slick flow
Drops a clean list of hidden gems 💎
Unearth that sneaky ML lib or Python gem—run python app.py or langgraph dev and boom! Peek it at https://github.com/zamalali/DeepGit. Fork it, tweak it, love it—Docker’s in, HF vibes are strong. Drop a 🌟 or a crazy idea—I’m pumped to jam with you all! 🪂
osanseviero
authored
a
paper
9 months ago
Post
2052
🚀 ftBoost is LIVE – Stop Struggling with Fine-Tuning Data!
Alright folks, if you’re tired of manually crafting fine-tuning datasets, ftBoost is here to do the heavy lifting. One-click, LangChain-Groq-powered data augmentation that scales your training data in OpenAI, Gemini, Mistral, and LLaMA formats—automatically.
🔥 What’s inside?
✅ Smart Augmentations – Paraphrasing, back translation, synonym swapping & synthetic noise.
✅ No more JSONL headaches – Auto-formats everything for OpenAI, Gemini, Mistral & LLaMA.
✅ Custom tuning – Adjust similarity, diversity, and fluency in real-time.
✅ Upload, generate, download – That’s it.
⚡ If you’re fine-tuning LLMs, this will save you hours.
🚀 Try it now: 👉 zamal/Finetune-Boost
🌟 Give us a star on GitHub!
Let me know what you think & how it boosts your workflow! 🔥
Alright folks, if you’re tired of manually crafting fine-tuning datasets, ftBoost is here to do the heavy lifting. One-click, LangChain-Groq-powered data augmentation that scales your training data in OpenAI, Gemini, Mistral, and LLaMA formats—automatically.
🔥 What’s inside?
✅ Smart Augmentations – Paraphrasing, back translation, synonym swapping & synthetic noise.
✅ No more JSONL headaches – Auto-formats everything for OpenAI, Gemini, Mistral & LLaMA.
✅ Custom tuning – Adjust similarity, diversity, and fluency in real-time.
✅ Upload, generate, download – That’s it.
⚡ If you’re fine-tuning LLMs, this will save you hours.
🚀 Try it now: 👉 zamal/Finetune-Boost
🌟 Give us a star on GitHub!
Let me know what you think & how it boosts your workflow! 🔥
ehristoforu
posted
an
update
10 months ago
Post
4105
Introducing our first standalone model – FluentlyLM Prinum
Introducing the first standalone model from Project Fluently LM! We worked on it for several months, used different approaches and eventually found the optimal one.
General characteristics:
- Model type: Causal language models (QwenForCausalLM, LM Transformer)
- Number of parameters: 32.5B
- Number of parameters (not embedded): 31.0B
- Number of layers: 64
- Context: 131,072 tokens
- Language(s) (NLP): English, French, Spanish, Russian, Chinese, Japanese, Persian (officially supported)
- License: MIT
Creation strategy:
The basis of the strategy is shown in Pic. 2.
We used Axolotl & Unsloth for SFT-finetuning with PEFT LoRA (rank=64, alpha=64) and Mergekit for SLERP and TIES mergers.
Evolution:
🏆 12th place in the Open LLM Leaderboard ( open-llm-leaderboard/open_llm_leaderboard) (21.02.2025)
Detailed results and comparisons are presented in Pic. 3.
Links:
- Model: https://huggingface.co/fluently-lm/FluentlyLM-Prinum
- GGUF version: mradermacher/FluentlyLM-Prinum-GGUF
- Demo on ZeroGPU: ehristoforu/FluentlyLM-Prinum-demo
Introducing the first standalone model from Project Fluently LM! We worked on it for several months, used different approaches and eventually found the optimal one.
General characteristics:
- Model type: Causal language models (QwenForCausalLM, LM Transformer)
- Number of parameters: 32.5B
- Number of parameters (not embedded): 31.0B
- Number of layers: 64
- Context: 131,072 tokens
- Language(s) (NLP): English, French, Spanish, Russian, Chinese, Japanese, Persian (officially supported)
- License: MIT
Creation strategy:
The basis of the strategy is shown in Pic. 2.
We used Axolotl & Unsloth for SFT-finetuning with PEFT LoRA (rank=64, alpha=64) and Mergekit for SLERP and TIES mergers.
Evolution:
🏆 12th place in the Open LLM Leaderboard ( open-llm-leaderboard/open_llm_leaderboard) (21.02.2025)
Detailed results and comparisons are presented in Pic. 3.
Links:
- Model: https://huggingface.co/fluently-lm/FluentlyLM-Prinum
- GGUF version: mradermacher/FluentlyLM-Prinum-GGUF
- Demo on ZeroGPU: ehristoforu/FluentlyLM-Prinum-demo
-
- 7 replies
Post
650
🚀 Try Out RAG Demo! 🚀
A Hugging Face Space where you can compare DeepSeek-R1 vs Llama-3 using Stuff RAG (Retrieval-Augmented Generation)!
🔍 Upload a PDF, ask questions, and see how both models perform in real-time!
Try out now:
zamal/Deepseek-R1-vs-LLama3
A Hugging Face Space where you can compare DeepSeek-R1 vs Llama-3 using Stuff RAG (Retrieval-Augmented Generation)!
🔍 Upload a PDF, ask questions, and see how both models perform in real-time!
Try out now:
zamal/Deepseek-R1-vs-LLama3
-
- 1 reply
Post
1522
zamal/Multimodal-Chat-PDF
🚀 Introducing Chat PDF Multimodal 💬
Interact with your PDF documents like never before! 🤯
Extract text & images, then ask context-aware questions based on both. Powered by RAG techniques & multimodal LLMs. Perfect for studying, research & more! 📝👀
Try it out now!!!! ✍️
#LlavaNext #MultimodalAI #Transformers
🚀 Introducing Chat PDF Multimodal 💬
Interact with your PDF documents like never before! 🤯
Extract text & images, then ask context-aware questions based on both. Powered by RAG techniques & multimodal LLMs. Perfect for studying, research & more! 📝👀
Try it out now!!!! ✍️
#LlavaNext #MultimodalAI #Transformers
ehristoforu
posted
an
update
about 1 year ago
Post
4652
✒️ Ultraset - all-in-one dataset for SFT training in Alpaca format.
fluently-sets/ultraset
❓ Ultraset is a comprehensive dataset for training Large Language Models (LLMs) using the SFT (instruction-based Fine-Tuning) method. This dataset consists of over 785 thousand entries in eight languages, including English, Russian, French, Italian, Spanish, German, Chinese, and Korean.
🤯 Ultraset solves the problem faced by users when selecting an appropriate dataset for LLM training. It combines various types of data required to enhance the model's skills in areas such as text writing and editing, mathematics, coding, biology, medicine, finance, and multilingualism.
🤗 For effective use of the dataset, it is recommended to utilize only the "instruction," "input," and "output" columns and train the model for 1-3 epochs. The dataset does not include DPO or Instruct data, making it suitable for training various types of LLM models.
❇️ Ultraset is an excellent tool to improve your language model's skills in diverse knowledge areas.
fluently-sets/ultraset
❓ Ultraset is a comprehensive dataset for training Large Language Models (LLMs) using the SFT (instruction-based Fine-Tuning) method. This dataset consists of over 785 thousand entries in eight languages, including English, Russian, French, Italian, Spanish, German, Chinese, and Korean.
🤯 Ultraset solves the problem faced by users when selecting an appropriate dataset for LLM training. It combines various types of data required to enhance the model's skills in areas such as text writing and editing, mathematics, coding, biology, medicine, finance, and multilingualism.
🤗 For effective use of the dataset, it is recommended to utilize only the "instruction," "input," and "output" columns and train the model for 1-3 epochs. The dataset does not include DPO or Instruct data, making it suitable for training various types of LLM models.
❇️ Ultraset is an excellent tool to improve your language model's skills in diverse knowledge areas.
Post
1864
🚀 Announcement for the Lovely community! 🚀
Just launched the zamal/DeepSeek-VL-1.3B-Chat on Hugging Face, and it's ready for YOU to explore! 💬🖼️
This full-fledged model is perfect for advanced image and text interactions, with zero GPU required. The Deepseek VL-1.3B Chat typically needs around 8 GB of VRAM and storage of almost 4 GB, but now you can experience it hassle-free right on our space!
Want something lighter? We’ve also uploaded a 4 bit quantized version (just around 1GB!), available on my profile. Perfect for those with limited hardware. 🌍🔍
Come try it now and see what this model can do! 🚀✨
Just launched the zamal/DeepSeek-VL-1.3B-Chat on Hugging Face, and it's ready for YOU to explore! 💬🖼️
This full-fledged model is perfect for advanced image and text interactions, with zero GPU required. The Deepseek VL-1.3B Chat typically needs around 8 GB of VRAM and storage of almost 4 GB, but now you can experience it hassle-free right on our space!
Want something lighter? We’ve also uploaded a 4 bit quantized version (just around 1GB!), available on my profile. Perfect for those with limited hardware. 🌍🔍
Come try it now and see what this model can do! 🚀✨
Post
2120
Hello, lovely community! 🌟
zamal/Molmo-4bit Thrilled to announce that the Molmo 7B 4-bit Space is now live! 🚀 The model size has been reduced by six times with almost no performance loss, and the results will leave you amazed!
It runs on zero GPU, making it incredibly accessible for everyone!
Check it out here and start exploring today!
Happy experimenting! 🎉
zamal/Molmo-4bit Thrilled to announce that the Molmo 7B 4-bit Space is now live! 🚀 The model size has been reduced by six times with almost no performance loss, and the results will leave you amazed!
It runs on zero GPU, making it incredibly accessible for everyone!
Check it out here and start exploring today!
Happy experimenting! 🎉
Post
1981
🚀 New Model Release: zamal/Molmo-7B-GPTQ-4bit 🚀
Hello lovely community,
zamal/Molmo-7B-GPTQ-4bit model is now available for all! This model has been highly quantized, reducing its size by almost six times. It now occupies significantly less space and vRAM, making it perfect for deployment on resource-constrained devices without compromising performance.
Now we get:
Efficient Performance: Maintains high accuracy while being highly quantized.
Reduced Size: The model size is reduced by nearly six times, optimizing storage and memory usage.
Versatile Application: Ideal for integrating a powerful visual language model into various projects particularly multi rag chains.
Check it out!
Hello lovely community,
zamal/Molmo-7B-GPTQ-4bit model is now available for all! This model has been highly quantized, reducing its size by almost six times. It now occupies significantly less space and vRAM, making it perfect for deployment on resource-constrained devices without compromising performance.
Now we get:
Efficient Performance: Maintains high accuracy while being highly quantized.
Reduced Size: The model size is reduced by nearly six times, optimizing storage and memory usage.
Versatile Application: Ideal for integrating a powerful visual language model into various projects particularly multi rag chains.
Check it out!
- 1 reply
Post
1534
i today make Shadow Chat, that make you can Chat with Shadow the Hedgehog (i was just bored, so i make this lol)
try it now in:
Hev832/Shadow_Chat
try it now in:
Hev832/Shadow_Chat
- 7 replies
ehristoforu
posted
an
update
over 1 year ago
Post
4596
😏 Hello from Project Fluently Team!
✨ Finally we can give you some details about Supple Diffusion. We worked on it for a long time and we have little left, we apologize that we had to increase the work time.
🛠️ Some technical information. The first version will be the Small version (there will also be Medium, Large, Huge, possibly Tiny), it will be based on the SD1 architecture, that is, one text encoder, U-net, VAE. Now about each component, the first is a text encoder, it will be a CLIP model (perhaps not CLIP-L-path14), CLIP was specially retrained by us in order to achieve the universality of the model in understanding completely different styles and to simplify the prompt as much as possible. Next, we did U-net, U-net in a rather complicated way, first we trained different parts (types) of data with different U-nets, then we carried out merging using different methods, then we trained DPO and SPO using methods, and then we looked at the remaining shortcomings and further trained model, details will come later. We left VAE the same as in SD1 architecture.
🙌 Compatibility. Another goal of the Supple model series is full compatibility with Auto1111 and ComfyUI already at the release stage, the model is fully supported by these interfaces and the diffusers library and does not require adaptation, your usual Sampling methods are also compatible, such as DPM++ 2M Karras, DPM++ SDE and others.
🧐 Today, without demo images (there wasn’t much time), final work is underway on the model and we are already preparing to develop the Medium version, the release of the Small version will most likely be in mid-August or earlier.
😻 Feel free to ask your questions in the comments below the post, we will be happy to answer them, have a nice day!
✨ Finally we can give you some details about Supple Diffusion. We worked on it for a long time and we have little left, we apologize that we had to increase the work time.
🛠️ Some technical information. The first version will be the Small version (there will also be Medium, Large, Huge, possibly Tiny), it will be based on the SD1 architecture, that is, one text encoder, U-net, VAE. Now about each component, the first is a text encoder, it will be a CLIP model (perhaps not CLIP-L-path14), CLIP was specially retrained by us in order to achieve the universality of the model in understanding completely different styles and to simplify the prompt as much as possible. Next, we did U-net, U-net in a rather complicated way, first we trained different parts (types) of data with different U-nets, then we carried out merging using different methods, then we trained DPO and SPO using methods, and then we looked at the remaining shortcomings and further trained model, details will come later. We left VAE the same as in SD1 architecture.
🙌 Compatibility. Another goal of the Supple model series is full compatibility with Auto1111 and ComfyUI already at the release stage, the model is fully supported by these interfaces and the diffusers library and does not require adaptation, your usual Sampling methods are also compatible, such as DPM++ 2M Karras, DPM++ SDE and others.
🧐 Today, without demo images (there wasn’t much time), final work is underway on the model and we are already preparing to develop the Medium version, the release of the Small version will most likely be in mid-August or earlier.
😻 Feel free to ask your questions in the comments below the post, we will be happy to answer them, have a nice day!
- 1 reply
Post
3901
Use GPT-4, GPT-4 Turbo Preview, GPT-3.5 Turbo, BingAI, and other models. The interface is similar to ChatGPT, with a speedy API endpoint.
https://huggingface.co/spaces/NiansuhAI/Copilot
https://huggingface.co/spaces/NiansuhAI/Copilot
- 4 replies