Csplk (Ci Splunk)

reacted to csabakecskemeti's post with 👍 3 days ago

Post

1187

Some time ago, I built a predictive LLM router that routes chat requests between small and large LLM models based on prompt classification. It dynamically selects the most suitable model depending on the complexity of the user input, ensuring optimal performance while maintaining conversation context. I also fine-tuned a RoBERTa model to use with the package, but you can plug and play any classifier of your choice.

Project's homepage:
https://devquasar.com/llm-predictive-router/
Pypi:
https://pypi.org/project/llm-predictive-router/
Model:
DevQuasar/roberta-prompt_classifier-v0.1
Training data:
DevQuasar/llm_router_dataset-synth
Git:
https://github.com/csabakecskemeti/llm_predictive_router_package

Feel free to check it out, and/or contribute.

replied to prithivMLmods's post 4 days ago

You really have been bringing the goodies lately (formerly too!) thanks !

reacted to prithivMLmods's post with ❤️ 4 days ago

Post

3832

Minimalistic Adapters 🎃

🚀Demo Here:
prithivMLmods/FLUX-LoRA-DLC

🚀Model:
{ Quote Tuner } : prithivMLmods/Flux.1-Dev-Quote-LoRA
{ Stamp Art } : prithivMLmods/Flux.1-Dev-Stamp-Art-LoRA
{ Hand Sticky } : prithivMLmods/Flux.1-Dev-Hand-Sticky-LoRA
{ Poster HQ } : prithivMLmods/Flux.1-Dev-Poster-HQ-LoRA
{ Ctoon Min } : prithivMLmods/Flux.1-Dev-Ctoon-LoRA

🚀Collection:
{ Flux LoRA Collection} : prithivMLmods/flux-lora-collections-66dd5908be2206cfaa8519be
{ LoRA Space Collection } : prithivMLmods/lora-space-collections-6714b72e0d49e1c97fbd6a32

🚀For More Visit
https://huggingface.co/strangerzonehf
.
.
.
🤗@prithivMLmods

3 replies

·

reacted to merve's post with 🔥👀 4 days ago

Post

4640

OmniVision-968M: a new local VLM for edge devices, fast & small but performant
💨 a new vision language model with 9x less image tokens, super efficient
📖 aligned with DPO for reducing hallucinations
⚡️ Apache 2.0 license 🔥

Demo hf.co/spaces/NexaAIDev/omnivlm-dpo-demo
Model NexaAIDev/omnivision-968M

4 replies

·

reacted to cfahlgren1's post with 🔥 5 days ago

Post

2190

Why use Google Drive when you can have:

• Free storage with generous limits🆓
• Dataset Viewer (Sorting, Filtering, FTS) 🔍
• Third Party Library Support
• SQL Console 🟧
• Security 🔒
• Community, Reach, and Visibility 📈

It's a no brainer!

Check out our post on what you get instantly out of the box when you create a dataset.
https://huggingface.co/blog/researcher-dataset-sharing

1 reply

·

reacted to merve's post with ❤️ 5 days ago

Post

1919

Amazing past days at open ML, it's raining coding models, let's have a recap 🌧️ Find all models and datasets here merve/nov-15-releases-67372d0ebdc354756a52ecd0

Models
💻 Coding: Qwen team released two Qwen2.5-Coder checkpoints of 32B and 7B. Infly released OpenCoder: 1.5B and 8B coding models with instruction SFT'd versions and their datasets! 💗

🖼️ Image/Video Gen: Alibaba vision lab released In-context LoRA -- 10 LoRA models on different themes based on Flux. Also Mochi the sota video generation model with A2.0 license now comes natively supported in diffusers 👏

🖼️ VLMs/Multimodal: NexaAIDev released Omnivision 968M a new vision language model aligned with DPO for reducing hallucinations, also comes with GGUF ckpts 👏 Microsoft released LLM2CLIP, a new CLIP-like model with longer context window allowing complex text inputs and better search

🎮 AGI?: Etched released Oasis 500M, a diffusion based open world model that takes keyboard input and outputs gameplay 🤯

Datasets
Common Corpus: A text dataset with 2T tokens with permissive license for EN/FR on various sources: code, science, finance, culture 📖

reacted to chansung's post with 🔥 5 days ago

Post

1596

🎙️ Listen to the audio "Podcast" of every single Hugging Face Daily Papers.

Now, "AI Paper Reviewer" project can automatically generates audio podcasts on any papers published on arXiv, and this is integrated into the GitHub Action pipeline. I sounds pretty similar to hashtag#NotebookLM in my opinion.

🎙️ Try out yourself at https://deep-diver.github.io/ai-paper-reviewer/

This audio podcast is powered by Google technologies: 1) Google DeepMind Gemini 1.5 Flash model to generate scripts of a podcast, then 2) Google Cloud Vertex AI's Text to Speech model to synthesize the voice turning the scripts into the natural sounding voices (with latest addition of "Journey" voice style)

"AI Paper Reviewer" is also an open source project. Anyone can use it to build and own a personal blog on any papers of your interests. Hence, checkout the project repository below if you are interested in!
: https://github.com/deep-diver/paper-reviewer

This project is going to support other models including open weights soon for both text-based content generation and voice synthesis for the podcast. The only reason I chose Gemini model is that it offers a "free-tier" which is enough to shape up this projects with non-realtime batch generations. I'm excited to see how others will use this tool to explore the world of AI research, hence feel free to share your feedback and suggestions!

1 reply

·

reacted to abhishek's post with 🔥 13 days ago

Post

4955

INTRODUCING Hugging Face AutoTrain Client 🔥
Fine-tuning models got even easier!!!!
Now you can fine-tune SOTA models on all compatible dataset-model pairs on Hugging Face Hub using Python on Hugging Face Servers. Choose from a number of GPU flavors, millions of models and dataset pairs and 10+ tasks 🤗

To try, install autotrain-advanced using pip. You can ignore dependencies and install without --no-deps and then you'd need to install some dependencies by hand.

"pip install autotrain-advanced"

Github repo: https://github.com/huggingface/autotrain-advanced

6 replies

·

reacted to prithivMLmods's post with 🧠 14 days ago

Post

4611

Quintet Drop : : 🤗

{ Flux LoRA DLC ⛵ } : prithivMLmods/FLUX-LoRA-DLC

-- Purple Dreamy
{ pop of color } : prithivMLmods/Purple-Dreamy-Flux-LoRA

-- Golden Dust
{ shimmer contrast } : prithivMLmods/Golden-Dust-Flux-LoRA

-- Lime Green
{ depth to the composition } : prithivMLmods/Lime-Green-Flux-LoRA

-- Flare Strike
{ Fractured Line } : prithivMLmods/Fractured-Line-Flare

-- Orange Chroma
{ studio lighting } : prithivMLmods/Orange-Chroma-Flux-LoRA
.
.
.
{ collection } : prithivMLmods/flux-lora-collections-66dd5908be2206cfaa8519be

@prithivMLmods

replied to qq8933's post 15 days ago

For users with Chinese IP addresses, consider adding this URL to the rules of your U.S. node, as the response headers from this site will report the user's physical location to GPT.

Interested in what this means, can you say more about this part on Chinese IPs?

reacted to qq8933's post with 👍 15 days ago

Post

2269

Discovered an outrageous bug on the ChatGPT official website, especially for those using ad-blocking plugins. Please make sure to add browser-intake-datadoghq.com to your ad block whitelist. The ChatGPT webpage relies on this site for heartbeat detection, but since it belongs to an ad tracking network, it's included in major ad-blocking lists. (If you're using Clash, also remember to add it to the whitelist.) Failing to do so may cause the ChatGPT web interface to display a greyed-out send button after clicking, with no response.

For users with Chinese IP addresses, consider adding this URL to the rules of your U.S. node, as the response headers from this site will report the user's physical location to GPT.

3 replies

·

replied to qq8933's post 15 days ago

I propose another potential solution: stop using chatgpt.com and instead use hf.co/chat :)

If anyone thinks they can’t use this alternative solution and must use chatgpt for what they use it for then please share the details of what it is doing for you that you are unable to do with hugging face chat or maybe have not heard of hugging face chat so the community can help you out with how it most likely actually can do such things so you can free yourself from the closedAI shackles. :)

reacted to merve's post with 🚀 25 days ago

Post

3447

Microsoft released a groundbreaking model that can be used for web automation, with MIT license 🔥 microsoft/OmniParser

Interesting highlight for me was Mind2Web (a benchmark for web navigation) capabilities of the model, which unlocks agentic behavior for RPA agents.

no need for hefty web automation pipelines that get broken when the website/app design changes! Amazing work.

Lastly, the authors also fine-tune this model on open-set detection for interactable regions and see if they can use it as a plug-in for VLMs and it actually outperforms off-the-shelf open-set detectors like GroundingDINO. 👏

OmniParser is a state-of-the-art UI parsing/understanding model that outperforms GPT4V in parsing.

replied to DeFactOfficial's post about 1 month ago

Its so fast! Great work

reacted to merve's post with 🚀 about 1 month ago

Post

2836

This is not a drill 💥
HuggingChat is now multimodal with meta-llama/Llama-3.2-11B-Vision-Instruct! 🤗
This also comes with multimodal assistants, I have migrated my Marcus Aurelius advice assistant to Llama-Vision and Marcus can see now! 😄

Chat with Marcus: https://hf.co/chat/assistant/65bfed22022ba290531112f8
Start chatting with Llama-Vision 3.2 11B Instruct https://huggingface.co/chat/models/meta-llama/Llama-3.2-11B-Vision-Instruct

1 reply

·

reacted to abidlabs's post with ❤️ about 2 months ago

Post

4185

👋 Hi Gradio community,

I'm excited to share that Gradio 5 will launch in October with improvements across security, performance, SEO, design (see the screenshot for Gradio 4 vs. Gradio 5), and user experience, making Gradio a mature framework for web-based ML applications.

Gradio 5 is currently in beta, so if you'd like to try it out early, please refer to the instructions below:

---------- Installation -------------

Gradio 5 depends on Python 3.10 or higher, so if you are running Gradio locally, please ensure that you have Python 3.10 or higher, or download it here: https://www.python.org/downloads/

* Locally: If you are running gradio locally, simply install the release candidate with pip install gradio --pre
* Spaces: If you would like to update an existing gradio Space to use Gradio 5, you can simply update the sdk_version to be 5.0.0b3 in the README.md file on Spaces.

In most cases, that’s all you have to do to run Gradio 5.0. If you start your Gradio application, you should see your Gradio app running, with a fresh new UI.

-----------------------------

Fore more information, please see: https://github.com/gradio-app/gradio/issues/9463

2 replies

·

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

Post

2357

📝 I wrote a tutorial on how to get started with the fine-tuning process using Hugging Face tools, providing an end-to-end workflow.

The tutorial covers creating a new dataset using the new SQL Console 🛢 and fine-tuning a model with SFT, guided by the Notebook Creator App 📙.

👉 You can read the full article here:
https://huggingface.co/blog/asoria/easy-fine-tuning-with-hf
asoria/auto-notebook-creator

reacted to davanstrien's post with ❤️ about 2 months ago

Post

2181

Yesterday, I shared a blog post on generating data for fine-tuning ColPali using the Qwen/Qwen2-VL-7B-Instruct model.

To simplify testing this approach, I created a Space that lets you generate queries from an input document page image: davanstrien/ColPali-Query-Generator

I think there is much room for improvement, but I'm excited about the potential for relatively small VLMs to create synthetic data.

You can read the original blog post that goes into more detail here: https://danielvanstrien.xyz/posts/post-with-code/colpali/2024-09-23-generate_colpali_dataset.html

replied to davidberenstein1957's post about 2 months ago

This gives me the feeling that this will be one one of those "Was there a time before...I can’t recall the time before..." based novelty acceleration tool. Amazingly useful.

Ci Splunk PRO

AI & ML interests

Recent Activity

Organizations

Csplk's activity