381–390 of 507 posts
Earlier quoted context omitted.
Release open weights so competitors can't raise good money, then rear naked choke when they run dry
Using Brazilian Jiu-Jitsu (BJJ) technical terms is confusing. Sports allusions don't travel well between cultures, especially if they sound seedy.
Hi all! I work on the Gemma team, one of many as this one was a bigger effort given it was a mainline release. Happy to answer whatever questions I can
This is of importance to me as I work on https://jsonquery.app and would prefer to use a model that works well with browser inference.
gemma-4-26b-a4b-it and gemma-4-31b-it produced accurate results in a few of my tests. But those are 50-60GB in size. Chrome has a developer preview that bundles Gemini Nano (under 2GB) and it used to work really well, but requires a few switches to be manually switched on, and has recently gotten worse in quality when testing for jq generation.
Earlier quoted context omitted.
Daniel, your work is changing the world. More power to you. I setup a pipeline for inference with OCR, full text search, embedding and summarization of land records dating back 1800s. All powered by the GGUF's you generate and llama.cpp. People are so excited that they can now search the records in multiple languages that a 1 minute wait to process the document seems nothing. Thank you!
Hey in really interested in your pipeline techniques. I've got some pdfs I need to get processed but processing them in the cloud with big providers requires redaction. Wondering if a local model or a self hosted one would work just as well.
Earlier quoted context omitted.
Hey, I tried to use Unsloth to run Gemma 4 locally but got stuck during the setup on Windows 11. At some point it asked me to create a password, and right after that it threw an error. Here’s a screenshot: https://imgur.com/a/sCMmqht This happened after running the PowerShell setup, where it installed several things like NVIDIA components, VS Code, and Python. At the end, PowerShell tell me to open a http://localhost…
Apologies we just fixed it!! If you try again from source ie irm https://unsloth.ai/install.ps1 | iex it should work hopefully. If not - please at us on Discord and we'll help you! The Network error is a bummer - we'll check. And yes we're working on a .exe!!
Thanks, will check it out tomorrow.
Hope the unsloth-setup.exe > Windows App is coming soon! I think it will expand accessibility and user base.
Hi all! I work on the Gemma team, one of many as this one was a bigger effort given it was a mainline release. Happy to answer whatever questions I can
Do any of you use this as a replacement for Claude Code? For example, you might use it with openclaw. I have a 24 GB integrated RAM Mac Mini M4 I currently run Claude Code on, do you think I can replace it with OpenClaw and one of these models?
I'm curious about the multimodal capabilities on the E2B and E4B and how fast is it. In ChatGPT right now, you can have a audio and video feed for the AI, and then the AI can respond in real-time. Now I wonder if the E2B or the E4B is capable enough for this and fast enough to be run on an iPhone. Basically replicating that experience, but all the computations (STT, LLM, and TTS) are done locally on the phone. I just…
Earlier quoted context omitted.
What does that mean for a user of the model? Is the "-it" version more direct with solutions or something?
It means that model was tuned to to act as chat bot. So write a reply on behalf of assistant and stop generating (by inserting special "end of turn" token to signal inference engine to stop generation). Base model (without instruction/chat tuning) just generates text non stop ("autocomplete on steroids") and text is not necessarily even formatted as chat -- most text in training data isn't dialogue, after all.
The it- one is the yellow smiling dot, the pt- is the rightmost monster head.
Earlier quoted context omitted.
Thanks! Just tried it on a 40 page pdf. Seems to work for single images but the large pdf gives me connection timeouts
I also get connection timeouts on larger documents, but it automatically retries and completes. All the pages are processed when I'm done. However, I'm using the Python client SDK for larger documents rather than the basic glmocr command line tool. I'm not sure if that makes a difference.
Thinking / reasoning + multimodal + tool calling. We made some quants at https://huggingface.co/collections/unsloth/gemma-4 for folks to run them - they work really well! Guide for those interested: https://unsloth.ai/docs/models/gemma-4 Also note to use temperature = 1.0, top_p = 0.95, top_k = 64 and the EOS is " ". " thought\n" is also used for the thinking trace!