Response prefill like in Claude
OPEN SOURCE
-
SmolLM 360M: Instant Lightweight Language Model Browser Demo
By
–
Sharing one demo which is blowing my mind, the new instant SmolLM 360M running live in your browser: https://
huggingface.co/spaces/Hugging
FaceTB/instant-smollm
… And find more info here: https://
huggingface.co/collections/Hu
ggingFaceTB/smollm-6695016cad7167254ce15966
… And here: -
Synthetic Data and Small Language Models Journey
By
–
It’s Sunday morning we have some time with the coffee so let me tell you about some of our recent surprising journey in synthetic data and small language models. This post is prompted by the coming release of an instant, in-browser model called SmolLM360 (link at the end) The
-
Asahi Linux reusable work for Apple silicon development
By
–
Would be cool yeah. Could reuse a lot of work from Asahi Linux.
-
Official Support for Easy Software Installation
By
–
Imagine if installing things wouldn’t require crazy system hacks but is officially supported.
-
LazyMergekit: Merge AI Models with Commands and Config
By
–
You can do it with LazyMergekit. I've added all the commands and the config I've used.
-
AI-in-Action Club Launches DSPy Framework Training Session
By
–
our next #ai-in-action club is starting now: on @lateinteraction
’s DSPy! led by @ProgramWithAi and @kbal11 -
GGUF Quantizations Ready for Hermes-3-Llama Model Testing
By
–
GGUF quants are also ready if you want to test the model. @bartowski1182 already made fancy imatrix ones. Love the new model tree on @huggingface
! (cc @victormustar @julien_c
) GGUF: https://
huggingface.co/mlabonne/Herme
s-3-Llama-3.1-8B-lorablated-GGUF
… -
Open-Source AI Models and Abliteration Techniques Explained
By
–
Of course, special thanks to @NousResearch and @teknium for these high-quality models. Thanks to grimjim and @failspy for the abliteration techniques that were used here. You can learn more about it in my article:
-
Hermes 3 LoRA-Ablated Uncensored Model Release
By
–
A fully uncensored Hermes 3 with lorablation! The lorablated model directly answers questions without any tweaking. Here's how it was made: 1/ Create a LoRA adapter based on Llama 3.1 8B Instruct and my abliterated version. 2/ Apply it to Hermes 3 from @NousResearch using