mradermacher

/

model_requests

Like 221

Hi @Rebis and @mradermacher ! I am the author of Mythos. Thank you so much for the interest, follow, and GGUF request!

A quick update on the model status:

• Architecture: Mythos is a custom Mixture-of-Experts (MoE) model with Liger Kernel Cross-Entropy designed for 500+ languages.
• Current Status: The model is actively undergoing pre-training from scratch (currently at Step 2,000+).
• GGUF Timeline: Because it is a custom MoE architecture and weights are still converging in pre-training, there are no final weights published yet. As soon as base training reaches convergence and we publish the Safetensors release, we will provide llama.cpp conversion scripts and GGUF quantizations!

If you'd like to track live training updates, telemetry, or chat about the architecture, you're very welcome to join our research Discord:
👉 https://discord.gg/KKVN5BShGj

Thank you for the support!

Hi,
I see, thanks for the information.
I'll look into signing up on Discord.
In any case, I am impressed by the speed of your responsiveness.

alright let me know then when it gets merged into main llamacpp and I will queue it =)

Thanks so much @RichardErkhov ! Really appreciate the support and looking forward to it.

Our base pre-training run and initial multilingual evaluations are estimated to take around 3 to 4 weeks to complete. Once the final weights are locked in and the llama.cpp conversion is ready, I'll definitely ping you here so you can queue the quantizations.

Thanks again! 🙌

Hi, for us to quant make sure that you are merged into main (ggeranov) llamacpp

Understood @RichardErkhov ! That makes total sense.

Once our base training finishes and we export the Hugging Face weights, we will ensure it aligns with llama.cpp main (or submit the architecture PR to ggerganov/llama.cpp) so your pipeline can convert it seamlessly.

Thanks for the heads-up and guidance! 🙌

or submit the architecture PR to ggerganov/llama.cpp

not or, have to. Otherwise we are not able to quant your model to avoid user confusion and the amount of llamacpp forks we have (we have 0 and want to maintain that number)

Understood and 100% agreed @RichardErkhov ! No forks at all.

When base training wraps, we will make sure the weights are formatted so they run directly on official ggerganov/llama.cpp main before pinging you.

Thanks for clarifying the policy! 👍

Update on GGUF & llama.cpp support:

We are wrapping up pre-training and preparing native GGUF conversion for release in early November. Our goal is full zero-fork integration directly into ggerganov/llama.cpp main.

We are actively coordinating the architecture PR, tokenization mapping, and early quant testing on our Discord:
👉 https://discord.gg/KKVN5BShGj

If you have experience with llama.cpp MoE ops or want to test early alpha quants before public release, we'd love your hands on deck in #contributions!

Hi, sorry, not joining. let me know when I should queue the model and a link =)
You can also share the progress here =)

Totally understand @RichardErkhov ! Thank you so much for offering to queue the model.

Just a quick heads-up: We've officially renamed the repository from Mythos_translation to AdithyanAI/Mythos2.0-2B (https://huggingface.co/AdithyanAI/Mythos2.0-2B).

I'll keep all progress updates posted right here in this thread. Once base training finishes and the weights are ready for the upstream llama.cpp pipeline in early November, I will ping you here with the link to queue it up!

Appreciate your support! 🚀