mradermacher

/

model_requests

like 132

They are all queued! :D

You can check for progress at http://hf.tst.eu/status.html or regularly check the model
summary pages under the following locations for quants to appear:

• https://hf.tst.eu/model#Hearthfire-24B-absolute-heresy-GGUF
• https://hf.tst.eu/model#Blossom-V6.3-36B-tainted-heresy-GGUF
• https://hf.tst.eu/model#LFM2.5-VL-1.6B-absolute-heresy-GGUF

Godspeed 🙏

I went down a rabbit hole to address the llama3~bpe errors in the following models and make them work on my end. Feel free to retry or not:
https://huggingface.co/MuXodious/Hearthfire-24B-absolute-heresy
https://huggingface.co/MuXodious/Harbinger-24B-noslop-absolute-heresy
Note: Noslop version is highly experimental.

As for the following model, I can try changing the original tokenizer class TokenizersBackend to PreTrainedTokenizerFast found in 1.2B-Base version to make it run with your tooling. I have already made some quants for it so, if you call the shot, I'll make the swap.
https://huggingface.co/MuXodious/LFM2.5-VL-1.6B-absolute-heresy

Edit: Thanks for the Quants!