mradermacher

/

model_requests

like 67

I will certainly try :) It's queued and should be done very soon (see http://hf.tst.eu/status.html fro status updates)

Unfortunately it fails:

llama_model_load: error loading model: missing tensor 'token_embd.weight'

I think this might have to do with my conversion to Safetensors, I'll revert the repo back to the .bin files

Just drop me a note when I should try again :)

Do you mind trying again? I grabbed the safetensor file from the original train and GGUF my repo seemed to quantize it without issue.

Don't mind at all. It's queued, and when I get up again, we'll have results :)

All worked fine, as far as I can see.

Nice - Thank you sorry for the trouble <3