vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-14 10:59:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

readme : model : mtdm : lfm2 improvements (#15476)

Browse source 
* Support untied embeddings

* Increase number of image tokens to 1024

* Add LFM2-VL to readme

* Actually use untied embeddings
This commit is contained in:
Tarek Dakhran 2025-08-22 09:29:08 +02:00 • committed by GitHub
parent a0f98dd604
commit e288693669
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 11 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

1
gguf-py/gguf/constants.py
View file

@ -2590,6 +2590,7 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.ATTN_K,
MODEL_TENSOR.ATTN_V,
MODEL_TENSOR.ATTN_OUT,
MODEL_TENSOR.OUTPUT,
],
MODEL_ARCH.SMALLTHINKER: [
MODEL_TENSOR.TOKEN_EMBD,