vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama : add 128k yarn context for Qwen (#10698)

Browse source 
* add 128k yarn context for Qwen

* added property for model tensors

* removing useless line
This commit is contained in:
Robert Collins 2024-12-07 16:12:27 -05:00 • committed by GitHub
parent 3573fa8e7b
commit 62e84d9848
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 9 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -761,6 +761,7 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.OUTPUT,
MODEL_TENSOR.ROPE_FREQS,
MODEL_TENSOR.ATTN_NORM,
MODEL_TENSOR.ATTN_Q,
MODEL_TENSOR.ATTN_K,