]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
model: support arch `DbrxForCausalLM` (#6515)
authorPierrick Hymbert <redacted>
Sat, 13 Apr 2024 09:33:52 +0000 (11:33 +0200)
committerGitHub <redacted>
Sat, 13 Apr 2024 09:33:52 +0000 (11:33 +0200)
commit4bd0f93e4ab4fe6682e7d0241c1bdec1397e954a
treeda912ccbf957473fb5aa6868c9cd73f0fcc42e63
parentab9a3240a9da941fdef5cd4a25f2b97c2f5a67aa
model: support arch `DbrxForCausalLM` (#6515)

* model: dbrx convert to gguf
#6344

* llama: support dbrx
#6344

* doc: dbrx: add the model as supported

* scripts: get-wikitext-2 add unzip

* llama: increase maximum experts allowed

* llama: factorize moe graph implementation between grok, mixtral and dbrx

---------

Co-authored-by: Megha Agarwal <redacted>
README.md
convert-hf-to-gguf.py
examples/eval-callback/eval-callback.cpp
gguf-py/gguf/constants.py
gguf-py/gguf/tensor_mapping.py
llama.cpp
scripts/get-wikitext-2.sh