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

model: support arch DbrxForCausalLM (#6515)

Browse source 
* 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 <16129366+megha95@users.noreply.github.com>
This commit is contained in:
Pierrick Hymbert 2024-04-13 11:33:52 +02:00 • committed by GitHub
parent ab9a3240a9
commit 4bd0f93e4a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 428 additions and 148 deletions
Download patch file Download diff file Expand all files Collapse all files

3
scripts/get-wikitext-2.sh
View file

@ -1,10 +1,11 @@
#!/bin/bash
wget https://huggingface.co/datasets/ggml-org/ci/resolve/main/wikitext-2-raw-v1.zip
unzip wikitext-2-raw-v1.zip
echo "Usage:"
echo ""
echo " ./perplexity -m model.gguf -f wiki.test.raw [other params]"
echo " ./perplexity -m model.gguf -f wikitext-2-raw/wiki.test.raw [other params]"
echo ""
exit 0