Skip to content

Fix repeat_last_n in OpenAI server #23

Fix repeat_last_n in OpenAI server

Fix repeat_last_n in OpenAI server #23

Workflow file for this run

name: CI
on:
push:
branches: [ master, main ]
pull_request:
branches: [ master, main ]
jobs:
Tests:
timeout-minutes: 60
runs-on: ${{ matrix.os }}
strategy:
fail-fast: false
matrix:
os: [ macos-latest ] # ubuntu-latest, windows-latest are currently non-functional, requiring adaptation for proper functionality.
steps:
- name: Checkout Repository
uses: actions/checkout@v4
- name: Build and Install CosmoCC
shell: bash
run: |
mkdir -p cosmocc
cd cosmocc
curl -o cosmocc.zip -L https://cosmo.zip/pub/cosmocc/cosmocc.zip
unzip cosmocc.zip
cd ..
./cosmocc/bin/make -j8 && ./cosmocc/bin/make install
- name: Create LLM Executable
shell: bash
run: |
curl -o mistral.gguf -L https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q4_K_M.gguf
cat << EoF > .args
-m
mistral.gguf
...
EoF
cp /usr/local/bin/llamafile llamafile_exe
chmod +x llamafile_exe
zipalign -j0 \
llamafile_exe \
mistral.gguf \
.args
- name: Execute LLM CLI
shell: bash
run: |
./llamafile_exe --temp 0.7 --n-predict 50 -p '[INST]Write a story about llamas[/INST]'