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

server: tests: change model to: @karpathy's tinyllamas

Browse source
This commit is contained in:
Pierrick HYMBERT 2024-02-20 20:50:14 +01:00
parent 8bb586bf06
commit 6c95ec6587
2 changed files with 4 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

4
.github/workflows/server-test.yml vendored
View file

@ -40,12 +40,12 @@ jobs:
- name: Download test model
id: download_model
run: |
./scripts/hf.sh --repo ngxson/dummy-llama --file llama_xs_q4.bin
./scripts/hf.sh --repo ggml-org/models --file tinyllamas/stories260K.gguf
- name: Server Integration Tests
id: server_integration_test
run: |
cd examples/server/tests
./tests.sh ../../../llama_xs_q4.bin
./tests.sh ../../../stories260K.gguf

4
examples/server/tests/README.md
View file

@ -7,5 +7,5 @@ Functional server tests suite.
### Run tests
1. Build the server
2. download a GGUF model: `../../../scripts/hf.sh --repo ngxson/dummy-llama --file llama_xs_q4.bin`
3. Start the test: `./tests.sh tinyllama-2-1b-miniguanaco.Q2_K.gguf -ngl 23 --log-disable`
2. download a GGUF model: `./scripts/hf.sh --repo ggml-org/models --file tinyllamas/stories260K.gguf`
3. Start the test: `./tests.sh stories260K.gguf -ngl 23`