ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-02-20 09:26:15 +00:00
Code Issues Actions 12 Packages Projects Releases Wiki Activity

docs(mixtral): add mixtral example (#1449)

Browse Source
This commit is contained in:
Ettore Di Giacinto 2023-12-16 11:44:43 -05:00 committed by GitHub
parent 2f7beb6744
commit 1c286c3c2f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 35 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
examples/configurations/README.md
View File

@ -64,4 +64,21 @@ wget https://huggingface.co/mys/ggml_bakllava-1/resolve/main/mmproj-model-f16.gg
curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
"model": "llava",
"messages": [{"role": "user", "content": [{"type":"text", "text": "What is in the image?"}, {"type": "image_url", "image_url": {"url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg" }}], "temperature": 0.9}]}'
```
### Mixtral
```
cp -r examples/configuration/mixtral/* models/
wget https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF/resolve/main/mixtral-8x7b-instruct-v0.1.Q2_K.gguf -O models/mixtral-8x7b-instruct-v0.1.Q2_K.gguf
```
#### Test it out
```
curl http://localhost:8080/v1/completions -H "Content-Type: application/json" -d '{
"model": "mixtral",
"prompt": "How fast is light?",
"temperature": 0.1 }'
```

1
examples/configurations/mixtral/mixtral Normal file
View File

@ -0,0 +1 @@
[INST] {{.Input}} [/INST]

1
examples/configurations/mixtral/mixtral-chat Normal file
View File

@ -0,0 +1 @@
[INST] {{.Input}} [/INST]

16
examples/configurations/mixtral/mixtral.yaml Executable file
View File

@ -0,0 +1,16 @@
context_size: 512
f16: true
threads: 11
gpu_layers: 90
name: mixtral
mmap: true
parameters:
model: mixtral-8x7b-instruct-v0.1.Q2_K.gguf
temperature: 0.2
top_k: 40
top_p: 0.95
batch: 512
tfz: 1.0
template:
chat: mixtral-chat
completion: mixtral