dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-20 10:35:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 21

docs/examples: enhancements (#1572)

Browse source 
* docs: re-order sections

* fix references

* Add mixtral-instruct, tinyllama-chat, dolphin-2.5-mixtral-8x7b

* Fix link

* Minor corrections

* fix: models is a StringSlice, not a String

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* WIP: switch docs theme

* content

* Fix GH link

* enhancements

* enhancements

* Fixed how to link

Signed-off-by: lunamidori5 <118759930+lunamidori5@users.noreply.github.com>

* fixups

* logo fix

* more fixups

* final touches

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Signed-off-by: lunamidori5 <118759930+lunamidori5@users.noreply.github.com>
Co-authored-by: lunamidori5 <118759930+lunamidori5@users.noreply.github.com>
This commit is contained in:
Ettore Di Giacinto 2024-01-18 19:41:08 +01:00 • committed by GitHub
parent b5c93f176a
commit 6ca4d38a01
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
79 changed files with 1826 additions and 3546 deletions
Download patch file Download diff file Expand all files Collapse all files

27
embedded/models/dolphin-2.5-mixtral-8x7b.yaml Normal file
View file

@ -0,0 +1,27 @@
name: dolphin-mixtral-8x7b
mmap: true
parameters:
model: huggingface://TheBloke/dolphin-2.5-mixtral-8x7b-GGUF/blob/main/dolphin-2.5-mixtral-8x7b.Q2_K.gguf
temperature: 0.2
top_k: 40
top_p: 0.95
template:
chat_message: |
<|im_start|>{{if eq .RoleName "assistant"}}assistant{{else if eq .RoleName "system"}}system{{else if eq .RoleName "user"}}user{{end}}
{{if .Content}}{{.Content}}{{end}}<|im_end|>
chat: |
{{.Input}}
<|im_start|>assistant
completion: |
{{.Input}}
context_size: 4096
f16: true
stopwords:
- <|im_end|>
gpu_layers: 90
usage: |
curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
"model": "dolphin-mixtral-8x7b",
"messages": [{"role": "user", "content": "How are you doing?", "temperature": 0.1}]
}'

20
embedded/models/mixtral-instruct.yaml Normal file
View file

@ -0,0 +1,20 @@
name: mixtral-instruct
mmap: true
parameters:
model: huggingface://TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF/mixtral-8x7b-instruct-v0.1.Q2_K.gguf
temperature: 0.2
top_k: 40
top_p: 0.95
template:
chat: &chat |
[INST] {{.Input}} [/INST]
completion: *chat
context_size: 4096
f16: true
gpu_layers: 90
usage: |
curl http://localhost:8080/v1/completions -H "Content-Type: application/json" -d '{
"model": "mixtral-instruct",
"prompt": "How are you doing?"
}'

28
embedded/models/tinyllama-chat.yaml Normal file
View file

@ -0,0 +1,28 @@
name: tinyllama-chat
mmap: true
parameters:
model: huggingface://TheBloke/TinyLlama-1.1B-Chat-v0.3-GGUF/tinyllama-1.1b-chat-v0.3.Q8_0.gguf
temperature: 0.2
top_k: 40
top_p: 0.95
template:
chat_message: |
<|im_start|>{{if eq .RoleName "assistant"}}assistant{{else if eq .RoleName "system"}}system{{else if eq .RoleName "user"}}user{{end}}
{{if .Content}}{{.Content}}{{end}}<|im_end|>
chat: |
{{.Input}}
<|im_start|>assistant
completion: |
{{.Input}}
context_size: 4096
f16: true
stopwords:
- <|im_end|>
gpu_layers: 90
usage: |
curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
"model": "tinyllama-chat",
"messages": [{"role": "user", "content": "How are you doing?", "temperature": 0.1}]
}'