LocalAI/embedded/models/tinyllama-chat.yaml
Ettore Di Giacinto 6ca4d38a01
docs/examples: enhancements (#1572)
* 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>
2024-01-18 19:41:08 +01:00

28 lines
800 B
YAML

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}]
}'