mirror of
https://github.com/katanemo/plano.git
synced 2026-04-29 10:56:35 +02:00
add support for 3b model (#96)
This commit is contained in:
parent
4d7c07a63c
commit
bb746e237a
2 changed files with 25 additions and 0 deletions
|
|
@ -0,0 +1,24 @@
|
|||
FROM Arch-Function-Calling-3B-Q4_K_M.gguf
|
||||
|
||||
# Set parameters for response generation
|
||||
PARAMETER num_ctx 4096
|
||||
PARAMETER num_predict 1024
|
||||
PARAMETER temperature 0.001
|
||||
PARAMETER top_p 1.0
|
||||
PARAMETER top_k 50
|
||||
PARAMETER repeat_penalty 1.0
|
||||
PARAMETER stop "<|im_start|>"
|
||||
PARAMETER stop "<|im_end|>"
|
||||
|
||||
# Set the random number seed to use for generation
|
||||
PARAMETER seed 42
|
||||
|
||||
# Set the prompt template to be passed into the model
|
||||
TEMPLATE """
|
||||
{{- if .System }}<|im_start|>system
|
||||
{{ .System }}<|im_end|>
|
||||
{{ end }}{{ if .Prompt }}
|
||||
<|im_start|>user
|
||||
{{ .Prompt }}<|im_end|>
|
||||
{{ end }}<|im_start|>assistant
|
||||
{{ .Response }}<|im_end|>"""
|
||||
|
|
@ -57,6 +57,7 @@ services:
|
|||
environment:
|
||||
# use ollama endpoint that is hosted by host machine (no virtualization)
|
||||
- OLLAMA_ENDPOINT=${OLLAMA_ENDPOINT:-host.docker.internal}
|
||||
- OLLAMA_MODEL=Arch-Function-Calling-3B-Q4_K_M
|
||||
# uncomment following line to use ollama endpoint that is hosted by docker
|
||||
# - OLLAMA_ENDPOINT=ollama
|
||||
# - OLLAMA_MODEL=Arch-Function-Calling-1.5B:Q4_K_M
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue