Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
L
localai-model-gallery
Manage
Activity
Members
Labels
Plan
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Locked files
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Package registry
Model registry
Operate
Environments
Terraform modules
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Code review analytics
Insights
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
KIT
AIFB
Betriebliche Informationssysteme
Infrastruktur
LocalAI
localai-model-gallery
Commits
09b0d4d8
Commit
09b0d4d8
authored
4 months ago
by
Fabian Rybinski
Browse files
Options
Downloads
Patches
Plain Diff
Update file aie-gemma-finetuned.yaml
parent
c65cb277
No related branches found
No related tags found
No related merge requests found
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
aie-gemma-finetuned.yaml
+25
-8
25 additions, 8 deletions
aie-gemma-finetuned.yaml
with
25 additions
and
8 deletions
aie-gemma-finetuned.yaml
+
25
−
8
View file @
09b0d4d8
...
@@ -12,15 +12,22 @@ config_file: |
...
@@ -12,15 +12,22 @@ config_file: |
parameters:
parameters:
model: downloads/llama_backend/AIE_Gemma2_2B_IT_Q4_K_M.gguf
model: downloads/llama_backend/AIE_Gemma2_2B_IT_Q4_K_M.gguf
roles:
roles:
assistant: '
A
ssistant:'
assistant: '
a
ssistant:'
system: '
S
ystem:'
system: '
s
ystem:'
user: '
U
ser:'
user: '
u
ser:'
template:
template:
chat_message: |-
chat_message: |-
<start_of_turn>{{if eq .RoleName "assistant" }}model{{else}}{{ .RoleName }}{{end}}
{{- range $i, $_ := .Messages }}
{{ if .Content -}}
{{- $last := eq (len (slice $.Messages $i)) 1 }}
{{.Content -}}
{{- if or (eq .Role "user") (eq .Role "system") }}<start_of_turn>user
{{ end -}}<end_of_turn>
{{ .Content }}<end_of_turn>
{{ if $last }}<start_of_turn>model
{{ end }}
{{- else if eq .Role "assistant" }}<start_of_turn>model
{{ .Content }}{{ if not $last }}<end_of_turn>
{{ end }}
{{- end }}
{{- end }}
chat: |
chat: |
{{.Input }}
{{.Input }}
<start_of_turn>model
<start_of_turn>model
...
@@ -30,7 +37,16 @@ config_file: |
...
@@ -30,7 +37,16 @@ config_file: |
- '<|im_end|>'
- '<|im_end|>'
- '<end_of_turn>'
- '<end_of_turn>'
- '<start_of_turn>'
- '<start_of_turn>'
context_size: 4096
context_size: 8192
system_prompt: |
You are a helpful and energy consumption aware assistant operating in a smart environment hosted using "Home Assistant".
As input, you will receive Home Assistant data, where each line represents a state change for an entity.
The data is limited to entities within a specific room and covers the past few minutes.
Analyze the provided data for patterns in entity state changes, where energy is used poorly.
Use the entity_ids from the provided historical data and create a Home Assistant automation that prevents the poor energy usage.
Do not provide any other information but the ```yaml formatted Home Assistant automation.
Use the "description" field inside your ```yaml response to explain your reasoning.
If there are no indicators for poor energy usage, answer with "NO".
usage
:
|
usage
:
|
...
@@ -44,3 +60,4 @@ files:
...
@@ -44,3 +60,4 @@ files:
-
filename
:
"
downloads/llama_backend/AIE_Gemma2_2B_IT_Q4_K_M.gguf"
-
filename
:
"
downloads/llama_backend/AIE_Gemma2_2B_IT_Q4_K_M.gguf"
sha256
:
"
"
sha256
:
"
"
uri
:
"
https://huggingface.co/Phabby/AIE-Gemma-2-2B-IT/resolve/main/AIE_Gemma2_2B_IT_Q4_K_M.gguf"
uri
:
"
https://huggingface.co/Phabby/AIE-Gemma-2-2B-IT/resolve/main/AIE_Gemma2_2B_IT_Q4_K_M.gguf"
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment