Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

stop parameter fixed #1805

Merged
merged 1 commit into from
Feb 13, 2025
Merged

stop parameter fixed #1805

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions docker/Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,13 +1,13 @@
FROM amazonlinux:latest

ENV KAIRON_HOME=/app PYTHON_VERSION=3.10.16 TEMPLATE_DIR_DEFAULT=./template/use-cases/Hi-Hello-GPT RASA_TELEMETRY_ENABLED=false
ENV KAIRON_HOME=/app PYTHON_VERSION=3.10 TEMPLATE_DIR_DEFAULT=./template/use-cases/Hi-Hello-GPT RASA_TELEMETRY_ENABLED=false
ENV PYENV_ROOT=/root/.pyenv
ENV PATH=$PYENV_ROOT/shims:$PYENV_ROOT/bin:$PATH

WORKDIR ${KAIRON_HOME}

RUN yum update -y
RUN yum install -y wget make gcc zlib-devel tar xz gzip openssl openssl-devel bzip2-devel sqlite-devel libffi-devel openblas-devel ca-certificates git
RUN yum install -y wget make gcc zlib-devel tar xz gzip openssl openssl-devel bzip2-devel sqlite-devel libffi-devel openblas-devel ca-certificates git ncurses-devel readline-devel xz-devel tk-devel bzip2 patch sqlite

RUN curl https://pyenv.run | bash
RUN echo 'export PYENV_ROOT="$HOME/.pyenv"' >> ~/.zshrc && \
Expand Down
40 changes: 40 additions & 0 deletions metadata/llm_metadata.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -202,6 +202,46 @@ perplexity:
minimum: -2.0
maximum: 2.0
description: "The frequency_penalty hyperparameter penalizes the model for generating words that have already been generated in the current response."
aws-nova:
$schema: "https://json-schema.org/draft/2020-12/schema"
type: "object"
description: "AWS Nova AI Models for Prompt"
properties:
temperature:
type: "number"
default: 0.0
minimum: 0.0
maximum: 2.0
description: "The temperature hyperparameter controls the creativity or randomness of the generated responses."
max_tokens:
type: "integer"
default: 300
minimum: 5
maximum: 5120
description: "The max_tokens hyperparameter limits the length of generated responses in chat completion."
model:
type: "string"
default: "bedrock/converse/us.amazon.nova-lite-v1:0"
enum: ["bedrock/converse/us.amazon.nova-micro-v1:0", "bedrock/converse/us.amazon.nova-lite-v1:0", "bedrock/converse/us.amazon.nova-pro-v1:0"]
description: "The model hyperparameter is the ID of the model to use such as gpt-2, gpt-3, or a custom model that you have trained or fine-tuned."
top_p:
type: "number"
default: 0.0
minimum: 0.0
maximum: 1.0
description: "The top_p hyperparameter is a value that controls the diversity of the generated responses."
stop:
anyOf:
- type: "array"
maxItems: 4
items:
type: "string"
- type: "null"
type:
- "array"
- "null"
default: null
description: "The stop hyperparameter is used to specify a list of tokens that should be used to indicate the end of a generated response."
Comment on lines +205 to +244
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue

Remove duplicate aws-nova section.

The file contains two identical aws-nova sections with different implementations of the stop parameter. Based on the PR title "stop parameter fixed", it appears the second implementation (array-only) is intended, but the old section wasn't removed.

Remove the first duplicate section:

-aws-nova:
-  $schema: "https://json-schema.org/draft/2020-12/schema"
-  type: "object"
-  description: "AWS Nova AI Models for Prompt"
-  properties:
-    temperature:
-      type: "number"
-      default: 0.0
-      minimum: 0.0
-      maximum: 2.0
-      description: "The temperature hyperparameter controls the creativity or randomness of the generated responses."
-    max_tokens:
-      type: "integer"
-      default: 300
-      minimum: 5
-      maximum: 5120
-      description: "The max_tokens hyperparameter limits the length of generated responses in chat completion."
-    model:
-      type: "string"
-      default: "bedrock/converse/us.amazon.nova-lite-v1:0"
-      enum: ["bedrock/converse/us.amazon.nova-micro-v1:0", "bedrock/converse/us.amazon.nova-lite-v1:0", "bedrock/converse/us.amazon.nova-pro-v1:0"]
-      description: "The model hyperparameter is the ID of the model to use such as gpt-2, gpt-3, or a custom model that you have trained or fine-tuned."
-    top_p:
-      type: "number"
-      default: 0.0
-      minimum: 0.0
-      maximum: 1.0
-      description: "The top_p hyperparameter is a value that controls the diversity of the generated responses."
-    stop:
-      anyOf:
-        - type: "array"
-          maxItems: 4
-          items:
-            type: "string"
-        - type: "null"
-      type:
-        - "array"
-        - "null"
-      default: null
-      description: "The stop hyperparameter is used to specify a list of tokens that should be used to indicate the end of a generated response."

Also applies to: 245-279

aws-nova:
$schema: "https://json-schema.org/draft/2020-12/schema"
type: "object"
Expand Down
Loading