github/privateGPT
1
0
Fork 1
mirror of https://github.com/imartinez/privateGPT.git synced 2025-05-30 18:56:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

updated settings.py and tidied up settings-ollama-yaml

Browse Source
This commit is contained in:
Stephen Gresham 2024-03-16 08:31:51 +11:00
parent 0bf0bff96a
commit 74e29e8947
2 changed files with 10 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
private_gpt/settings/settings.py
View File

@ -229,6 +229,10 @@ class OllamaSettings(BaseModel):
1.1,
description="Sets how strongly to penalize repetitions. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient. (Default: 1.1)",
)
request_timeout: float = Field(
120.0,
description="Time elapsed until ollama times out the request. Default is 120s. Format is float. "
)
class UISettings(BaseModel):

12
settings-ollama.yaml
View File

@ -14,12 +14,12 @@ ollama:
llm_model: mistral
embedding_model: nomic-embed-text
api_base: http://localhost:11434
tfs_z: 1.0 # Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting.
top_k: 40 # Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative. (Default: 40)
top_p: 0.9 # Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)
repeat_last_n: 64 # Sets how far back for the model to look back to prevent repetition. (Default: 64, 0 = disabled, -1 = num_ctx)
repeat_penalty: 1.2 # Sets how strongly to penalize repetitions. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient. (Default: 1.1)
request_timeout: 120.0 # Time elapsed until ollama times out the request. Default is 120s. Format is float.
tfs_z: 1.0 # Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting.
top_k: 40 # Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative. (Default: 40)
top_p: 0.9 # Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)
repeat_last_n: 64 # Sets how far back for the model to look back to prevent repetition. (Default: 64, 0 = disabled, -1 = num_ctx)
repeat_penalty: 1.2 # Sets how strongly to penalize repetitions. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient. (Default: 1.1)
request_timeout: 120.0 # Time elapsed until ollama times out the request. Default is 120s. Format is float.
vectorstore:
database: qdrant