AI/dify
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/langgenius/dify.git synced 2025-08-12 18:59:07 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(model_runtime): fix wrong max_tokens for Claude 3.5 Haiku on Amazon Bedrock (#10286)

Browse Source
This commit is contained in:
Matsuda 2024-11-05 15:41:15 +09:00 committed by GitHub
parent 249b897872
commit cb245b5435
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
api/core/model_runtime/model_providers/bedrock/llm/anthropic.claude-3-5-haiku-v1.yaml
View File

@ -16,9 +16,9 @@ parameter_rules:
use_template: max_tokens use_template: max_tokens
required: true required: true
type: int type: int
default: 4096 default: 8192
min: 1 min: 1
max: 4096 max: 8192
help: help:
zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。 zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter. en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.