discourse-ai/config/eval-llms.yml
Sam 28af4434c5
Dev: eval improvements (#1162)
Adds sonnet 3.7
Adds support for temp in eval framework
2025-03-04 16:12:25 +11:00

71 lines
2.1 KiB
YAML

llms:
gpt-4o:
display_name: GPT-4o
name: gpt-4o
tokenizer: DiscourseAi::Tokenizer::OpenAiTokenizer
api_key_env: OPENAI_API_KEY
provider: open_ai
url: https://api.openai.com/v1/chat/completions
max_prompt_tokens: 131072
vision_enabled: true
gpt-4o-mini:
display_name: GPT-4o-mini
name: gpt-4o-mini
tokenizer: DiscourseAi::Tokenizer::OpenAiTokenizer
api_key_env: OPENAI_API_KEY
provider: open_ai
url: https://api.openai.com/v1/chat/completions
max_prompt_tokens: 131072
vision_enabled: true
claude-3.5-haiku:
display_name: Claude 3.5 Haiku
name: claude-3-5-haiku-latest
tokenizer: DiscourseAi::Tokenizer::AnthropicTokenizer
api_key_env: ANTHROPIC_API_KEY
provider: anthropic
url: https://api.anthropic.com/v1/messages
max_prompt_tokens: 200000
vision_enabled: false
claude-3.5-sonnet:
display_name: Claude 3.5 Sonnet
name: claude-3-5-sonnet-latest
tokenizer: DiscourseAi::Tokenizer::AnthropicTokenizer
api_key_env: ANTHROPIC_API_KEY
provider: anthropic
url: https://api.anthropic.com/v1/messages
max_prompt_tokens: 200000
vision_enabled: true
claude-3.7-sonnet:
display_name: Claude 3.7 Sonnet
name: claude-3-7-sonnet-latest
tokenizer: DiscourseAi::Tokenizer::AnthropicTokenizer
api_key_env: ANTHROPIC_API_KEY
provider: anthropic
url: https://api.anthropic.com/v1/messages
max_prompt_tokens: 200000
vision_enabled: true
gemini-2.0-flash:
display_name: Gemini 2.0 Flash
name: gemini-2-0-flash
tokenizer: DiscourseAi::Tokenizer::GeminiTokenizer
api_key_env: GEMINI_API_KEY
provider: google
url: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash
max_prompt_tokens: 1000000
vision_enabled: true
gemini-2.0-pro-exp:
display_name: Gemini 2.0 pro
name: gemini-2-0-pro-exp
tokenizer: DiscourseAi::Tokenizer::GeminiTokenizer
api_key_env: GEMINI_API_KEY
provider: google
url: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-pro-exp
max_prompt_tokens: 1000000
vision_enabled: true