diff --git a/ra_aid/models_tokens.py b/ra_aid/models_tokens.py deleted file mode 100644 index a15214e..0000000 --- a/ra_aid/models_tokens.py +++ /dev/null @@ -1,271 +0,0 @@ -""" -List of model tokens -""" - -DEFAULT_TOKEN_LIMIT = 100000 - - -models_tokens = { - "openai": { - "gpt-3.5-turbo-0125": 16385, - "gpt-3.5": 4096, - "gpt-3.5-turbo": 16385, - "gpt-3.5-turbo-1106": 16385, - "gpt-3.5-turbo-instruct": 4096, - "gpt-4-0125-preview": 128000, - "gpt-4-turbo-preview": 128000, - "gpt-4-turbo": 128000, - "gpt-4-turbo-2024-04-09": 128000, - "gpt-4-1106-preview": 128000, - "gpt-4-vision-preview": 128000, - "gpt-4": 8192, - "gpt-4-0613": 8192, - "gpt-4-32k": 32768, - "gpt-4-32k-0613": 32768, - "gpt-4o": 128000, - "gpt-4o-2024-08-06": 128000, - "gpt-4o-2024-05-13": 128000, - "gpt-4o-mini": 128000, - "o1-preview": 128000, - "o1-mini": 128000, - }, - "azure_openai": { - "gpt-3.5-turbo-0125": 16385, - "gpt-3.5": 4096, - "gpt-3.5-turbo": 16385, - "gpt-3.5-turbo-1106": 16385, - "gpt-3.5-turbo-instruct": 4096, - "gpt-4-0125-preview": 128000, - "gpt-4-turbo-preview": 128000, - "gpt-4-turbo": 128000, - "gpt-4-turbo-2024-04-09": 128000, - "gpt-4-1106-preview": 128000, - "gpt-4-vision-preview": 128000, - "gpt-4": 8192, - "gpt-4-0613": 8192, - "gpt-4-32k": 32768, - "gpt-4-32k-0613": 32768, - "gpt-4o": 128000, - "gpt-4o-mini": 128000, - "chatgpt-4o-latest": 128000, - "o1-preview": 128000, - "o1-mini": 128000, - }, - "google_genai": { - "gemini-pro": 128000, - "gemini-1.5-flash-latest": 128000, - "gemini-1.5-pro-latest": 128000, - "models/embedding-001": 2048, - }, - "google_vertexai": { - "gemini-1.5-flash": 128000, - "gemini-1.5-pro": 128000, - "gemini-1.0-pro": 128000, - }, - "ollama": { - "command-r": 12800, - "codellama": 16000, - "dbrx": 32768, - "deepseek-coder:33b": 16000, - "falcon": 2048, - "llama2": 4096, - "llama2:7b": 4096, - "llama2:13b": 4096, - "llama2:70b": 4096, - "llama3": 8192, - "llama3:8b": 8192, - "llama3:70b": 8192, - "llama3.1": 128000, - "llama3.1:8b": 128000, - "llama3.1:70b": 128000, - "lama3.1:405b": 128000, - "llama3.2": 128000, - "llama3.2:1b": 128000, - "llama3.2:3b": 128000, - "llama3.3:70b": 128000, - "scrapegraph": 8192, - "mistral-small": 128000, - "mistral-openorca": 32000, - "mistral-large": 128000, - "grok-1": 8192, - "llava": 4096, - "mixtral:8x22b-instruct": 65536, - "nomic-embed-text": 8192, - "nous-hermes2:34b": 4096, - "orca-mini": 2048, - "phi3:3.8b": 12800, - "phi3:14b": 128000, - "qwen:0.5b": 32000, - "qwen:1.8b": 32000, - "qwen:4b": 32000, - "qwen:14b": 32000, - "qwen:32b": 32000, - "qwen:72b": 32000, - "qwen:110b": 32000, - "stablelm-zephyr": 8192, - "wizardlm2:8x22b": 65536, - "mistral": 128000, - "gemma2": 128000, - "gemma2:9b": 128000, - "gemma2:27b": 128000, - # embedding models - "shaw/dmeta-embedding-zh-small-q4": 8192, - "shaw/dmeta-embedding-zh-q4": 8192, - "chevalblanc/acge_text_embedding": 8192, - "martcreation/dmeta-embedding-zh": 8192, - "snowflake-arctic-embed": 8192, - "mxbai-embed-large": 512, - }, - "oneapi": { - "qwen-turbo": 6000, - }, - "nvidia": { - "meta/llama3-70b-instruct": 419, - "meta/llama3-8b-instruct": 419, - "nemotron-4-340b-instruct": 1024, - "databricks/dbrx-instruct": 4096, - "google/codegemma-7b": 8192, - "google/gemma-2b": 2048, - "google/gemma-7b": 8192, - "google/recurrentgemma-2b": 2048, - "meta/codellama-70b": 16384, - "meta/llama2-70b": 4096, - "microsoft/phi-3-mini-128k-instruct": 122880, - "mistralai/mistral-7b-instruct-v0.2": 4096, - "mistralai/mistral-large": 8192, - "mistralai/mixtral-8x22b-instruct-v0.1": 32768, - "mistralai/mixtral-8x7b-instruct-v0.1": 8192, - "snowflake/arctic": 16384, - }, - "groq": { - "llama3-8b-8192": 8192, - "llama3-70b-8192": 8192, - "mixtral-8x7b-32768": 32768, - "gemma-7b-it": 8192, - "claude-3-haiku-20240307'": 8192, - }, - "toghetherai": { - "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": 128000, - "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": 128000, - "mistralai/Mixtral-8x22B-Instruct-v0.1": 128000, - "stabilityai/stable-diffusion-xl-base-1.0": 2048, - "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": 128000, - "NousResearch/Hermes-3-Llama-3.1-405B-Turbo": 128000, - "Gryphe/MythoMax-L2-13b-Lite": 8192, - "Salesforce/Llama-Rank-V1": 8192, - "meta-llama/Meta-Llama-Guard-3-8B": 128000, - "meta-llama/Meta-Llama-3-70B-Instruct-Turbo": 128000, - "meta-llama/Llama-3-8b-chat-hf": 8192, - "meta-llama/Llama-3-70b-chat-hf": 8192, - "Qwen/Qwen2-72B-Instruct": 128000, - "google/gemma-2-27b-it": 8192, - }, - "anthropic": { - "claude_instant": 100000, - "claude2": 9000, - "claude2.1": 200000, - "claude3": 200000, - "claude3.5": 200000, - "claude-3-opus-20240229": 200000, - "claude-3-sonnet-20240229": 200000, - "claude-3-haiku-20240307": 200000, - "claude-3-5-sonnet-20240620": 200000, - "claude-3-5-sonnet-20241022": 200000, - "claude-3-5-haiku-latest": 200000, - }, - "bedrock": { - "anthropic.claude-3-haiku-20240307-v1:0": 200000, - "anthropic.claude-3-sonnet-20240229-v1:0": 200000, - "anthropic.claude-3-opus-20240229-v1:0": 200000, - "anthropic.claude-3-5-sonnet-20240620-v1:0": 200000, - "claude-3-5-haiku-latest": 200000, - "anthropic.claude-v2:1": 200000, - "anthropic.claude-v2": 100000, - "anthropic.claude-instant-v1": 100000, - "meta.llama3-8b-instruct-v1:0": 8192, - "meta.llama3-70b-instruct-v1:0": 8192, - "meta.llama2-13b-chat-v1": 4096, - "meta.llama2-70b-chat-v1": 4096, - "mistral.mistral-7b-instruct-v0:2": 32768, - "mistral.mixtral-8x7b-instruct-v0:1": 32768, - "mistral.mistral-large-2402-v1:0": 32768, - "mistral.mistral-small-2402-v1:0": 32768, - "amazon.titan-embed-text-v1": 8000, - "amazon.titan-embed-text-v2:0": 8000, - "cohere.embed-english-v3": 512, - "cohere.embed-multilingual-v3": 512, - }, - "mistralai": { - "mistral-large-latest": 128000, - "open-mistral-nemo": 128000, - "codestral-latest": 32000, - "mistral-embed": 8000, - "open-mistral-7b": 32000, - "open-mixtral-8x7b": 32000, - "open-mixtral-8x22b": 64000, - "open-codestral-mamba": 256000, - }, - "hugging_face": { - "xai-org/grok-1": 8192, - "meta-llama/Meta-Llama-3-8B": 8192, - "meta-llama/Meta-Llama-3-8B-Instruct": 8192, - "meta-llama/Meta-Llama-3-70B": 8192, - "meta-llama/Meta-Llama-3-70B-Instruct": 8192, - "google/gemma-2b": 8192, - "google/gemma-2b-it": 8192, - "google/gemma-7b": 8192, - "google/gemma-7b-it": 8192, - "microsoft/phi-2": 2048, - "openai-community/gpt2": 1024, - "openai-community/gpt2-medium": 1024, - "openai-community/gpt2-large": 1024, - "facebook/opt-125m": 2048, - "petals-team/StableBeluga2": 8192, - "distilbert/distilgpt2": 1024, - "mistralai/Mistral-7B-Instruct-v0.2": 32768, - "gradientai/Llama-3-8B-Instruct-Gradient-1048k": 1040200, - "NousResearch/Hermes-2-Pro-Llama-3-8B": 8192, - "NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF": 8192, - "nvidia/Llama3-ChatQA-1.5-8B": 8192, - "microsoft/Phi-3-mini-4k-instruct": 4192, - "microsoft/Phi-3-mini-128k-instruct": 131072, - "mlabonne/Meta-Llama-3-120B-Instruct": 8192, - "cognitivecomputations/dolphin-2.9-llama3-8b": 8192, - "cognitivecomputations/dolphin-2.9-llama3-8b-gguf": 8192, - "cognitivecomputations/dolphin-2.8-mistral-7b-v02": 32768, - "cognitivecomputations/dolphin-2.5-mixtral-8x7b": 32768, - "TheBloke/dolphin-2.7-mixtral-8x7b-GGUF": 32768, - "deepseek-ai/DeepSeek-V2": 131072, - "deepseek-ai/DeepSeek-V2-Chat": 131072, - "claude-3-haiku": 200000, - }, - "deepseek": { - "deepseek-chat": 28672, - "deepseek-coder": 16384, - "deepseek-reasoner": 64000, - }, - "openrouter": { - "deepseek/deepseek-r1": 65536, - }, - "ernie": { - "ernie-bot-turbo": 4096, - "ernie-bot": 4096, - "ernie-bot-2": 4096, - "ernie-bot-2-base": 4096, - "ernie-bot-2-base-zh": 4096, - "ernie-bot-2-base-en": 4096, - "ernie-bot-2-base-en-zh": 4096, - "ernie-bot-2-base-zh-en": 4096, - }, - "fireworks": { - "llama-v2-7b": 4096, - "mixtral-8x7b-instruct": 4096, - "nomic-ai/nomic-embed-text-v1.5": 8192, - "llama-3.1-405B-instruct": 131072, - "llama-3.1-70B-instruct": 131072, - "llama-3.1-8B-instruct": 131072, - "mixtral-moe-8x22B-instruct": 65536, - "mixtral-moe-8x7B-instruct": 65536, - }, - "togetherai": {"Meta-Llama-3.1-70B-Instruct-Turbo": 128000}, -}