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.

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

Initializing Model objects for different model names can take > 10s. #1308

Open
zer0dss opened this issue Nov 22, 2024 · 2 comments
Open

Initializing Model objects for different model names can take > 10s. #1308

zer0dss opened this issue Nov 22, 2024 · 2 comments
Labels
bug Something isn't working

Comments

@zer0dss
Copy link
Collaborator

zer0dss commented Nov 22, 2024

from edsl import Model
import time


models_list = [['Austism/chronos-hermes-13b-v2', 'deep_infra', 0], ['BAAI/bge-base-en-v1.5', 'together', 1], ['BAAI/bge-large-en-v1.5', 'together', 2], ['Gryphe/MythoMax-L2-13b', 'deep_infra', 3], ['Gryphe/MythoMax-L2-13b', 'together', 4], ['Gryphe/MythoMax-L2-13b-Lite', 'together', 5], ['Meta-Llama/Llama-Guard-7b', 'together', 6], ['NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO', 'together', 7], ['NousResearch/Nous-Hermes-2-Yi-34B', 'together', 8], ['Qwen/Qwen1.5-110B-Chat', 'together', 9], ['Qwen/Qwen1.5-72B-Chat', 'together', 10], ['Qwen/Qwen2-72B-Instruct', 'deep_infra', 11], ['Qwen/Qwen2-72B-Instruct', 'together', 12], ['Qwen/Qwen2-7B-Instruct', 'deep_infra', 13], ['Qwen/Qwen2.5-72B-Instruct', 'deep_infra', 14], ['Salesforce/Llama-Rank-V1', 'together', 15], ['Sao10K/L3-70B-Euryale-v2.1', 'deep_infra', 16], ['Sao10K/L3.1-70B-Euryale-v2.2', 'deep_infra', 17], ['WhereIsAI/UAE-Large-V1', 'together', 18], ['amazon.titan-text-express-v1', 'bedrock', 19], ['amazon.titan-text-lite-v1', 'bedrock', 20], ['anthropic.claude-3-5-sonnet-20240620-v1:0', 'bedrock', 21], ['anthropic.claude-3-haiku-20240307-v1:0', 'bedrock', 22], ['anthropic.claude-3-opus-20240229-v1:0', 'bedrock', 23], ['anthropic.claude-3-sonnet-20240229-v1:0', 'bedrock', 24], ['anthropic.claude-instant-v1', 'bedrock', 25], ['anthropic.claude-v2', 'bedrock', 26], ['anthropic.claude-v2:1', 'bedrock', 27], ['azure:gpt-4o', 'azure', 28], ['azure:gpt-4o-mini', 'azure', 29], ['claude-3-5-sonnet-20240620', 'anthropic', 30], ['claude-3-haiku-20240307', 'anthropic', 31], ['claude-3-opus-20240229', 'anthropic', 32], ['claude-3-sonnet-20240229', 'anthropic', 33], ['codellama/CodeLlama-34b-Instruct-hf', 'together', 34], ['codestral-2405', 'mistral', 35], ['cohere.command-light-text-v14', 'bedrock', 36], ['cohere.command-r-plus-v1:0', 'bedrock', 37], ['cohere.command-r-v1:0', 'bedrock', 38], ['cohere.command-text-v14', 'bedrock', 39], ['cursor/Llama-3-8b-hf', 'together', 40], ['databricks/dbrx-instruct', 'together', 41], ['deepseek-ai/deepseek-llm-67b-chat', 'together', 42], ['gemini-1.0-pro', 'google', 43], ['gemini-1.5-flash', 'google', 44], ['gemini-1.5-pro', 'google', 45], ['gemini-pro', 'google', 46], ['gemma-7b-it', 'groq', 47], ['gemma2-9b-it', 'groq', 48], ['google/gemma-2-27b-it', 'deep_infra', 49], ['google/gemma-2-27b-it', 'together', 50], ['google/gemma-2-9b-it', 'deep_infra', 51], ['google/gemma-2-9b-it', 'together', 52], ['google/gemma-2b-it', 'together', 53], ['gpt-3.5-turbo', 'openai', 54], ['gpt-3.5-turbo-0125', 'openai', 55], ['gpt-3.5-turbo-0301', 'openai', 56], ['gpt-3.5-turbo-0613', 'openai', 57], ['gpt-3.5-turbo-1106', 'openai', 58], ['gpt-3.5-turbo-16k', 'openai', 59], ['gpt-3.5-turbo-16k-0613', 'openai', 60], ['gpt-3.5-turbo-instruct', 'openai', 61], ['gpt-3.5-turbo-instruct-0914', 'openai', 62], ['gpt-4', 'openai', 63], ['gpt-4-0125-preview', 'openai', 64], ['gpt-4-0613', 'openai', 65], ['gpt-4-1106-preview', 'openai', 66], ['gpt-4-1106-vision-preview', 'openai', 67], ['gpt-4-turbo', 'openai', 68], ['gpt-4-turbo-2024-04-09', 'openai', 69], ['gpt-4-turbo-preview', 'openai', 70], ['gpt-4-vision-preview', 'openai', 71], ['gpt-4o', 'openai', 72], ['gpt-4o-2024-05-13', 'openai', 73], ['lizpreciatior/lzlv_70b_fp16_hf', 'deep_infra', 74], ['llama-3.1-70b-versatile', 'groq', 75], ['llama-3.1-8b-instant', 'groq', 76], ['llama-guard-3-8b', 'groq', 77], ['llama3-70b-8192', 'groq', 78], ['llama3-8b-8192', 'groq', 79], ['llama3-groq-70b-8192-tool-use-preview', 'groq', 80], ['llama3-groq-8b-8192-tool-use-preview', 'groq', 81], ['meta-llama/Llama-2-13b-chat-hf', 'together', 82], ['meta-llama/Llama-2-70b-hf', 'together', 83], ['meta-llama/Llama-2-7b-chat-hf', 'together', 84], ['meta-llama/Llama-3-70b-chat-hf', 'together', 85], ['meta-llama/Llama-3-8b-chat-hf', 'together', 86], ['meta-llama/LlamaGuard-2-8b', 'together', 87], ['meta-llama/Meta-Llama-3-70B-Instruct', 'deep_infra', 88], ['meta-llama/Meta-Llama-3-70B-Instruct-Lite', 'together', 89], ['meta-llama/Meta-Llama-3-70B-Instruct-Turbo', 'together', 90], ['meta-llama/Meta-Llama-3-8B-Instruct', 'deep_infra', 91], ['meta-llama/Meta-Llama-3-8B-Instruct-Lite', 'together', 92], ['meta-llama/Meta-Llama-3-8B-Instruct-Turbo', 'together', 93], ['meta-llama/Meta-Llama-3.1-405B-Instruct', 'deep_infra', 94], ['meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo', 'together', 95], ['meta-llama/Meta-Llama-3.1-70B-Instruct', 'deep_infra', 96], ['meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo', 'together', 97], ['meta-llama/Meta-Llama-3.1-8B-Instruct', 'deep_infra', 98], ['meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo', 'together', 99], ['meta-llama/Meta-Llama-Guard-3-8B', 'together', 100], ['meta.llama3-1-405b-instruct-v1:0', 'bedrock', 101], ['meta.llama3-1-70b-instruct-v1:0', 'bedrock', 102], ['meta.llama3-1-8b-instruct-v1:0', 'bedrock', 103], ['meta.llama3-70b-instruct-v1:0', 'bedrock', 104], ['meta.llama3-8b-instruct-v1:0', 'bedrock', 105], ['microsoft/Phi-3-medium-4k-instruct', 'deep_infra', 106], ['microsoft/WizardLM-2-7B', 'deep_infra', 107], ['microsoft/WizardLM-2-8x22B', 'deep_infra', 108], ['microsoft/WizardLM-2-8x22B', 'together', 109], ['mistral-embed', 'mistral', 110], ['mistral-large-2407', 'mistral', 111], ['mistral-medium-latest', 'mistral', 112], ['mistral-small-2409', 'mistral', 113], ['mistral-small-latest', 'mistral', 114], ['mistral.mistral-7b-instruct-v0:2', 'bedrock', 115], ['mistral.mistral-large-2402-v1:0', 'bedrock', 116], ['mistral.mixtral-8x7b-instruct-v0:1', 'bedrock', 117], ['mistralai/Mistral-7B-Instruct-v0.1', 'together', 118], ['mistralai/Mistral-7B-Instruct-v0.2', 'together', 119], ['mistralai/Mistral-7B-Instruct-v0.3', 'deep_infra', 120], ['mistralai/Mistral-7B-Instruct-v0.3', 'together', 121], ['mistralai/Mistral-7B-v0.1', 'together', 122], ['mistralai/Mistral-Nemo-Instruct-2407', 'deep_infra', 123], ['mistralai/Mixtral-8x22B-Instruct-v0.1', 'together', 124], ['mistralai/Mixtral-8x7B-Instruct-v0.1', 'deep_infra', 125], ['mistralai/Mixtral-8x7B-Instruct-v0.1', 'together', 126], ['mistralai/Mixtral-8x7B-v0.1', 'together', 127], ['mixtral-8x7b-32768', 'groq', 128], ['open-mistral-7b', 'mistral', 129], ['open-mistral-nemo-2407', 'mistral', 130], ['open-mixtral-8x22b', 'mistral', 131], ['open-mixtral-8x7b', 'mistral', 132], ['openbmb/MiniCPM-Llama3-V-2_5', 'deep_infra', 133], ['openchat/openchat_3.5', 'deep_infra', 134], ['pixtral-12b-2409', 'mistral', 135], ['test', 'test', 136], ['togethercomputer/StripedHyena-Nous-7B', 'together', 137], ['togethercomputer/m2-bert-80M-2k-retrieval', 'together', 138], ['togethercomputer/m2-bert-80M-32k-retrieval', 'together', 139], ['togethercomputer/m2-bert-80M-8k-retrieval', 'together', 140], ['upstage/SOLAR-10.7B-Instruct-v1.0', 'together', 141]]
model_names = [ x[0] for x in  models_list]

for model_name in model_names:
    start = time.time()
    model = Model(model_name)
    print(f"Exec time for initializing {model_name} model",time.time()-start)

Output example

Screenshot 2024-11-22 at 18 21 43
@zer0dss zer0dss added the bug Something isn't working label Nov 22, 2024
@johnjosephhorton
Copy link
Contributor

Hmm - good catch. Any ideas?

@zer0dss
Copy link
Collaborator Author

zer0dss commented Nov 23, 2024

I assume there are some HTTP api calls.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

No branches or pull requests

2 participants