virevolai/logos-shift-client
Replace expensive LLM calls with finetunes automatically
This helps engineering teams automatically reduce costs and latency for applications that use expensive large language models (LLMs) like GPT or Claude. It observes your existing LLM calls and then automatically trains and deploys cheaper, faster fine-tuned models like Llama or Mistral when they're ready, without you having to manually manage A/B tests or deployments. It's for engineering or product teams building LLM-powered features in production.
No commits in the last 6 months. Available on PyPI.
Use this if you are deploying LLMs in production and want to automatically replace expensive, high-latency API calls with cheaper, faster fine-tuned models without manual intervention.
Not ideal if you prefer to manually manage every step of your model fine-tuning and deployment, or if cost and latency are not primary concerns for your LLM applications.
Stars
66
Forks
3
Language
Python
License
MIT
Category
Last pushed
Feb 15, 2024
Commits (30d)
0
Dependencies
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/virevolai/logos-shift-client"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Goekdeniz-Guelmez/mlx-lm-lora
Train Large Language Models on MLX.
uber-research/PPLM
Plug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.
VHellendoorn/Code-LMs
Guide to using pre-trained large language models of source code
ssbuild/chatglm_finetuning
chatglm 6b finetuning and alpaca finetuning
jarobyte91/pytorch_beam_search
A lightweight implementation of Beam Search for sequence models in PyTorch.