GitHub - Giskard-AI/giskard: š¢ The testing framework for ML models, from tabular to LLMs
ā” LitGPT
Pretrain, finetune, evaluate, and deploy 20+ LLMs on your own data
Uses the latest state-of-the-art techniques:
ā flash attention ā fp4/8/16/32 ā LoRA, QLoRA, Adapter (v1, v2) ā FSDP ā 1-1000+ GPUs/TPUs
Lightning AI ā¢ Models ā¢ Quick start ā¢ Inference ā¢ Finetune ā¢ Pretrain ā¢ Deploy ā¢ Features ā¢ Training recipes (YAML)
Finetune, pretrain and d... See more
Pretrain, finetune, evaluate, and deploy 20+ LLMs on your own data
Uses the latest state-of-the-art techniques:
ā flash attention ā fp4/8/16/32 ā LoRA, QLoRA, Adapter (v1, v2) ā FSDP ā 1-1000+ GPUs/TPUs
Lightning AI ā¢ Models ā¢ Quick start ā¢ Inference ā¢ Finetune ā¢ Pretrain ā¢ Deploy ā¢ Features ā¢ Training recipes (YAML)
Finetune, pretrain and d... See more
Lightning-AI ā¢ GitHub - Lightning-AI/litgpt: Pretrain, finetune, deploy 20+ LLMs on your own data. Uses state-of-the-art techniques: flash attention, FSDP, 4-bit, LoRA, and more.
Onyxia Datalab
The modern datascience stack made accessible
Pool computing resources and provide a state of the art work environment to your data scientists without relying on big tech closed-source software.
The modern datascience stack made accessible
Pool computing resources and provide a state of the art work environment to your data scientists without relying on big tech closed-source software.
Onyxia Datalab
ANY
LLM of your choice, statistical methods, or NLP models that runs
locally on your machine
:
- G-Eval
- Summarization
- Answer Relevancy
- Faithfulness
- Contextual Recall
- Contextual Precision
- RAGAS
- Hallucination
- Toxicity
- Bias
- etc.
GitHub - confident-ai/deepeval: The LLM Evaluation Framework
š³ Galileo LLM Studio
Algorithm-powered LLMOps Platform
Find the best prompt, inspect data errors while fine-tuning, monitor LLM outputs in real-time. All in one powerful, collaborative platform.