philschmid.de - RSS feed philschmid.de

LLM Evaluation doesn't need to be complicated

philschmid.de·96w

Evaluating Open LLMs with MixEval: The Closest Benchmark to LMSYS Chatbot Arena

philschmid.de·97w

Train and Deploy open Embedding Models on Amazon SageMaker

philschmid.de·98w

Deploy Mixtral 8x7B on AWS Inferentia2 with Hugging Face Optimum

philschmid.de·99w

Fine-tune Llama 3 with PyTorch FSDP and Q-Lora on Amazon SageMaker

philschmid.de·100w

Fine-tune Embedding models for Retrieval Augmented Generation (RAG)

philschmid.de·101w

Understanding the Cost of Generative AI Models in Production

philschmid.de·102w

Deploy Llama 3 70B on AWS Inferentia2 with Hugging Face Optimum

philschmid.de·103w

Deploy open LLMs with vLLM on Hugging Face Inference Endpoints

philschmid.de·106w

Efficiently fine-tune Llama 3 with PyTorch FSDP and Q-Lora

philschmid.de·107w

Deploy Llama 3 on Amazon SageMaker

philschmid.de·108w

Accelerate Mixtral 8x7B with Speculative Decoding and Quantization on Amazon SageMaker

philschmid.de·110w

Deploy Llama 2 70B on AWS Inferentia2 with Hugging Face Optimum

philschmid.de·111w

Fine-Tune and Evaluate LLMs in 2024 with Amazon SageMaker

philschmid.de·113w

Evaluate LLMs with Hugging Face Lighteval on Amazon SageMaker

philschmid.de·114w

How to fine-tune Google Gemma with ChatML and Hugging Face TRL

philschmid.de·114w

RLHF in 2024 with DPO and Hugging Face

philschmid.de·120w

How to Fine-Tune LLMs in 2024 with Hugging Face

philschmid.de·120w

Scale LLM Inference on Amazon SageMaker with Multi-Replica Endpoints

philschmid.de·122w

Fine-tune Llama 7B on AWS Trainium

philschmid.de·125w

Log in to enable infinite scrolling