Pinned Repositories
adversarial-density
cppn_research
distillation
Distill language models, online or offline
dotfiles
fine-tune-fuyu
gan-skeleton
skeleton code for conditional gan training in tensorflow
gpt-fast
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
lit-gpt
Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
llama.cpp
Port of Facebook's LLaMA model in C/C++
pixie
Instant Kubernetes-Native Application Observability
phillip-kravtsov's Repositories
phillip-kravtsov/fine-tune-fuyu
phillip-kravtsov/distillation
Distill language models, online or offline
phillip-kravtsov/dotfiles
phillip-kravtsov/gpt-fast
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
phillip-kravtsov/lit-gpt
Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
phillip-kravtsov/pixie
Instant Kubernetes-Native Application Observability
phillip-kravtsov/adversarial-density
phillip-kravtsov/cppn_research
phillip-kravtsov/gan-skeleton
skeleton code for conditional gan training in tensorflow
phillip-kravtsov/llama.cpp
Port of Facebook's LLaMA model in C/C++
phillip-kravtsov/mlab-tools
mlab tools
phillip-kravtsov/neural-cube
3x3 rubik's cube solver that uses neural nets as predictors and heuristics
phillip-kravtsov/nmep-hw-6
nmep hw 6
phillip-kravtsov/openai-cookbook
Examples and guides for using the OpenAI API
phillip-kravtsov/phillip-kravtsov.github.io
phillip-kravtsov/qlora
QLoRA: Efficient Finetuning of Quantized LLMs
phillip-kravtsov/renegade
On-chain dark pool. MPC for anonymous crosses at midpoint prices.
phillip-kravtsov/sol-token-list
phillip-kravtsov/tensorflow
An Open Source Machine Learning Framework for Everyone
phillip-kravtsov/tensorrt
TensorFlow/TensorRT integration
phillip-kravtsov/token-transfer
estimate logprobs from one tokenizer under a different tokenizer
phillip-kravtsov/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
phillip-kravtsov/unit-node-sdk
phillip-kravtsov/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs