MinWoo(Daniel) Park's repositories
Gemini-API
The unofficial python package that returns response of Google Gemini through cookie values.
hf-transllm
LLMtranslator translates and generates text in multiple languages.
open-interview
Open Interview automates technical Q&A generation from resumes, offers document and audio outputs, and customizable settings for efficient interview prep.
all-about-llm
dsdanielpark's curation and categorization of resources on large language models, along with documentation.
llm-data-hub
A quick guide (especially) for trending instruction finetuning datasets
llama-cpp-python
Python bindings for llama.cpp
tokenizers
Fast State-of-the-Art Tokenizers optimized for Research and Production
abliterator
Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens
axolotl
Go ahead and axolotl questions
chroma
the AI-native open-source embedding database
flax
Flax is a neural network library for JAX that is designed for flexibility.
generative-ai-python
The Gemini API Python SDK enables developers to use Google's state-of-the-art generative AI models to build AI-powered features and applications.
gymnasium
An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
jax
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
llama.cpp
LLM inference in C/C++
llama_index
LlamaIndex is a data framework for your LLM applications
MedicalGPT
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO。
minbpe
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
ms-macro-web-search
A large-scale information-rich web dataset, featuring millions of real clicked query-document labels
openai-cookbook
Examples and guides for using the OpenAI API
openapi-typescript
Generate TypeScript types from OpenAPI 3 specs
openssl
TLS/SSL and crypto library
prometheus-eval
[Preprint] Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models
sniffnet
Comfortably monitor your Internet traffic 🕵️♂️
text-generation-inference
Large Language Model Text Generation Inference
wireshark
Read-only mirror of Wireshark's Git repository at https://gitlab.com/wireshark/wireshark. ⚠️ GitHub won't let us disable pull requests. ⚠️ THEY WILL BE IGNORED HERE ⚠️ Upload them at GitLab instead.
Yi-1.5
Yi-1.5 is an upgraded version of Yi, delivering stronger performance in coding, math, reasoning, and instruction-following capability.