Björn Plüster (bjoernpl)

bjoernpl

User data from Github https://github.com/bjoernpl

Company:@ellamind @DiscoResearch

GitHub:@bjoernpl

Björn Plüster's repositories

llama_gradio_interface

Inference code for LLaMA models with Gradio Interface and rolling generation like ChatGPT

Language:PythonLicense:GPL-3.0Stargazers:48Issues:1Issues:0

GermanBenchmark

A repository containing the code for translating popular LLM benchmarks to German.

Language:PythonLicense:Apache-2.0Stargazers:25Issues:1Issues:3

lm-evaluation-harness-de

A framework for few-shot evaluation of autoregressive language models.

Language:PythonLicense:MITStargazers:13Issues:0Issues:0

cerebras-lora

Instruct-tune Cerebras-GPT on consumer hardware

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:8Issues:0Issues:0
Language:PythonStargazers:7Issues:1Issues:0

bitllama

Initial implementation of 1.58-bit Llama Model

Language:PythonLicense:Apache-2.0Stargazers:3Issues:1Issues:1

prismer_gradio_demo

The implementation of "Prismer: A Vision-Language Model with An Ensemble of Experts".

Language:PythonLicense:NOASSERTIONStargazers:3Issues:0Issues:0

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Language:PythonLicense:Apache-2.0Stargazers:1Issues:0Issues:0

FastEval

Fast evaluation of chat language models. Includes leaderboard.

Language:PythonLicense:Apache-2.0Stargazers:1Issues:0Issues:0
Stargazers:0Issues:0Issues:0

axolotl

Go ahead and axolotl questions

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0
Stargazers:0Issues:1Issues:0

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

distilabel

Distilabel is a framework for synthetic data and AI feedback for AI engineers that require high-quality outputs, full data ownership, and overall efficiency

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

epfl-megatron

distributed trainer for LLMs

Language:PythonLicense:NOASSERTIONStargazers:0Issues:0Issues:0

exllama

A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.

Language:PythonLicense:MITStargazers:0Issues:0Issues:0

github-deploy-notifications-hider

Chrome extension to hide deployment notifications in GitHub pull requests

Stargazers:0Issues:0Issues:0

inspect_ai

Inspect: A framework for large language model evaluations

Language:PythonLicense:MITStargazers:0Issues:0Issues:0

llama-pipeline-parallel

A prototype repo for hybrid training of pipeline parallel and distributed data parallel with comments on core code snippets. Feel free to copy code and launch discussions about the problems you have encoured.

Language:PythonStargazers:0Issues:0Issues:0

llama_index

LlamaIndex is a data framework for your LLM applications

License:MITStargazers:0Issues:0Issues:0

LMFlow

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Model for All.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

NeedleInAHaystack_DE

Doing simple retrieval from LLM models at various context lengths to measure accuracy

Language:Jupyter NotebookLicense:NOASSERTIONStargazers:0Issues:0Issues:0

Open-Assistant

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

qlora_oasst

QLoRA: Efficient Finetuning of Quantized LLMs

Language:Jupyter NotebookLicense:MITStargazers:0Issues:0Issues:0
Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

text-dedup-oscar2023

All-in-one text de-duplication

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:0Issues:0Issues:0

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0