Akshat Bubna

Cofounder of Modal

Starred Projects (22)

rlm by alexzhang13

Inference library for Recursive Language Models (RLMs)

tobi:

vincentweisser:

john-b-yang:

jeffchuber:

Created 1 month ago

Updated 4 days ago

ArcticTraining by snowflakedb

LLM post-training acceleration framework

luiscape:

stas00:

Created 1 year ago

Updated 5 days ago

cwm by facebookresearch

LLM for advanced code generation and reasoning

vincentweisser:

Created 4 months ago

Updated 1 month ago

avataRL by tokenbender

Train language models from scratch using pure reinforcement learning

atroyn:

vincentweisser:

Created 8 months ago

Updated 4 months ago

vui by fluxions-ai

Conversational speech models for on-device use

tobi:

luiscape:

Created 7 months ago

Updated 2 months ago

KernelBench by ScalingIntelligence

Benchmark for LLMs generating GPU kernels from PyTorch ops

luiscape:

xiezhq-hermann:

chiphuyen:

Created 1 year ago

Updated 1 week ago

SWE-bench by SWE-bench

Benchmark for evaluating LLMs on real-world GitHub issues

patrickvonplaten:

pgarbacki:

shizhediao:

transitive-bullshit:

Created 2 years ago

Updated 5 days ago

SWE-Gym by SWE-Gym

Environment for training software engineering agents

vincentweisser:

hammer:

shizhediao:

winglian:

Created 1 year ago

Updated 6 months ago

omi by BasedHardware

AI wearable for real-time audio capture and intelligent processing

ogabrielluiz:

AlexCheema:

omarsar:

taranjeet:

Created 1 year ago

Updated 1 day ago

axolotl by axolotl-ai-cloud

CLI tool for streamlined post-training of AI models

tobi:

jn2clark:

beyang:

zhyncs:

Created 2 years ago

Updated 4 days ago

mamba-chat by redotvideo

Chat LLM based on state-space model architecture

mlabonne:

vincentweisser:

marcklingen:

Created 2 years ago

Updated 1 year ago

openrouter-runner by OpenRouterTeam

Inference engine for deploying open-source models

vincentweisser:

hammer:

transitive-bullshit:

louisgv:

Created 2 years ago

Updated 4 months ago

OpenPipe by OpenPipe

Fine-tuning platform for cheaper models

pgarbacki:

marcklingen:

transitive-bullshit:

chiphuyen:

Created 2 years ago

Updated 1 year ago

llm-finetuning by modal-labs

LLM fine-tuning guide using Modal and Axolotl

beyang:

shyamal-anadkat:

hammer:

erikbern:

Created 2 years ago

Updated 3 months ago

modal_finetune_sql by run-llama

Walkthrough for fine-tuning LLaMa 2 7B on Text-to-SQL datasets

jerryjliu:

Created 2 years ago

Updated 2 years ago

instructor by 567-labs

SDK for structured LLM outputs using Pydantic models

cournape:

gregpr07:

jxnl:

willccbb:

Created 2 years ago

Updated 1 day ago

functime by functime-org

Python library for time-series ML at scale

ankane:

changhiskhan:

Created 2 years ago

Updated 3 months ago

llm-engine by scaleapi

Open-source engine for fine-tuning and serving LLMs

alexandr:

hammer:

zhuohan123:

bryanhelmig:

Created 2 years ago

Updated 2 days ago

developer by smol-ai

Agent for embedding a developer in your app

vanpelt:

chiphuyen:

shyamal-anadkat:

mchiang0610:

Created 2 years ago

Updated 1 year ago

ask-fsdl by the-full-stack

RAG app for querying educational materials

shyamal-anadkat:

Created 3 years ago

Updated 1 year ago

cbp-translate by elanmart

Cyberpunk-style video translation with modern DL stack

nat:

ggerganov:

hammer:

luiscape:

Created 3 years ago

Updated 3 years ago

modal-examples by modal-labs

Examples for Modal, a platform for running cloud applications

luiscape:

gakonst:

stevenhao:

hammer:

Created 3 years ago

Updated 3 days ago

Feedback? Help us improve.