lukemarsden 295b2662e1 Get qlora mistral-7b fine tuning working on a single 4090 (#708)

2023-10-10 15:14:23 +09:00

..

cerebras

prepared dataset caching, other misc fixes (#665)

2023-10-02 21:07:24 -04:00

code-llama

prepared dataset caching, other misc fixes (#665)

2023-10-02 21:07:24 -04:00

falcon

prepared dataset caching, other misc fixes (#665)

2023-10-02 21:07:24 -04:00

gptj

prepared dataset caching, other misc fixes (#665)

2023-10-02 21:07:24 -04:00

jeopardy-bot

prepared dataset caching, other misc fixes (#665)

2023-10-02 21:07:24 -04:00

llama-2

prepared dataset caching, other misc fixes (#665)

2023-10-02 21:07:24 -04:00

mistral

Get qlora mistral-7b fine tuning working on a single 4090 (#708)

2023-10-10 15:14:23 +09:00

mpt-7b

prepared dataset caching, other misc fixes (#665)

2023-10-02 21:07:24 -04:00

openllama-3b

prepared dataset caching, other misc fixes (#665)

2023-10-02 21:07:24 -04:00

phi

prepared dataset caching, other misc fixes (#665)

2023-10-02 21:07:24 -04:00

pythia

prepared dataset caching, other misc fixes (#665)

2023-10-02 21:07:24 -04:00

pythia-12b

prepared dataset caching, other misc fixes (#665)

2023-10-02 21:07:24 -04:00

redpajama

prepared dataset caching, other misc fixes (#665)

2023-10-02 21:07:24 -04:00

replit-3b

prepared dataset caching, other misc fixes (#665)

2023-10-02 21:07:24 -04:00

xgen-7b

prepared dataset caching, other misc fixes (#665)

2023-10-02 21:07:24 -04:00