Stanford Alpaca 與 Alpaca.cpp

先前提到的「玩最近 Facebook Research (Meta) 放出來的 LLaMA」，在 2/24 公佈後，過沒多久 Stanford CRFM 團隊就丟出 fine-tuned 過的版本：「Alpaca: A Strong, Replicable Instruction-Following Model」，對應的討論在「Alpaca: A strong open-source instruction-following model (stanford.edu)」。

這個 tuning 是基於 LLaMA-7B：

We are releasing our findings about an instruction-following language model, dubbed Alpaca, which is fine-tuned from Meta’s LLaMA 7B model. We train the Alpaca model on 52K instruction-following demonstrations generated in the style of self-instruct using text-davinci-003. On the self-instruct evaluation set, Alpaca shows many behaviors similar to OpenAI’s text-davinci-003, but is also surprisingly small and easy/cheap to reproduce.

後來就再被包成一個專案 (改自 llama.cpp)，讓大家可以很方便的跑：「Alpaca.cpp」。

剛好可以比較，用 llama.cpp 跑的話是：

$ ./main -m ./models/7B/ggml-model-q4_0.bin -t 12 -n 128 -p ‘Explain FAANG. ‘

Explain FAANG. 🙂
The acronym “FAAN” is used for the five tech giants (Facebook, Apple, Amazon and Netflix) that are
taking over our lives:
15 November 2018 / by Amaraksha S [end of text]

而用 alpaca.cpp 跑的話回答品質好不少：

> Explain FAANG.
FAANG (or FANNG) refers to five technology companies, Facebook Inc., Apple Inc., Amazon.com Inc., Netflix Inc and Alphabet’s Google division that have become some of the most influential in recent years due to their rapid growth rates as well as their market capitalization values:
Facebook (FB), $596 billion; Apple (AAPL) ,$1,084.72 billion; Amazon (AMZN), $394.5 billion ; Netflix( NFLX ), $154.8 billion and Google’s parent company Alphabet Inc., ($GOOG,$GOOGL).
These companies have become some of the most influential in recent years due to their rapid growth rates as well as their market capitalization values: Facebook (FB),$307.15 billion; Apple(AAPL) , $924.86 billion ; Amazon (AMZN ), $783.

可以看到 instruction-following 後的差異，很像是 GPT-3.5 API 與 ChatGPT API 的輸出結果差異。

而這只是 LLaMA-7B 的成果，好像可以期待有人對 LLaMA-65B 做些事情？