Hugging Face's logo

TheBloke
/
alpaca-lora-65B-GGML

Model card Files Community
7
alpaca-lora-65B-GGML / README.md
TheBloke's picture
TheBloke
Updating model files
dcea1dc
preview code
|
raw
history blame
4.15 kB
metadata
license: other
inference: false
TheBlokeAI

Quantised GGMLs of alpaca-lora-65B

Quantised 4bit and 5bit GGMLs of changsung's alpaca-lora-65B for CPU inference with llama.cpp.

I also have 4bit GPTQ files for GPU inference available here: TheBloke/alpaca-lora-65B-GPTQ-4bit.

THE FILES IN MAIN BRANCH REQUIRES LATEST LLAMA.CPP (May 19th 2023 - commit 2d5db48)!

llama.cpp recently made another breaking change to its quantisation methods - https://github.com/ggerganov/llama.cpp/pull/1508

I have quantised the GGML files in this repo with the latest version. Therefore you will require llama.cpp compiled on May 19th or later (commit 2d5db48 or later) to use them.

For files compatible with the previous version of llama.cpp, please see branch previous_llama_ggmlv2.

Provided files

Name Quant method Bits Size RAM required Use case
alpaca-lora-65B.ggmlv3.q4_0.bin q4_0 4bit 40.8GB 43GB 4bit.
alpaca-lora-65B.ggmlv3.q4_1.bin q4_1 4bit 44.9GB 43GB 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models.
alpaca-lora-65B.ggmlv3.q5_0.bin q5_0 5bit 44.9GB 47GB 5bit. Higher quality than 4bit, at cost of slightly higher resources.
alpaca-lora-65B.ggmlv3.q5_1.bin q5_1 5bit 49GB 51GB 5bit. Slightly higher resource usage and quality than q5_0.

How to run in llama.cpp

I use the following command line; adjust for your tastes and needs:

./main -t 8 -m alpaca-lora-65B.ggmlv3.q4_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
Write a story about llamas
### Response:"

Change -t 8 to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use -t 8.

If you want to have a chat-style conversation, replace the -p <PROMPT> argument with -i -ins

How to run in text-generation-webui

Further instructions here: text-generation-webui/docs/llama.cpp-models.md.

Note: at this time text-generation-webui may not support the new May 19th llama.cpp quantisation methods for q4_0, q4_1 and q8_0 files.

Want to support my work?

I've had a lot of people ask if they can contribute. I love providing models and helping people, but it is starting to rack up pretty big cloud computing bills.

So if you're able and willing to contribute, it'd be most gratefully received and will help me to keep providing models, and work on various AI projects.

Donaters will get priority support on any and all AI/LLM/model questions, and I'll gladly quantise any model you'd like to try.

Original model card not provided

No model card was provided in changsung's original repository.

Based on the name, I assume this is the result of fine tuning using the original GPT 3.5 Alpaca dataset. It is unknown as to whether the original Stanford data was used, or the cleaned tloen/alpaca-lora variant.