TheBloke's picture
New GGMLv3 format for breaking llama.cpp change May 19th commit 2d5db48
ba6f6e6
|
raw
history blame
4.03 kB
metadata
license: other
datasets:
  - ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered
inference: false

WizardLM - uncensored: An Instruction-following LLM Using Evol-Instruct

These files are GGML format model files for Eric Hartford's 'uncensored' version of WizardLM.

GGML files are for CPU inference using llama.cpp.

Eric did a fresh 7B training using the WizardLM method, on a dataset edited to remove all the "I'm sorry.." type ChatGPT responses.

Other repositories available

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
WizardLM-7B-uncensored.q4_0.bin q4_0 4bit 4.2GB 6GB 4-bit.
WizardLM-7B-uncensored.q4_1.bin q4_1 4bit 4.63GB 6GB 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models.
WizardLM-7B-uncensored.q5_0.bin q5_0 5bit 4.63GB 7GB 5-bit. Higher accuracy, higher resource usage and slower inference.
WizardLM-7B-uncensored.q5_1.bin q5_1 5bit 5.0GB 7GB 5-bit. Even higher accuracy, resource usage and slower inference.
WizardLM-7B-uncensored.q8_0.bin q8_0 5bit 9.0GB 11 5-bit. Even higher accuracy, resource usage and slower inference.

How to run in llama.cpp

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

./main -t 12 -m WizardLM-7B-uncensored.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 12 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.

Eric's original model card

This is WizardLM trained with a subset of the dataset - responses that contained alignment / moralizing were removed. The intent is to train a WizardLM that doesn't have alignment built-in, so that alignment (of any sort) can be added separately with for example with a RLHF LoRA.

Shout out to the open source AI/ML community, and everyone who helped me out, including Rohan, TheBloke, and Caseus

WizardLM's original model card

Overview of Evol-Instruct Evol-Instruct is a novel method using LLMs instead of humans to automatically mass-produce open-domain instructions of various difficulty levels and skills range, to improve the performance of LLMs.

info info