README.md

metadata

inference: false
language:
  - en
license: other
model_type: llama
pipeline_tag: text-generation
tags:
  - facebook
  - meta
  - pytorch
  - llama
  - llama-2
  - gptq

Meta's Llama 2 13B GPTQ

These files are GPTQ model files for Meta's Llama 2 13B.

Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.

Repositories available

• GPTQ models for GPU inference, with multiple quantisation parameter options.
• 2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference
• Original unquantised fp16 model in pytorch format, for GPU inference and for further conversions

Prompt template: None

### System:\n{system}\n\n### User:\n{instruction}\n\n### Response:

Provided files

Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.

Each separate quant is in a different branch. See below for instructions on fetching from different branches.

Branch	Bits	Group Size	Act Order (desc_act)	File Size	ExLlama Compatible?	Made With	Description
main	4	128	False	7.26 GB	True	AutoGPTQ	Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options.
gptq-4bit-32g-actorder_True	4	32	True	8.00 GB	True	AutoGPTQ	4-bit, with Act Order and group size. 32g gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed.
gptq-4bit-64g-actorder_True	4	64	True	7.51 GB	True	AutoGPTQ	4-bit, with Act Order and group size. 64g uses less VRAM than 32g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed.
gptq-4bit-128g-actorder_True	4	128	True	7.26 GB	True	AutoGPTQ	4-bit, with Act Order and group size. 128g uses even less VRAM, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed.
gptq-8bit-128g-actorder_True	8	128	True	13.65 GB	False	AutoGPTQ	8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. Poor AutoGPTQ CUDA speed.
gptq-8bit-64g-actorder_True	8	64	True	13.95 GB	False	AutoGPTQ	8-bit, with group size 64g and Act Order for maximum inference quality. Poor AutoGPTQ CUDA speed.
gptq-8bit-128g-actorder_False	8	128	False	13.65 GB	False	AutoGPTQ	8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed.
gptq-8bit--1g-actorder_True	8	None	True	13.36 GB	False	AutoGPTQ	8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed.

How to download from branches

• In text-generation-webui, you can add :branch to the end of the download name, eg TheBloke/Llama-2-13B-GPTQ:gptq-4bit-32g-actorder_True
• With Git, you can clone a branch with:

git clone --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/Llama-2-13B-GPTQ`

• In Python Transformers code, the branch is the revision parameter; see below.

How to easily download and use this model in text-generation-webui.

Please make sure you're using the latest version of text-generation-webui.

It is strongly recommended to use the text-generation-webui one-click-installers unless you know how to make a manual install.

1. Click the Model tab.
2. Under Download custom model or LoRA, enter TheBloke/Llama-2-13B-GPTQ.

• To download from a specific branch, enter for example TheBloke/Llama-2-13B-GPTQ:gptq-4bit-32g-actorder_True
• see Provided Files above for the list of branches for each option.

3. Click Download.
4. The model will start downloading. Once it's finished it will say "Done"
5. In the top left, click the refresh icon next to Model.
6. In the Model dropdown, choose the model you just downloaded: Llama-2-13B-GPTQ
7. The model will automatically load, and is now ready for use!
8. If you want any custom settings, set them and then click Save settings for this model followed by Reload the Model in the top right.

• Note that you do not need to set GPTQ parameters any more. These are set automatically from the file quantize_config.json.

9. Once you're ready, click the Text Generation tab and enter a prompt to get started!

How to use this GPTQ model from Python code

First make sure you have AutoGPTQ installed:

GITHUB_ACTIONS=true pip install auto-gptq

Then try the following example code:

from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
import json
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig, get_gptq_peft_model


MODEL_PATH_GPTQ= "Llama-2-13B-GPTQ"
ADAPTER_DIR= "Llama-2-13B-GPTQ-Orca"

DEV = "cuda:0"

tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH_GPTQ, use_fast=True)
model = AutoGPTQForCausalLM.from_quantized(
    MODEL_PATH_GPTQ,
    use_safetensors=True,
    trust_remote_code=False,
    use_triton=True,
    device="cuda:0",
    warmup_triton=False,
    trainable=True,
    inject_fused_attention=True,
    inject_fused_mlp=False,
)
model = get_gptq_peft_model(
    model,
    model_id=ADAPTER_DIR,
    train_mode=False
)
model.eval()

Compatibility

The files provided will work with AutoGPTQ (CUDA and Triton modes), GPTQ-for-LLaMa (only CUDA has been tested), and Occ4m's GPTQ-for-LLaMa fork.