Dolphin 2.5 Mixtral 8X7B Open-source Language Model - Free Deployment, Capable of Handling Multiple Types of Natural Language Processing Tasks

Dolphin 2.5 Mixtral 8x7b GPTQ

Developed by TheBloke

Dolphin 2.5 Mixtral 8X7B is a large language model developed by Eric Hartford based on the Mixtral architecture, fine-tuned on multiple high-quality datasets, suitable for various natural language processing tasks.

Large Language Model

Transformers

EnglishOpen Source License:Apache-2.0 #Mixture of Experts #Long Sequence Processing #Instruction Fine-tuning

Downloads 164

Release Time : 12/14/2023

Model Overview

This model is a large language model based on the Mixtral 8X7B architecture, fine-tuned with the Dolphin dataset, supporting various natural language processing tasks including text generation, code generation, and more.

Model Features

Mixture of Experts

Based on the Mixtral 8X7B architecture, it employs a mixture of experts design to efficiently handle complex tasks.

High-quality Fine-tuning

Fine-tuned using multiple high-quality datasets (e.g., Dolphin, Airoboros, Synthia, etc.) to enhance model performance.

Long Context Support

Supports context lengths up to 8192, making it suitable for long-text tasks.

Quantization Support

Offers multiple quantization versions (e.g., 3-bit, 4-bit, 8-bit) to reduce hardware requirements.

Model Capabilities

Text generation

Code generation

Natural language understanding

Instruction following

Use Cases

Code Generation

Code Completion

Generates completion code based on user-provided code snippets.

Produces high-quality code completion suggestions.

Code Explanation

Explains the functionality and logic of complex code.

Provides clear and understandable code explanations.

Text Generation

Creative Writing

Generates creative texts such as stories and poems.

Produces imaginative and creative text content.

Technical Documentation

Generates technical documents or instructions based on user requirements.

Produces well-structured and accurate technical documentation.

🚀 Dolphin 2.5 Mixtral 8X7B - GPTQ

This repository offers GPTQ model files for Eric Hartford's Dolphin 2.5 Mixtral 8X7B, providing multiple quantisation options for different hardware and requirements.

📦 Model Information

Property	Details
Base Model	ehartford/dolphin-2.5-mixtral-8x7b
Datasets	ehartford/dolphin, jondurbin/airoboros-2.2.1, ehartford/dolphin-coder, migtissera/Synthia-v1.3, teknium/openhermes, ise-uiuc/Magicoder-OSS-Instruct-75K, ise-uiuc/Magicoder-Evol-Instruct-110K, LDJnr/Pure-Dove
Inference	false
Language	en
License	apache-2.0
Model Creator	Eric Hartford
Model Name	Dolphin 2.5 Mixtral 8X7B
Model Type	mixtral
Prompt Template	'<
Quantized By	TheBloke

🌐 Repositories available

💬 Prompt template: ChatML

<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

🖥️ Known compatible clients / servers

GPTQ models are currently supported on Linux (NVidia/AMD) and Windows (NVidia only). macOS users: please use GGUF models.

Mixtral GPTQs currently have special requirements - see Description above.

📄 Provided files, and GPTQ parameters

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.

Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers.

Explanation of GPTQ parameters

Bits: The bit size of the quantised model.
GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
Act Order: True or False. Also known as desc_act. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama and Mistral models in 4-bit.

Branch	Bits	GS	Act Order	Damp %	GPTQ Dataset	Seq Len	Size	ExLlama	Desc
main	4	None	Yes	0.1	VMware Open Instruct	8192	23.81 GB	No	4-bit, with Act Order. No group size, to lower VRAM requirements.
gptq-4bit-128g-actorder_True	4	128	Yes	0.1	VMware Open Instruct	8192	24.70 GB	No	4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy.
gptq-4bit-32g-actorder_True	4	32	Yes	0.1	VMware Open Instruct	8192	27.42 GB	No	4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage.
gptq-3bit--1g-actorder_True	3	None	Yes	0.1	VMware Open Instruct	8192	18.01 GB	No	3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g.
gptq-3bit-128g-actorder_True	3	128	Yes	0.1	VMware Open Instruct	8192	18.85 GB	No	3-bit, with group size 128g and act-order. Higher quality than 128g-False.
gptq-3bit-32g-actorder_True	3	32	Yes	0.1	VMware Open Instruct	8192	21.43 GB	No	3-bit, with group size 64g and act-order. Highest quality 3-bit option.
gptq-8bit--1g-actorder_True	8	None	Yes	0.1	VMware Open Instruct	8192	47.04 GB	No	8-bit, with Act Order. No group size, to lower VRAM requirements.
gptq-8bit-128g-actorder_True	8	128	Yes	0.1	VMware Open Instruct	8192	48.10 GB	No	8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy.

⬇️ How to download, including from branches

In text-generation-webui

To download from the main branch, enter TheBloke/dolphin-2.5-mixtral-8x7b-GPTQ in the "Download model" box.

To download from another branch, add :branchname to the end of the download name, eg TheBloke/dolphin-2.5-mixtral-8x7b-GPTQ:gptq-4bit-128g-actorder_True

From the command line

I recommend using the huggingface-hub Python library:

pip3 install huggingface-hub

To download the main branch to a folder called dolphin-2.5-mixtral-8x7b-GPTQ:

mkdir dolphin-2.5-mixtral-8x7b-GPTQ
huggingface-cli download TheBloke/dolphin-2.5-mixtral-8x7b-GPTQ --local-dir dolphin-2.5-mixtral-8x7b-GPTQ --local-dir-use-symlinks False

To download from a different branch, add the --revision parameter:

mkdir dolphin-2.5-mixtral-8x7b-GPTQ
huggingface-cli download TheBloke/dolphin-2.5-mixtral-8x7b-GPTQ --revision gptq-4bit-128g-actorder_True --local-dir dolphin-2.5-mixtral-8x7b-GPTQ --local-dir-use-symlinks False

More advanced huggingface-cli download usage

If you remove the --local-dir-use-symlinks False parameter, the files will instead be stored in the central Hugging Face cache directory (default location on Linux is: ~/.cache/huggingface), and symlinks will be added to the specified --local-dir, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.

The cache location can be changed with the HF_HOME environment variable, and/or the --cache-dir parameter to huggingface-cli.

For more documentation on downloading with huggingface-cli, please see: HF -> Hub Python Library -> Download files -> Download from the CLI.

To accelerate downloads on fast connections (1Gbit/s or higher), install hf_transfer:

pip3 install hf_transfer

And set environment variable HF_HUB_ENABLE_HF_TRANSFER to 1:

mkdir dolphin-2.5-mixtral-8x7b-GPTQ
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/dolphin-2.5-mixtral-8x7b-GPTQ --local-dir dolphin-2.5-mixtral-8x7b-GPTQ --local-dir-use-symlinks False

Windows Command Line users: You can set the environment variable by running set HF_HUB_ENABLE_HF_TRANSFER=1 before the download command.

With `git` (not recommended)

To clone a specific branch with git, use a command like this:

git clone --single-branch --branch gptq-4bit-128g-actorder_True https://huggingface.co/TheBloke/dolphin-2.5-mixtral-8x7b-GPTQ

Note that using Git with HF repos is strongly discouraged. It will be much slower than using huggingface-hub, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the .git folder as a blob.)

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

NOTE: Requires:

Transformers 4.36.0, or Transformers 4.37.0.dev0 from Github
Either AutoGPTQ 0.6 compiled from source and Loader: AutoGPTQ,
or, Loader: Transformers, if you installed Transformers from Github: pip3 install git+https://github.com/huggingface/transformers

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're sure you know how to make a manual install.

Click the Model tab.
Under Download custom model or LoRA, enter TheBloke/dolphin-2.5-mixtral-8x7b-GPTQ.
- To download from a specific branch, enter for example TheBloke/dolphin-2.5-mixtral-8x7b-GPTQ:gptq-4bit-128g-actorder_True
- see Provided Files above for the list of branches for each

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご