ManniX-ITA/Mixtral_7Bx2_MoE-GGUF

Mixtral 7Bx2 MoE - GGUF

• Model creator: hai
• Original model: Mixtral 7Bx2 MoE

Description

This repo contains GGUF format model files for hai's Mixtral 7Bx2 MoE.

About GGUF

GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.

Here is an incomplete list of clients and libraries that are known to support GGUF:

• llama.cpp. The source project for GGUF. Offers a CLI and a server option.
• text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
• KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
• GPT4All, a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
• LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
• LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.
• Faraday.dev, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
• llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
• candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.
• ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.

Repositories available

• 2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference
• hai's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions

Prompt template: Mixtral

[INST] {{ .System }} {{ .Prompt }} [/INST]

Compatibility

These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit d0cee0d

They are also compatible with many third party UIs and libraries - please see the list at the top of this README.

Explanation of quantisation methods

Click to see details

• q2_k: Uses Q4_K for the attention.vw and feed_forward.w2 tensors, Q2_K for the other tensors.
• q3_k_l: Uses Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K
• q3_k_m: Uses Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K
• q3_k_s: Uses Q3_K for all tensors
• q4_0: Original quant method, 4-bit.
• q4_1: Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models.
• q4_k_m: Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q4_K
• q4_k_s: Uses Q4_K for all tensors
• q5_0: Higher accuracy, higher resource usage and slower inference.
• q5_1: Even higher accuracy, resource usage and slower inference.
• q5_k_m: Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_K
• q5_k_s: Uses Q5_K for all tensors
• q6_k: Uses Q8_K for all tensors
• q8_0: Almost indistinguishable from float16. High resource use and slow. Not recommended for most users.

How to download GGUF files

Note for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.

The following clients/libraries will automatically download models for you, providing a list of available models to choose from:

• LM Studio
• LoLLMS Web UI
• Faraday.dev

In text-generation-webui

Under Download Model, you can enter the model repo: ManniX-ITA/Mixtral_7Bx2_MoE-GGUF and below it, a specific filename to download, such as: mixtral_7bx2_moe.Q4_K_M.gguf.

Then click Download.

On the command line, including multiple files at once

I recommend using the huggingface-hub Python library:

pip3 install huggingface-hub

Then you can download any individual model file to the current directory, at high speed, with a command like this:

huggingface-cli download ManniX-ITA/Mixtral_7Bx2_MoE-GGUF mixtral_7bx2_moe.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False

More advanced huggingface-cli download usage (click to read)

You can also download multiple files at once with a pattern:

huggingface-cli download ManniX-ITA/Mixtral_7Bx2_MoE-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'

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:

HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download ManniX-ITA/Mixtral_7Bx2_MoE-GGUF mixtral_7bx2_moe.Q4_K_M.gguf --local-dir . --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.

Example llama.cpp command

Make sure you are using llama.cpp from commit d0cee0d or later.

./main -ngl 35 -m mixtral_7bx2_moe.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "{prompt}"

Change -ngl 32 to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.

Change -c 32768 to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.

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

For other parameters and how to use them, please refer to the llama.cpp documentation

How to run in text-generation-webui

Further instructions can be found in the text-generation-webui documentation, here: text-generation-webui/docs/04 ‐ Model Tab.md.

How to run from Python code

You can use GGUF models from Python using the llama-cpp-python or ctransformers libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.

How to load this model in Python code, using llama-cpp-python

For full documentation, please see: llama-cpp-python docs.

First install the package

Run one of the following commands, according to your system:

# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python

# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python

Simple llama-cpp-python example code

from llama_cpp import Llama

# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
  model_path="./mixtral_7bx2_moe.Q4_K_M.gguf",  # Download the model file first
  n_ctx=32768,  # The max sequence length to use - note that longer sequence lengths require much more resources
  n_threads=8,            # The number of CPU threads to use, tailor to your system and the resulting performance
  n_gpu_layers=35         # The number of layers to offload to GPU, if you have GPU acceleration available
)

# Simple inference example
output = llm(
  "{prompt}", # Prompt
  max_tokens=512,  # Generate up to 512 tokens
  stop=["</s>"],   # Example stop token - not necessarily correct for this specific model! Please check before using.
  echo=True        # Whether to echo the prompt
)

# Chat Completion API

llm = Llama(model_path="./mixtral_7bx2_moe.Q4_K_M.gguf", chat_format="llama-2")  # Set chat_format according to the model you are using
llm.create_chat_completion(
    messages = [
        {"role": "system", "content": "You are a story writing assistant."},
        {
            "role": "user",
            "content": "Write a story about llamas."
        }
    ]
)

How to use with LangChain

Here are guides on using llama-cpp-python and ctransformers with LangChain:

• LangChain + llama-cpp-python
• LangChain + ctransformers

Original model card: hai's Mixtral 7Bx2 MoE

Mixtral MOE 2x7B

MoE of the following models :

• rwitz2/go-bruins-v2.1.1
• NurtureAI/neural-chat-7b-v3-16k
• meta-math/mncai/mistral-7b-dpo-v6

gpu code example

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
import math

## v2 models
model_path = "cloudyu/Mixtral_7Bx2_MoE"

tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
model = AutoModelForCausalLM.from_pretrained(
    model_path, torch_dtype=torch.float32, device_map='auto',local_files_only=False, load_in_4bit=True
)
print(model)
prompt = input("please input prompt:")
while len(prompt) > 0:
  input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to("cuda")

  generation_output = model.generate(
    input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2
  )
  print(tokenizer.decode(generation_output[0]))
  prompt = input("please input prompt:")

CPU example

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
import math

## v2 models
model_path = "cloudyu/Mixtral_7Bx2_MoE"

tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
model = AutoModelForCausalLM.from_pretrained(
    model_path, torch_dtype=torch.float32, device_map='cpu',local_files_only=False
)
print(model)
prompt = input("please input prompt:")
while len(prompt) > 0:
  input_ids = tokenizer(prompt, return_tensors="pt").input_ids

  generation_output = model.generate(
    input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2
  )
  print(tokenizer.decode(generation_output[0]))
  prompt = input("please input prompt:")