boxomcfoxo/YiffyEstopianMaid-13B-GGUF

YiffyEstopianMaid 13B - GGUF

• Model creator: Katy Vetteriano
• Original model: YiffyEstopianMaid 13B

Description

This repo contains GGUF format model files for Katy Vetteriano's YiffyEstopianMaid 13B.

These files were quantized using llama.cpp via ggml.ai's GGUF-my-repo space.

Prompt template: Alpaca

Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:

Recommended settings

• Default preset if using SillyTavern
• Temperature: 0.7
• Min-P: 0.3
• Amount to generate: 256
• Top P: 1
• Repetition penalty: 1.10

Licensing

As this model merge is based on Llama 2, it is subject to Meta's LLAMA 2 Community License terms. The appropriate license files are therefore included.

Models that were released under the Apache 2.0 license have also been used in the creation of this model merge. Due to Apache 2.0's permissive relicensing terms, the merge inherits the LLAMA 2 Community License and is not dual licensed. The Apache 2.0 license requires that attribution is included at the point of relicensing. This has been done by listing the models in the Notice file alongside the LLAMA 2 Community License notice.

Explanation of quantization methods

Click to see details

The new methods available are:

• GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
• GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
• GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
• GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
• GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw

Refer to the Provided Files table below to see what files use which methods, and how.

Provided files

Name	Quant method	Bits	Size	Max RAM required	Use case
yiffyestopianmaid-13b.Q2_K.gguf	Q2_K	2	4.85 GB	7.35 GB	significant quality loss - not recommended for most purposes
yiffyestopianmaid-13b.Q3_K_S.gguf	Q3_K_S	3	5.66 GB	8.16 GB	very small, high quality loss
yiffyestopianmaid-13b.Q3_K_M.gguf	Q3_K_M	3	6.34 GB	8.84 GB	very small, high quality loss
yiffyestopianmaid-13b.Q3_K_L.gguf	Q3_K_L	3	6.93 GB	9.43 GB	small, substantial quality loss
yiffyestopianmaid-13b.Q4_0.gguf	Q4_0	4	7.37 GB	9.87 GB	legacy; small, very high quality loss - prefer using Q3_K_M
yiffyestopianmaid-13b.Q4_K_S.gguf	Q4_K_S	4	7.42 GB	9.92 GB	small, greater quality loss
yiffyestopianmaid-13b.Q4_K_M.gguf	Q4_K_M	4	7.87 GB	10.37 GB	medium, balanced quality - recommended
yiffyestopianmaid-13b.Q5_0.gguf	Q5_0	5	8.97 GB	11.47 GB	legacy; medium, balanced quality - prefer using Q4_K_M
yiffyestopianmaid-13b.Q5_K_S.gguf	Q5_K_S	5	8.97 GB	11.47 GB	large, low quality loss - recommended
yiffyestopianmaid-13b.Q5_K_M.gguf	Q5_K_M	5	9.23 GB	11.73 GB	large, very low quality loss - recommended
yiffyestopianmaid-13b.Q6_K.gguf	Q6_K	6	10.68 GB	13.18 GB	very large, extremely low quality loss
yiffyestopianmaid-13b.Q8_0.gguf	Q8_0	8	13.83 GB	16.33 GB	very large, extremely low quality loss - not recommended

Note: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.

How to download GGUF files

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

In text-generation-webui

Under Download Model, you can enter the model repo: boxomcfoxo/YiffyEstopianMaid-13B-GGUF and below it, a specific filename to download, such as: yiffyestopianmaid-13b.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 boxomcfoxo/YiffyEstopianMaid-13B-GGUF yiffyestopianmaid-13b.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 boxomcfoxo/YiffyEstopianMaid-13B-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 boxomcfoxo/YiffyEstopianMaid-13B-GGUF yiffyestopianmaid-13b.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 yiffyestopianmaid-13b.Q4_K_M.gguf --color -c 4096 --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.\n\n### Instruction:\n{prompt}\n\n### Response:"

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

Change -c 4096 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="./yiffyestopianmaid-13b.Q4_K_M.gguf",  # Download the model file first
  n_ctx=4096,  # 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(
  "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:", # 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="./yiffyestopianmaid-13b.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