TheBloke/Inkbot-13B-4k-GGUF

Chat & support: TheBloke's Discord server

Want to contribute? TheBloke's Patreon page

TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)

---

Inkbot 13B 4K - GGUF

• Model creator: Tostino
• Original model: Inkbot 13B 4K

Description

This repo contains GGUF format model files for Tostino's Inkbot 13B 4K.

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 incomplate 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.
• LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
• 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.
• ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
• 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.

Repositories available

• AWQ model(s) for GPU inference.
• GPTQ models for GPU inference, with multiple quantisation parameter options.
• 2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference
• Tostino's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions

Prompt template: Inkbot

<#meta#>
- Date: [DATE]
- Task: [TASK TYPE]
<#system#>
{system_message}
<#chat#>
<#user#>
{prompt}
<#bot#>

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

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
inkbot-13b-4k.Q2_K.gguf	Q2_K	2	5.43 GB	7.93 GB	smallest, significant quality loss - not recommended for most purposes
inkbot-13b-4k.Q3_K_S.gguf	Q3_K_S	3	5.66 GB	8.16 GB	very small, high quality loss
inkbot-13b-4k.Q3_K_M.gguf	Q3_K_M	3	6.34 GB	8.84 GB	very small, high quality loss
inkbot-13b-4k.Q3_K_L.gguf	Q3_K_L	3	6.93 GB	9.43 GB	small, substantial quality loss
inkbot-13b-4k.Q4_0.gguf	Q4_0	4	7.37 GB	9.87 GB	legacy; small, very high quality loss - prefer using Q3_K_M
inkbot-13b-4k.Q4_K_S.gguf	Q4_K_S	4	7.41 GB	9.91 GB	small, greater quality loss
inkbot-13b-4k.Q4_K_M.gguf	Q4_K_M	4	7.87 GB	10.37 GB	medium, balanced quality - recommended
inkbot-13b-4k.Q5_0.gguf	Q5_0	5	8.97 GB	11.47 GB	legacy; medium, balanced quality - prefer using Q4_K_M
inkbot-13b-4k.Q5_K_S.gguf	Q5_K_S	5	8.97 GB	11.47 GB	large, low quality loss - recommended
inkbot-13b-4k.Q5_K_M.gguf	Q5_K_M	5	9.23 GB	11.73 GB	large, very low quality loss - recommended
inkbot-13b-4k.Q6_K.gguf	Q6_K	6	10.68 GB	13.18 GB	very large, extremely low quality loss
inkbot-13b-4k.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 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: TheBloke/Inkbot-13B-4k-GGUF and below it, a specific filename to download, such as: inkbot-13b-4k.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 TheBloke/Inkbot-13B-4k-GGUF inkbot-13b-4k.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False

More advanced huggingface-cli download usage

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

huggingface-cli download TheBloke/Inkbot-13B-4k-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 TheBloke/Inkbot-13B-4k-GGUF inkbot-13b-4k.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 32 -m inkbot-13b-4k.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<#meta#>\n- Date: [DATE]\n- Task: [TASK TYPE]\n<#system#>\n{system_message}\n<#chat#>\n<#user#>\n{prompt}\n<#bot#>"

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.

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 here: text-generation-webui/docs/llama.cpp.md.

How to run from Python code

You can use GGUF models from Python using the llama-cpp-python or ctransformers libraries.

How to load this model in Python code, using ctransformers

First install the package

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

# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers

Simple ctransformers example code

from ctransformers import AutoModelForCausalLM

# 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 = AutoModelForCausalLM.from_pretrained("TheBloke/Inkbot-13B-4k-GGUF", model_file="inkbot-13b-4k.Q4_K_M.gguf", model_type="llama", gpu_layers=50)

print(llm("AI is going to"))

How to use with LangChain

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

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

Discord

For further support, and discussions on these models and AI in general, join us at:

TheBloke AI's Discord server

Thanks, and how to contribute

Thanks to the chirper.ai team!

Thanks to Clay from gpus.llm-utils.org!

I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.

If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.

Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.

• Patreon: https://patreon.com/TheBlokeAI
• Ko-Fi: https://ko-fi.com/TheBlokeAI

Special thanks to: Aemon Algiz.

Patreon special mentions: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

Original model card: Tostino's Inkbot 13B 4K

Model Card for Inkbot

Model Details

Inkbot is a conversational AI model designed to interpret and respond to structured prompts with or without contextual information. Built on the latest advancements in natural language processing (NLP) and understanding (NLU), Inkbot provides users with accurate and meaningful interactions, addressing a wide range of queries and topics. Its unique feature lies in the structured prompt system, allowing users to engage in dynamic dialogues that can evolve based on context, metadata, and user input.

How to Use

Inkbot uses a structured prompt template system. Depending on the information you have or want to give, you can use templates 'with context' or 'without context'.

Prompt Template Structure

With Context:

<#meta#>
- Date: [DATE]
- Task: [TASK TYPE]
<#system#>
[SYSTEM PROMPT/DESCRIPTION OF THE INTERACTION]
<#chat#>
<#user#>
[USER QUESTION]
<#bot#>
[BOT RESPONSE]
<#user#>
[USER FOLLOW-UP QUESTION]
<#user_context#>
[ADDITIONAL CONTEXT FOR THE BOT]
<#bot#>
[BOT RESPONSE BASED ON CONTEXT]

Without Context:

<#meta#>
- Date: [DATE]
- Task: [TASK TYPE]
<#system#>
[SYSTEM PROMPT/DESCRIPTION OF THE INTERACTION]
<#chat#>
<#user#>
[USER QUESTION]
<#bot#>
[BOT RESPONSE]
<#user#>
[USER FOLLOW-UP QUESTION]
<#bot#>
[BOT RESPONSE]

Examples

With Context:

<#meta#>
- Date: 2023-07-20
- Task: general
<#system#>
A dialogue focused on determining dates based on context clues.
<#chat#>
<#user#>
What is today's date?
<#bot#>
The date is: 2023-07-20
<#user#>
When did the event in the provided context take place?
<#user_context#>
It's the day after new years eve, and I'm starting 2018 with a headache.
<#bot#>
The event in the context took place on: 2018-01-01

Without Context:

<#meta#>
- Date: 2023-07-20
- Task: general
<#system#>
A simple dialogue about daily queries.
<#chat#>
<#user#>
Will it rain today?
<#bot#>
I am not sure, without knowing your location I am unable to determine the weather.
<#user#>
Can you compose a haiku for me?
<#bot#>
Whispers of the breeze,
Nature's melodies unfold,
Dawn dispels the night.

Task Options

Inkbot has been trained for a variety of tasks. Below are some of the key task options you can utilize:

1. general: This is the default task and is designed for a broad range of general questions and interactions.

   • Usage: Suitable for most day-to-day interactions and queries.

2. knowledge_graph: This task involves extracting, understanding, and representing information in a structured way.

   • Usage: When you want to extract relationships between entities or desire structured representations of data.

3. question_answer: Explicitly trained for answering questions in a straightforward manner.

   • Usage: Best used when you have direct questions and expect concise answers.

4. reasoning: Allows Inkbot to showcase its logical and deductive reasoning capabilities.

   • Usage: Ideal for puzzles, riddles, or scenarios where logical analysis is required.

5. translation: Use this for language translation tasks.

   • Usage: Provide a sentence or paragraph in one language, and specify the desired target language for translation.

6. summarization: Trained for condensing large texts into shorter, coherent summaries.

   • Usage: When you have a lengthy text or article that you want to be summarized to its key points.

7. creative_writing: Engage Inkbot in composing stories, poetry, and other creative content.

   • Usage: For tasks that require imaginative and original content generation.

How to Use Task Options

In the prompt template structure, the Task metadata field is where you specify the task option. Here's an example of how to structure a prompt using the reasoning task:

Limitations

• Ensure you adhere to the prompt structure for best results.
• When providing contextual details, clarity is essential for Inkbot to derive accurate and meaningful responses.

Additional Notes

• The 'date', 'task', and 'system' are crucial metadata components that need to be provided outside the core dialogue.
• Use the 'user_context' key when you want to offer supplementary context that guides Inkbot's response.