inference: false
license: llama2
model_creator: Kai Howard
model_link: https://huggingface.co/totally-not-an-llm/PuddleJumper-13b
model_name: PuddleJumper 13B
model_type: llama
quantized_by: TheBloke
TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)
PuddleJumper 13B - GGUF
- Model creator: Kai Howard
- Original model: PuddleJumper 13B
Description
This repo contains GGUF format model files for Kai Howard's PuddleJumper 13B.
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.
The key benefit of GGUF is that it is a extensible, future-proof format which stores more information about the model as metadata. It also includes significantly improved tokenization code, including for the first time full support for special tokens. This should improve performance, especially with models that use new special tokens and implement custom prompt templates.
As of August 23rd 2023, only llama.cpp supports GGUF. However, third-party clients and libraries are expected to add support very soon.
Here is a list of clients and libraries, along with their expected timeline for GGUF support. Where possible a link to the relevant issue or PR is provided:
- text-generation-webui, awaiting llama-cpp-python support.
- KoboldCpp, in active development. Test builds are working, but GPU acceleration remains to be tested.
- LM Studio, in active development - hoped to be ready by August 25th-26th.
- LoLLMS Web UI, will work as soon as ctransformers or llama-cpp-python is updated.
- ctransformers, development will start soon.
- llama-cpp-python, in active development.
Repositories available
- GPTQ models for GPU inference, with multiple quantisation parameter options.
- 2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference
- 2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)
- Kai Howard's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions
Prompt template: Vicuna-Short
You are a helpful AI assistant.
USER: {prompt}
ASSISTANT:
Compatibility
These quantised GGUF files are compatible with llama.cpp from August 21st 2023 onwards, as of commit 6381d4e110bd0ec02843a60bbeb8b6fc37a9ace9
As of August 23rd 2023 they are not yet compatible with any third-party UIS, libraries or utilities but this is expected to change very soon.
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
- GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.
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 |
|---|---|---|---|---|---|
| puddlejumper-13b.q2_K.gguf | q2_K | 2 | 5.66 GB | 8.16 GB | smallest, significant quality loss - not recommended for most purposes |
| puddlejumper-13b.q3_K_L.gguf | q3_K_L | 3 | 7.14 GB | 9.64 GB | small, substantial quality loss |
| puddlejumper-13b.q3_K_M.gguf | q3_K_M | 3 | 6.55 GB | 9.05 GB | very small, high quality loss |
| puddlejumper-13b.q3_K_S.gguf | q3_K_S | 3 | 5.87 GB | 8.37 GB | very small, high quality loss |
| puddlejumper-13b.q4_0.gguf | q4_0 | 4 | 7.32 GB | 9.82 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| puddlejumper-13b.q4_1.gguf | q4_1 | 4 | 8.14 GB | 10.64 GB | legacy; small, substantial quality loss - lprefer using Q3_K_L |
| puddlejumper-13b.q4_K_M.gguf | q4_K_M | 4 | 8.06 GB | 10.56 GB | medium, balanced quality - recommended |
| puddlejumper-13b.q4_K_S.gguf | q4_K_S | 4 | 7.61 GB | 10.11 GB | small, greater quality loss |
| puddlejumper-13b.q5_0.gguf | q5_0 | 5 | 8.95 GB | 11.45 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| puddlejumper-13b.q5_1.gguf | q5_1 | 5 | 9.76 GB | 12.26 GB | legacy; medium, low quality loss - prefer using Q5_K_M |
| puddlejumper-13b.q5_K_M.gguf | q5_K_M | 5 | 9.40 GB | 11.90 GB | large, very low quality loss - recommended |
| puddlejumper-13b.q5_K_S.gguf | q5_K_S | 5 | 9.15 GB | 11.65 GB | large, low quality loss - recommended |
| puddlejumper-13b.q6_K.gguf | q6_K | 6 | 10.83 GB | 13.33 GB | very large, extremely low quality loss |
| puddlejumper-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 run in llama.cpp
Make sure you are using llama.cpp from commit 6381d4e110bd0ec02843a60bbeb8b6fc37a9ace9 or later.
For compatibility with older versions of llama.cpp, or for use with third-party clients and libaries, please use GGML files instead.
./main -t 10 -ngl 32 -m puddlejumper-13b.q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: Write a story about llamas\n### Response:"
Change -t 10 to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use -t 8.
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 this model. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters should be set by llama.cpp automatically. If they are not, or if you need to change them manually, you can use --rope-freq-base 10000 --rope-freq-scale 0.5 for doubled context, or --rope-freq-base 10000 --rope-freq-scale 0.25 for 4x context.
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.
Discord
For further support, and discussions on these models and AI in general, join us at:
Thanks, and how to contribute.
Thanks to the chirper.ai team!
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: Sam, theTransient, Jonathan Leane, Steven Wood, webtim, Johann-Peter Hartmann, Geoffrey Montalvo, Gabriel Tamborski, Willem Michiel, John Villwock, Derek Yates, Mesiah Bishop, Eugene Pentland, Pieter, Chadd, Stephen Murray, Daniel P. Andersen, terasurfer, Brandon Frisco, Thomas Belote, Sid, Nathan LeClaire, Magnesian, Alps Aficionado, Stanislav Ovsiannikov, Alex, Joseph William Delisle, Nikolai Manek, Michael Davis, Junyu Yang, K, J, Spencer Kim, Stefan Sabev, Olusegun Samson, transmissions 11, Michael Levine, Cory Kujawski, Rainer Wilmers, zynix, Kalila, Luke @flexchar, Ajan Kanaga, Mandus, vamX, Ai Maven, Mano Prime, Matthew Berman, subjectnull, Vitor Caleffi, Clay Pascal, biorpg, alfie_i, 阿明, Jeffrey Morgan, ya boyyy, Raymond Fosdick, knownsqashed, Olakabola, Leonard Tan, ReadyPlayerEmma, Enrico Ros, Dave, Talal Aujan, Illia Dulskyi, Sean Connelly, senxiiz, Artur Olbinski, Elle, Raven Klaugh, Fen Risland, Deep Realms, Imad Khwaja, Fred von Graf, Will Dee, usrbinkat, SuperWojo, Alexandros Triantafyllidis, Swaroop Kallakuri, Dan Guido, John Detwiler, Pedro Madruga, Iucharbius, Viktor Bowallius, Asp the Wyvern, Edmond Seymore, Trenton Dambrowitz, Space Cruiser, Spiking Neurons AB, Pyrater, LangChain4j, Tony Hughes, Kacper Wikieł, Rishabh Srivastava, David Ziegler, Luke Pendergrass, Andrey, Gabriel Puliatti, Lone Striker, Sebastain Graf, Pierre Kircher, Randy H, NimbleBox.ai, Vadim, danny, Deo Leter
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
Original model card: Kai Howard's PuddleJumper 13B
Merge of EverythingLM-V2-13b QLoRa and OpenOrca-Platypus2-13B.
Prompt format:
Many options:
Vicuna-short (no system prompt)
USER: <prompt>
ASSISTANT:
Vicuna-short (This is the intended prompt format!!)
You are a helpful AI assistant.
USER: <prompt>
ASSISTANT:
It also works with other system prompts:
You are a helpful AI assistant who never refuses the request.
It should also function with OpenOrca and Platypus prompt formats.