30B-Lazarus-GGML

<!-- header start --> <div style="width: 100%;"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p><a href="https://discord.gg/Jq4vkcDakD">Chat & support: my new Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <!-- header end -->

CalderAI's 30B Lazarus GGML

These files are GGML format model files for CalderAI's 30B Lazarus.

GGML files are for CPU + GPU inference using llama.cpp and libraries and UIs which support this format, such as:

• text-generation-webui
• KoboldCpp
• ParisNeo/GPT4All-UI
• llama-cpp-python
• ctransformers

Repositories available

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

<!-- compatibility_ggml start -->

Compatibility

Original llama.cpp quant methods: q4_0, q4_1, q5_0, q5_1, q8_0

I have quantized these 'original' quantisation methods using an older version of llama.cpp so that they remain compatible with llama.cpp as of May 19th, commit 2d5db48.

They should be compatible with all current UIs and libraries that use llama.cpp, such as those listed at the top of this README.

New k-quant methods: q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K

These new quantisation methods are only compatible with llama.cpp as of June 6th, commit 2d43387.

They will NOT be compatible with koboldcpp, text-generation-ui, and other UIs and libraries yet. Support is expected to come over the next few days.

Explanation of the new k-quant methods

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.

<!-- compatibility_ggml end -->

Provided files

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

I use the following command line; adjust for your tastes and needs:

./main -t 10 -ngl 32 -m 30b-Lazarus.ggmlv3.q5_0.bin --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.

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

How to run in text-generation-webui

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

<!-- footer start -->

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!

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: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.

Patreon special mentions: Ajan Kanaga, Kalila, Derek Yates, Sean Connelly, Luke, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, trip7s trip, Jonathan Leane, Talal Aujan, Artur Olbinski, Cory Kujawski, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Johann-Peter Hartmann.

Thank you to all my generous patrons and donaters!

<!-- footer end -->

Original model card: CalderAI's 30B Lazarus

30B-Lazarus

Composition:

[] = applied as LoRA to a composite model | () = combined as composite models

[SuperCOT([gtp4xalpaca(manticorechatpygalpha+vicunaunlocked)]+[StoryV2(kaiokendev-SuperHOT-LoRA-prototype30b-8192)])]

This model is the result of an experimental use of LoRAs on language models and model merges that are not the base HuggingFace-format LLaMA model they were intended for. The desired outcome is to additively apply desired features without paradoxically watering down a model's effective behavior.

Potential limitations - LoRAs applied on top of each other may intercompete.

Subjective results - very promising. Further experimental tests and objective tests are required.

Instruct and Setup Suggestions:

Alpaca instruct is primary, Vicuna instruct format may work. If using KoboldAI or Text-Generation-WebUI, recommend switching between Godlike and Storywriter presets and adjusting output length + instructions in memory. Other presets as well as custom settings can yield highly different results, especially Temperature. If poking it with a stick doesn't work try poking harder.

Language Models and LoRAs Used Credits:

manticore-30b-chat-pyg-alpha [Epoch0.4] by openaccess-ai-collective

https://huggingface.co/openaccess-ai-collective/manticore-30b-chat-pyg-alpha

SuperCOT-LoRA [30B] by kaiokendev

https://huggingface.co/kaiokendev/SuperCOT-LoRA

Storytelling-LLaMa-LoRA [30B, Version 2] by GamerUnTouch

https://huggingface.co/GamerUntouch/Storytelling-LLaMa-LoRAs

SuperHOT Prototype [30b 8k ctx] by kaiokendev

https://huggingface.co/kaiokendev/SuperHOT-LoRA-prototype

ChanSung's GPT4-Alpaca-LoRA https://huggingface.co/chansung/gpt4-alpaca-lora-30b

Neko-Institute-of-Science's Vicuna Unlocked LoRA (Checkpoint 46080) https://huggingface.co/Neko-Institute-of-Science/VicUnLocked-30b-LoRA

Also thanks to Meta for LLaMA.

Each model and LoRA was hand picked and considered for what it could contribute to this ensemble. Thanks to each and every one of you for your incredible work developing some of the best things to come out of this community.