Initial GGML model commit

README.md

@@ -0,0 +1,176 @@
+---
+inference: false
+license: llama2
+model_creator: grimpep
+model_link: https://huggingface.co/grimpep/llama2-22B-GPLATTY
+model_name: Llama2 22B GPLATTY
+model_type: llama
+quantized_by: TheBloke
+tags:
+- llama
+- llama-2
+---
+
+<!-- header start -->
+<!-- 200823 -->
+<div style="width: auto; margin-left: auto; margin-right: auto">
+<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 style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
+ </div>
+ <div style="display: flex; flex-direction: column; align-items: flex-end;">
+ <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
+ </div>
+</div>
+<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
+<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
+<!-- header end -->
+
+# Llama2 22B GPLATTY - GGML
+- Model creator: [grimpep](https://huggingface.co/grimpep)
+- Original model: [Llama2 22B GPLATTY](https://huggingface.co/grimpep/llama2-22B-GPLATTY)
+
+## Description
+
+This repo contains GGML format model files for [grimpep's Llama2 22B GPLATTY](https://huggingface.co/grimpep/llama2-22B-GPLATTY).
+
+GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as:
+* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most popular web UI. Supports NVidia CUDA GPU acceleration.
+* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a powerful GGML web UI with GPU acceleration on all platforms (CUDA and OpenCL). Especially good for story telling.
+* [LM Studio](https://lmstudio.ai/), a fully featured local GUI with GPU acceleration on both Windows (NVidia and AMD), and macOS.
+* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with CUDA GPU acceleration via the c_transformers backend.
+* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
+* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
+
+## Repositories available
+
+* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Llama2-22B-GPLATTY-GPTQ)
+* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/Llama2-22B-GPLATTY-GGML)
+* [grimpep's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/grimpep/llama2-22B-GPLATTY)
+
+## Prompt template: Alpaca
+
+```
+Below is an instruction that describes a task. Write a response that appropriately completes the request.
+
+### Instruction:
+{prompt}
+
+### Response:
+```
+
+<!-- compatibility_ggml start -->
+## Compatibility
+
+These quantised GGML files are compatible with llama.cpp as of June 6th, commit `2d43387`.
+
+They should also be compatible with all UIs, libraries and utilities which use GGML.
+
+## Explanation of the new k-quant methods
+<details>
+ <summary>Click to see details</summary>
+
+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.
+</details>
+<!-- compatibility_ggml end -->
+
+## Provided files
+
+| Name | Quant method | Bits | Size | Max RAM required | Use case |
+| ---- | ---- | ---- | ---- | ---- | ----- |
+| [llama2-22b-gplatty.ggmlv3.q2_K.bin](https://huggingface.co/TheBloke/Llama2-22B-GPLATTY-GGML/blob/main/llama2-22b-gplatty.ggmlv3.q2_K.bin) | q2_K | 2 | 9.22 GB| 11.72 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. |
+| [llama2-22b-gplatty.ggmlv3.q3_K_L.bin](https://huggingface.co/TheBloke/Llama2-22B-GPLATTY-GGML/blob/main/llama2-22b-gplatty.ggmlv3.q3_K_L.bin) | q3_K_L | 3 | 11.61 GB| 14.11 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
+| [llama2-22b-gplatty.ggmlv3.q3_K_M.bin](https://huggingface.co/TheBloke/Llama2-22B-GPLATTY-GGML/blob/main/llama2-22b-gplatty.ggmlv3.q3_K_M.bin) | q3_K_M | 3 | 10.57 GB| 13.07 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
+| [llama2-22b-gplatty.ggmlv3.q3_K_S.bin](https://huggingface.co/TheBloke/Llama2-22B-GPLATTY-GGML/blob/main/llama2-22b-gplatty.ggmlv3.q3_K_S.bin) | q3_K_S | 3 | 9.46 GB| 11.96 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
+| [llama2-22b-gplatty.ggmlv3.q4_0.bin](https://huggingface.co/TheBloke/Llama2-22B-GPLATTY-GGML/blob/main/llama2-22b-gplatty.ggmlv3.q4_0.bin) | q4_0 | 4 | 12.34 GB| 14.84 GB | Original quant method, 4-bit. |
+| [llama2-22b-gplatty.ggmlv3.q4_1.bin](https://huggingface.co/TheBloke/Llama2-22B-GPLATTY-GGML/blob/main/llama2-22b-gplatty.ggmlv3.q4_1.bin) | q4_1 | 4 | 13.69 GB| 16.19 GB | Original quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
+| [llama2-22b-gplatty.ggmlv3.q4_K_M.bin](https://huggingface.co/TheBloke/Llama2-22B-GPLATTY-GGML/blob/main/llama2-22b-gplatty.ggmlv3.q4_K_M.bin) | q4_K_M | 4 | 13.18 GB| 15.68 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K |
+| [llama2-22b-gplatty.ggmlv3.q4_K_S.bin](https://huggingface.co/TheBloke/Llama2-22B-GPLATTY-GGML/blob/main/llama2-22b-gplatty.ggmlv3.q4_K_S.bin) | q4_K_S | 4 | 12.34 GB| 14.84 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
+| [llama2-22b-gplatty.ggmlv3.q5_0.bin](https://huggingface.co/TheBloke/Llama2-22B-GPLATTY-GGML/blob/main/llama2-22b-gplatty.ggmlv3.q5_0.bin) | q5_0 | 5 | 15.04 GB| 17.54 GB | Original quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
+| [llama2-22b-gplatty.ggmlv3.q5_1.bin](https://huggingface.co/TheBloke/Llama2-22B-GPLATTY-GGML/blob/main/llama2-22b-gplatty.ggmlv3.q5_1.bin) | q5_1 | 5 | 16.39 GB| 18.89 GB | Original quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
+| [llama2-22b-gplatty.ggmlv3.q5_K_M.bin](https://huggingface.co/TheBloke/Llama2-22B-GPLATTY-GGML/blob/main/llama2-22b-gplatty.ggmlv3.q5_K_M.bin) | q5_K_M | 5 | 15.47 GB| 17.97 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K |
+| [llama2-22b-gplatty.ggmlv3.q5_K_S.bin](https://huggingface.co/TheBloke/Llama2-22B-GPLATTY-GGML/blob/main/llama2-22b-gplatty.ggmlv3.q5_K_S.bin) | q5_K_S | 5 | 15.04 GB| 17.54 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
+| [llama2-22b-gplatty.ggmlv3.q6_K.bin](https://huggingface.co/TheBloke/Llama2-22B-GPLATTY-GGML/blob/main/llama2-22b-gplatty.ggmlv3.q6_K.bin) | q6_K | 6 | 17.91 GB| 20.41 GB | New k-quant method. Uses GGML_TYPE_Q8_K for all tensors - 6-bit quantization |
+| [llama2-22b-gplatty.ggmlv3.q8_0.bin](https://huggingface.co/TheBloke/Llama2-22B-GPLATTY-GGML/blob/main/llama2-22b-gplatty.ggmlv3.q8_0.bin) | q8_0 | 8 | 23.14 GB| 25.64 GB | Original quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
+
+**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 llama2-22b-gplatty.ggmlv3.q4_K_M.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.
+
+Change `-c 2048` to the desired sequence length for this model. For example, `-c 4096` for a Llama 2 model. For models that use RoPE, add `--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](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
+
+## How to run in `text-generation-webui`
+
+Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
+
+<!-- footer start -->
+<!-- 200823 -->
+## Discord
+
+For further support, and discussions on these models and AI in general, join us at:
+
+[TheBloke AI's Discord server](https://discord.gg/theblokeai)
+
+## Thanks, and how to contribute.
+
+Thanks to the [chirper.ai](https://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.
+
+<!-- footer end -->
+
+# Original model card: grimpep's Llama2 22B GPLATTY
+
+
+This model is an experiment using the frankenstein script from 
+https://huggingface.co/chargoddard/llama2-22b
+I merged an already merged 13B Llama v2 model
+GUACHAT + KIMIKO = https://huggingface.co/grimpep/13Bv2-llama-modelmerge
+
+Then used https://huggingface.co/TheBloke/GPlatty-30B-SuperHOT-8K-fp16
+as donor model.
+
+It used 160GB of system ram to merge these models, they merge fast without swap.
+
+No strange behaviour noticed when generating with this model (maybe more hallucinations than usual), but note that this is still all experimental.
+
+This model might be more (didn't finetune it) more "ethically" aligned than https://huggingface.co/grimpep/llama2-22b-wizard_vicuna