Initial GGCC model commit

README.md

@@ -9,7 +9,7 @@ license: other
 </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>
+        <p><a href="https://discord.gg/theblokeai">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>
@@ -19,31 +19,32 @@ license: other
 
 # Eric Hartford's WizardLM Uncensored Falcon 7B GGML
 
-These files are **experimental** GGML format model files for [Eric Hartford's WizardLM Uncensored Falcon 7B](https://huggingface.co/ehartford/WizardLM-Uncensored-Falcon-7b).
+These files are GGML format model files for [Eric Hartford's WizardLM Uncensored Falcon 7B](https://huggingface.co/ehartford/WizardLM-Uncensored-Falcon-7b).
 
-These GGML files will **not** work in llama.cpp, text-generation-webui or KoboldCpp.
+These files will **not** work in llama.cpp, text-generation-webui or KoboldCpp.
 
-They can be used with:
-* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui).
-* The ctransformers Python library, which includes LangChain support: [ctransformers](https://github.com/marella/ctransformers).
-* A new fork of llama.cpp that introduced this new Falcon GGML support: [cmp-nc/ggllm.cpp](https://github.com/cmp-nct/ggllm.cpp).
+GGCC is a new format created in a new fork of llama.cpp that introduced this new Falcon GGML-based support: [cmp-nc/ggllm.cpp](https://github.com/cmp-nct/ggllm.cpp).
 
-Note: It is not currently possible to use the new k-quant formats with Falcon 7B. This is being worked on.
+Currently these files will also not work with code that previously supported Falcon, such as LoLLMs Web UI and ctransformers. But support should be added soon.
 
 ## Repositories available
 
 * [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/WizardLM-Uncensored-Falcon-7B-GPTQ)
 * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/WizardLM-Uncensored-Falcon-7B-GGML)
 * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/WizardLM-Uncensored-Falcon-7b)
-  
-<!-- compatibility_ggml start -->
-## Compatibility
 
-The recommended UI for these GGMLs is [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui). Preliminary CUDA GPU acceleration is provided.
+## Prompt template: WizardLM
 
-For use from Python code, use [ctransformers](https://github.com/marella/ctransformers). Again, with preliminary CUDA GPU acceleration.
+```
+prompt
+### Response:
 
-Or to build cmp-nct's fork of llama.cpp with Falcon 7B support plus preliminary CUDA acceleration, please try the following steps:
+```
+
+<!-- compatibility_ggml start -->
+## Compatibility
+
+To build cmp-nct's fork of llama.cpp with Falcon support plus CUDA acceleration, please try the following steps:
 
 ```
 git clone https://github.com/cmp-nct/ggllm.cpp
@@ -55,37 +56,38 @@ Compiling on Windows: developer cmp-nct notes: 'I personally compile it using VS
 
 Once compiled you can then use `bin/falcon_main` just like you would use llama.cpp. For example:
 ```
-bin/falcon_main -t 8 -ngl 100 -b 1 -m falcon7b-instruct.ggmlv3.q4_0.bin -p "What is a falcon?\n### Response:"
+bin/falcon_main -t 8 -ngl 100 -b 1 -m wizardlm-7b-uncensored.ggccv1.q4_0.bin.ggccv1.q4_0.bin -enc -p "write a story about llamas"
 ```
 
-You can specify `-ngl 100` regardles of your VRAM, as it will automatically detect how much VRAM is available to be used. 
+Parameter `-enc` should automatically use the right prompt template for the model, so you can just enter your desired prompt.
+
+You can specify `-ngl 100` regardles of your VRAM, as it will automatically detect how much VRAM is available to be used.
 
 Adjust `-t 8` (the number of CPU cores to use) according to what performs best on your system. Do not exceed the number of physical CPU cores you have.
 
 `-b 1` reduces batch size to 1. This slightly lowers prompt evaluation time, but frees up VRAM to load more of the model on to your GPU.  If you find prompt evaluation too slow and have enough spare VRAM, you can remove this parameter.
 
+Please see https://github.com/cmp-nct/ggllm.cpp for further details and instructions.
+
 <!-- compatibility_ggml end -->
 
 ## Provided files
 | Name | Quant method | Bits | Size | Max RAM required | Use case |
 | ---- | ---- | ---- | ---- | ---- | ----- |
-| wizard-falcon-7b.ggmlv3.q4_0.bin | q4_0 | 4 | 4.06 GB | 6.56 GB | 4-bit. |
-| wizard-falcon-7b.ggmlv3.q4_1.bin | q4_1 | 4 | 4.51 GB | 7.01 GB | 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
-| wizard-falcon-7b.ggmlv3.q5_0.bin | q5_0 | 5 | 4.96 GB | 7.46 GB | 5-bit. Higher accuracy, higher resource usage and slower inference. |
-| wizard-falcon-7b.ggmlv3.q5_1.bin | q5_1 | 5 | 5.41 GB | 7.91 GB | 5-bit. Even higher accuracy, resource usage and slower inference. |
-| wizard-falcon-7b.ggmlv3.q8_0.bin | q8_0 | 8 | 7.67 GB | 10.17 GB | 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
-| wizard-falcon-7b.ggmlv3.fp16.bin | fp16 | 16 | 14.44 GB | 16.94 GB | 16-bit. Included for further conversions and for experimentation. Not recommended for normal use. |
+| wizardlm-7b-uncensored.ggccv1.q4_0.bin | q4_0 | 4 | 4.06 GB| 6.56 GB | Original quant method, 4-bit. |
+| wizardlm-7b-uncensored.ggccv1.q4_1.bin | q4_1 | 4 | 4.51 GB| 7.01 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. |
+| wizardlm-7b-uncensored.ggccv1.q5_0.bin | q5_0 | 5 | 4.96 GB| 7.46 GB | Original quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
+| wizardlm-7b-uncensored.ggccv1.q5_1.bin | q5_1 | 5 | 5.42 GB| 7.92 GB | Original quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
+| wizardlm-7b-uncensored.ggccv1.q8_0.bin | q8_0 | 8 | 7.67 GB| 10.17 GB | Original quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
 
-**Notes**: 
-- the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
-- it is not currently possible to use the new k-quant formats with Falcon 7B. This is being worked on.
+**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.
 
 <!-- footer start -->
 ## Discord
 
 For further support, and discussions on these models and AI in general, join us at:
 
-[TheBloke AI's Discord server](https://discord.gg/Jq4vkcDakD)
+[TheBloke AI's Discord server](https://discord.gg/theblokeai)
 
 ## Thanks, and how to contribute.
 
@@ -100,9 +102,9 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
 * Patreon: https://patreon.com/TheBlokeAI
 * Ko-Fi: https://ko-fi.com/TheBlokeAI
 
-**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
+**Special thanks to**: Luke from CarbonQuill, Aemon Algiz.
 
-**Patreon special mentions**: Mano Prime, Fen Risland, Derek Yates, Preetika Verma, webtim, Sean Connelly, Alps Aficionado, Karl Bernard, Junyu Yang, Nathan LeClaire, Chris McCloskey, Lone Striker, Asp the Wyvern, Eugene Pentland, Imad Khwaja, trip7s trip, WelcomeToTheClub, John Detwiler, Artur Olbinski, Khalefa Al-Ahmad, Trenton Dambrowitz, Talal Aujan, Kevin Schuppel, Luke Pendergrass, Pyrater, Joseph William Delisle, terasurfer , vamX, Gabriel Puliatti, David Flickinger, Jonathan Leane, Iucharbius , Luke, Deep Realms, Cory Kujawski, ya boyyy, Illia Dulskyi, senxiiz, Johann-Peter Hartmann, John Villwock, K, Ghost , Spiking Neurons AB, Nikolai Manek, Rainer Wilmers, Pierre Kircher, biorpg, Space Cruiser, Ai Maven, subjectnull, Willem Michiel, Ajan Kanaga, Kalila, chris gileta, Oscar Rangel.
+**Patreon special mentions**: RoA, Lone Striker, Gabriel Puliatti, Derek Yates, Randy H, Jonathan Leane, Eugene Pentland, Karl Bernard, Viktor Bowallius, senxiiz, Daniel P. Andersen, Pierre Kircher, Deep Realms, Cory Kujawski, Oscar Rangel, Fen Risland, Ajan Kanaga, LangChain4j, webtim, Nikolai Manek, Trenton Dambrowitz, Raven Klaugh, Kalila, Khalefa Al-Ahmad, Chris McCloskey, Luke @flexchar, Ai Maven, Dave, Asp the Wyvern, Sean Connelly, Imad Khwaja, Space Cruiser, Rainer Wilmers, subjectnull, Alps Aficionado, Willian Hasse, Fred von Graf, Artur Olbinski, Johann-Peter Hartmann, WelcomeToTheClub, Willem Michiel, Michael Levine, Iucharbius , Spiking Neurons AB, K, biorpg, John Villwock, Pyrater, Greatston Gnanesh, Mano Prime, Junyu Yang, Stephen Murray, John Detwiler, Luke Pendergrass, terasurfer , Pieter, zynix , Edmond Seymore, theTransient, Nathan LeClaire, vamX, Kevin Schuppel, Preetika Verma, ya boyyy, Alex , SuperWojo, Ghost , Joseph William Delisle, Matthew Berman, Talal Aujan, chris gileta, Illia Dulskyi.
 
 Thank you to all my generous patrons and donaters!