Upload new k-quant GGML quantised models.

README.md

@@ -1,13 +1,8 @@
 ---
-license: other
-datasets:
-- ehartford/wizard_vicuna_70k_unfiltered
-language:
-- en
-tags:
-- uncensored
 inference: false
+license: other
 ---
+
 <!-- 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;">
@@ -22,53 +17,89 @@ inference: false
 </div>
 <!-- header end -->
 
-# Wizard-Vicuna-7B-Uncensored GGML
+# Eric Hartford's Wizard Vicuna 7B Uncensored GGML
 
-This is GGML format quantised 4bit and 5bit models of [Eric Hartford's 'uncensored' training of Wizard-Vicuna 13B](https://huggingface.co/ehartford/Wizard-Vicuna-7B-Uncensored).
+These files are GGML format model files for [Eric Hartford's Wizard Vicuna 7B Uncensored](https://huggingface.co/ehartford/Wizard-Vicuna-7B-Uncensored).
 
-This repo is the result of quantising to 4bit and 5bit GGML for CPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp).
+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)
+* [KoboldCpp](https://github.com/LostRuins/koboldcpp)
+* [ParisNeo/GPT4All-UI](https://github.com/ParisNeo/gpt4all-ui)
+* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python)
+* [ctransformers](https://github.com/marella/ctransformers)
 
 ## Repositories available
 
-* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/Wizard-Vicuna-7B-Uncensored-GPTQ).
-* [4-bit, 5-bit and 8-bit GGML models for CPU (+CUDA) inference](https://huggingface.co/TheBloke/Wizard-Vicuna-7B-Uncensored-GGML).
-* [float16 HF format model for GPU inference and further conversions](https://huggingface.co/TheBloke/Wizard-Vicuna-7B-Uncensored-HF).
+* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/Wizard-Vicuna-7B-Uncensored-GPTQ)
+* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/Wizard-Vicuna-7B-Uncensored-GGML)
+* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/Wizard-Vicuna-7B-Uncensored-HF)
+
+<!-- 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`
 
-## THE FILES IN MAIN BRANCH REQUIRES LATEST LLAMA.CPP (May 19th 2023 - commit 2d5db48)!
+These new quantisation methods are only compatible with llama.cpp as of June 6th, commit `2d43387`.
 
-llama.cpp recently made another breaking change to its quantisation methods - https://github.com/ggerganov/llama.cpp/pull/1508
+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.
 
-I have quantised the GGML files in this repo with the latest version. Therefore you will require llama.cpp compiled on May 19th or later (commit `2d5db48` or later) to use them.
+## Explanation of the new k-quant methods
 
-For files compatible with the previous version of llama.cpp, please see branch `previous_llama_ggmlv2`.
+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
-| Name | Quant method | Bits | Size | RAM required | Use case |
+| Name | Quant method | Bits | Size | Max RAM required | Use case |
 | ---- | ---- | ---- | ---- | ---- | ----- |
-`Wizard-Vicuna-7B-Uncensored.ggmlv3.q4_0.bin` | q4_0 | 4bit | 4.21GB | 7.0GB | 4-bit. |
-`Wizard-Vicuna-7B-Uncensored.ggmlv3.q4_1.bin` | q4_1 | 4bit | 4.63GB | 7.5GB | 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
-`Wizard-Vicuna-7B-Uncensored.ggmlv3.q5_0.bin` | q5_0 | 5bit | 4.63GB | 7.5GB | 5-bit. Higher accuracy, higher resource usage and slower inference. |
-`Wizard-Vicuna-7B-Uncensored.ggmlv3.q5_1.bin` | q5_1 | 5bit | 5.06GB | 7.5GB | 5-bit. Even higher accuracy, and higher resource usage and slower inference. |
-`Wizard-Vicuna-7B-Uncensored.ggmlv3.q8_0.bin` | q8_0 | 8bit | 7.58GB | 9.0GB | 8-bit. Almost indistinguishable from float16. Huge resource use and slow. Not recommended for normal use. |
+| .ggmlv3.q2_K.bin | q2_K | 2 | 2.80 GB | 5.30 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. |
+| .ggmlv3.q3_K_L.bin | q3_K_L | 3 | 3.55 GB | 6.05 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 |
+| .ggmlv3.q3_K_M.bin | q3_K_M | 3 | 3.23 GB | 5.73 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 |
+| .ggmlv3.q3_K_S.bin | q3_K_S | 3 | 2.90 GB | 5.40 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
+| .ggmlv3.q4_K_M.bin | q4_K_M | 4 | 4.05 GB | 6.55 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 |
+| .ggmlv3.q4_K_S.bin | q4_K_S | 4 | 3.79 GB | 6.29 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
+| .ggmlv3.q5_K_M.bin | q5_K_M | 5 | 4.77 GB | 7.27 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 |
+| .ggmlv3.q5_K_S.bin | q5_K_S | 5 | 4.63 GB | 7.13 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
+| .ggmlv3.q6_K.bin | q6_K | 6 | 5.53 GB | 8.03 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors |
+| Wizard-Vicuna-7B-Uncensored.ggmlv3.q4_0.bin | q4_0 | 4 | 3.79 GB | 6.29 GB | Original llama.cpp quant method, 4-bit. |
+| Wizard-Vicuna-7B-Uncensored.ggmlv3.q4_1.bin | q4_1 | 4 | 4.21 GB | 6.71 GB | Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
+| Wizard-Vicuna-7B-Uncensored.ggmlv3.q5_0.bin | q5_0 | 5 | 4.63 GB | 7.13 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
+| Wizard-Vicuna-7B-Uncensored.ggmlv3.q5_1.bin | q5_1 | 5 | 5.06 GB | 7.56 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
+| Wizard-Vicuna-7B-Uncensored.ggmlv3.q8_0.bin | q8_0 | 8 | 7.16 GB | 9.66 GB | Original llama.cpp 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 8 -m Wizard-Vicuna-7B-Uncensored.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: write a story about llamas ### Response:"
+./main -t 10 -ngl 32 -m .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 `-t 8` to the number of physical CPU cores you have.
+Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
 
-## How to run in `text-generation-webui`
+If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
 
-GGML models can be loaded into text-generation-webui by installing the llama.cpp module, then placing the ggml model file in a model folder as usual.
+## How to run in `text-generation-webui`
 
 Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md).
 
-Note: at this time text-generation-webui may not support the new May 19th llama.cpp quantisation methods for q4_0, q4_1 and q8_0 files.
-
 <!-- footer start -->
 ## Discord
 
@@ -89,19 +120,24 @@ 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
 
-**Patreon special mentions**: Aemon Algiz, Dmitriy Samsonov, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, Jonathan Leane, Talal Aujan, V. Lukas, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Sebastain Graf, Johann-Peter Hartman.
+**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
+
+# Original model card: Eric Hartford's Wizard Vicuna 7B Uncensored
+
 
 This is [wizard-vicuna-13b](https://huggingface.co/junelee/wizard-vicuna-13b) trained against LLaMA-7B with a subset of the dataset - responses that contained alignment / moralizing were removed. The intent is to train a WizardLM that doesn't have alignment built-in, so that alignment (of any sort) can be added separately with for example with a RLHF LoRA.
 
 Shout out to the open source AI/ML community, and everyone who helped me out.
 
-Note:
+Note:  
 
-An uncensored model has no guardrails.
+An uncensored model has no guardrails.  
 
 You are responsible for anything you do with the model, just as you are responsible for anything you do with any dangerous object such as a knife, gun, lighter, or car.