Initial GGML model commit

README.md

@@ -1,10 +1,6 @@
 ---
 inference: false
 license: other
-tags:
-- medical
-datasets:
-- allenai/s2orc
 ---
 
 <!-- header start -->
@@ -28,31 +24,61 @@ These files are GGML format model files for [Chaoyi Wi's PMC_LLAMA 7B](https://h
 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)
+* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui)
 * [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/PMC_LLAMA-7B-GPTQ)
-* [4-bit, 5-bit, and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/PMC_LLAMA-7B-GGML)
+* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/PMC_LLAMA-7B-GGML)
 * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/chaoyi-wu/PMC_LLAMA_7B)
 
-## THE FILES IN MAIN BRANCH REQUIRES LATEST LLAMA.CPP (May 19th 2023 - commit 2d5db48)!
+<!-- compatibility_ggml start -->
+## Compatibility
 
-llama.cpp recently made another breaking change to its quantisation methods - https://github.com/ggerganov/llama.cpp/pull/1508
+### Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0`
 
-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.
+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`.
+
+These are guaranteed to be compatbile with any UIs, tools and libraries released since late May.
+
+### 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 compatible with llama.cpp as of June 6th, commit `2d43387`.
+
+They are now also compatible with recent releases of text-generation-webui, KoboldCpp, llama-cpp-python and ctransformers. Other tools and libraries may or may not be compatible - check their documentation if in doubt.
+
+## 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
 | Name | Quant method | Bits | Size | Max RAM required | Use case |
 | ---- | ---- | ---- | ---- | ---- | ----- |
-| PMC_LLAMA-7B.ggmlv3.q4_0.bin | q4_0 | 4 | 3.79 GB | 6.29 GB | 4-bit. |
-| PMC_LLAMA-7B.ggmlv3.q4_1.bin | q4_1 | 4 | 4.21 GB | 6.71 GB | 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
-| PMC_LLAMA-7B.ggmlv3.q5_0.bin | q5_0 | 5 | 4.63 GB | 7.13 GB | 5-bit. Higher accuracy, higher resource usage and slower inference. |
-| PMC_LLAMA-7B.ggmlv3.q5_1.bin | q5_1 | 5 | 5.06 GB | 7.56 GB | 5-bit. Even higher accuracy, resource usage and slower inference. |
-| PMC_LLAMA-7B.ggmlv3.q8_0.bin | q8_0 | 8 | 7.16 GB | 9.66 GB | 8-bit. Almost indistinguishable from float16. Huge resource use and slow. Not recommended for normal use. |
-
+| PMC_LLAMA-7B.ggmlv3.q2_K.bin | q2_K | 2 | 2.87 GB | 5.37 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. |
+| PMC_LLAMA-7B.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 3.60 GB | 6.10 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 |
+| PMC_LLAMA-7B.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 3.28 GB | 5.78 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 |
+| PMC_LLAMA-7B.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 2.95 GB | 5.45 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
+| PMC_LLAMA-7B.ggmlv3.q4_0.bin | q4_0 | 4 | 3.79 GB | 6.29 GB | Original llama.cpp quant method, 4-bit. |
+| PMC_LLAMA-7B.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. |
+| PMC_LLAMA-7B.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 4.08 GB | 6.58 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 |
+| PMC_LLAMA-7B.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 3.83 GB | 6.33 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
+| PMC_LLAMA-7B.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. |
+| PMC_LLAMA-7B.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. |
+| PMC_LLAMA-7B.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 4.78 GB | 7.28 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 |
+| PMC_LLAMA-7B.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 4.65 GB | 7.15 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
+| PMC_LLAMA-7B.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 |
+| PMC_LLAMA-7B.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.
 
@@ -63,7 +89,9 @@ I use the following command line; adjust for your tastes and needs:
 ```
 ./main -t 10 -ngl 32 -m PMC_LLAMA-7B.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`.
+If you're able to use full GPU offloading, you should use `-t 1` to get best performance.
+
+If not able to fully offload to GPU, you should use more cores. Change `-t 10` to the number of physical CPU cores you have, or a lower number depending on what gives best performance.
 
 Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
 
@@ -93,9 +121,12 @@ 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**: 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.
 
 Thank you to all my generous patrons and donaters!
+
 <!-- footer end -->
 
 # Original model card: Chaoyi Wi's PMC_LLAMA 7B
@@ -104,8 +135,8 @@ This repo contains PMC_LLaMA_7B, which is LLaMA-7b finetuned on the PMC papers i
 
 The model was trained with the following hyperparameters:
 
-* Epochs: 5
-* Batch size: 128
+* Epochs: 5 
+* Batch size: 128 
 * Cutoff length: 512
 * Learning rate: 2e-5
 
@@ -118,10 +149,10 @@ import transformers
 import torch
 tokenizer = transformers.LlamaTokenizer.from_pretrained('chaoyi-wu/PMC_LLAMA_7B')
 model = transformers.LlamaForCausalLM.from_pretrained('chaoyi-wu/PMC_LLAMA_7B')
-sentence = 'Hello, doctor'
+sentence = 'Hello, doctor' 
 batch = tokenizer(
             sentence,
-            return_tensors="pt",
+            return_tensors="pt", 
             add_special_tokens=False
         )
 with torch.no_grad():