Initial GGML model commit

README.md

@@ -1,7 +1,8 @@
 ---
-license: other
 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;">
@@ -16,33 +17,86 @@ inference: false
 </div>
 <!-- header end -->
 
-## Dromedary-65B-LoRA GGML
+# Dromedary-65B-LoRA GGML
 
-These files are the result of merging the [delta weights of IBM's Dromedary 65B LoRA](https://huggingface.co/zhiqings/dromedary-65b-lora-delta-v0) with the original Llama 65B model.
+These files are GGML format model files for [Dromedary-65B-LoRA](https://huggingface.co/zhiqings/dromedary-65b-lora-delta-v0).
 
-This repo contains GGML files for 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
 
-* [4bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/dromedary-65B-lora-GPTQ)
-* [4bit and 5bit GGML models for CPU inference in llama.cpp](https://huggingface.co/TheBloke/dromedary-65B-lora-GGML)
-* [float16 unquantised model for GPU](https://huggingface.co/TheBloke/dromedary-65B-lora-HF)
+* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/dromedary-65b-lora-GPTQ)
+* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/dromedary-65b-lora-GGML)
+* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/dromedary-65b-lora-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.
 
-## THE FILES IN MAIN BRANCH REQUIRES LATEST LLAMA.CPP (May 19th 2023 - commit 2d5db48)!
+### 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`
 
-llama.cpp recently made another breaking change to its quantisation methods - https://github.com/ggerganov/llama.cpp/pull/1508
+These new quantisation methods are only compatible with llama.cpp as of June 6th, commit `2d43387`.
 
-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.
+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.
 
-For files compatible with the previous version of llama.cpp, please see branch `previous_llama_ggmlv2`.
+## 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 | RAM required | Use case |
+| Name | Quant method | Bits | Size | Max RAM required | Use case |
 | ---- | ---- | ---- | ---- | ---- | ----- |
-`dromedary-lora-65B.ggmlv3.q4_0.bin` | q4_0 | 4bit | 40.8GB | 43GB | 4-bit. |
-`dromedary-lora-65B.ggmlv3.q4_1.bin` | q4_1 | 4bit | 44.9GB | 47GB | 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
-`dromedary-lora-65B.ggmlv3.q5_0.bin` | q5_0 | 5bit | 44.9GB | 47GB | 5-bit. Higher accuracy, higher resource usage and slower inference.  |
-`dromedary-lora-65B.ggmlv3.q5_1.bin` | q5_1 | 5bit | 49GB | 51GB | 5-bit. Even higher accuracy, higher resource usage and slower inference. |
+| dromedary-lora-65B.ggmlv3.q2_K.bin | q2_K | 2 | 27.33 GB | 29.83 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. |
+| dromedary-lora-65B.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 34.55 GB | 37.05 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 |
+| dromedary-lora-65B.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 31.40 GB | 33.90 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 |
+| dromedary-lora-65B.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 28.06 GB | 30.56 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
+| dromedary-lora-65B.ggmlv3.q4_0.bin | q4_0 | 4 | 36.73 GB | 39.23 GB | Original llama.cpp quant method, 4-bit. |
+| dromedary-lora-65B.ggmlv3.q4_1.bin | q4_1 | 4 | 40.81 GB | 43.31 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. |
+| dromedary-lora-65B.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 39.28 GB | 41.78 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 |
+| dromedary-lora-65B.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 36.73 GB | 39.23 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
+| dromedary-lora-65B.ggmlv3.q5_0.bin | q5_0 | 5 | 44.89 GB | 47.39 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
+| dromedary-lora-65B.ggmlv3.q5_1.bin | q5_1 | 5 | 48.97 GB | 51.47 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
+| dromedary-lora-65B.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 46.20 GB | 48.70 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 |
+| dromedary-lora-65B.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 44.89 GB | 47.39 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
+
+
+**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 dromedary-lora-65B.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](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md).
 
 <!-- footer start -->
 ## Discord
@@ -64,19 +118,31 @@ 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 Dromedary Model Card
+# Original model card: Dromedary-65B-LoRA
+
+
+# Dromedary Model Card
 
+**NOTE: This "delta model" cannot be used directly.**  
+Users have to apply it on top of the original LLaMA weights to get actual Dromedary weights.  
 See https://github.com/IBM/Dromedary#model-weights for instructions.
 
 ## Model details
 
+<div align="center">
+
 <img src="https://raw.githubusercontent.com/IBM/Dromedary/main/assets/images/dromedary_logo.svg" alt="Dromedary Logo"/>
 
+</div>
+
 **Model type:**
 Dromedary is an open-source self-aligned language model trained with minimal human supervision.
 The base language model is LLaMA-65b, based on the transformer architecture.