commit 9187ed9aa040327faae60620075f8c27fdc61c5c Author: ModelHub XC Date: Mon Jul 13 12:02:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..97a12d7 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +PocketDoc_Dans-PersonalityEngine-V1.3.0-24b.imatrix filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ2_M.gguf b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ2_M.gguf new file mode 100644 index 0000000..0059332 --- /dev/null +++ b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dd3cc44d22fa0f06d0ed16d6b03c0ef6fbaf8cc897be96b648b6b5c8e33d2b1 +size 8114064000 diff --git a/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ2_S.gguf b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ2_S.gguf new file mode 100644 index 0000000..4f28c95 --- /dev/null +++ b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a2485403bb105c04a034be28cd6579aea722625ecdc30095d5b9a6102e4d020 +size 7478364800 diff --git a/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ2_XS.gguf b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ2_XS.gguf new file mode 100644 index 0000000..3427ee4 --- /dev/null +++ b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f39ceaa252ed1d523c4d0a2ef4c30b9953463fa9b7919dc625e189a9b3cd5884 +size 7207045760 diff --git a/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ3_M.gguf b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ3_M.gguf new file mode 100644 index 0000000..55ea721 --- /dev/null +++ b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20cc80b5d6e561a66983ba2fc713942eca505e28de294c65b1e63ea7d2a3c4bc +size 10650962560 diff --git a/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ3_XS.gguf b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ3_XS.gguf new file mode 100644 index 0000000..f4c9c40 --- /dev/null +++ b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbd32249c64951d95c3e091dca75eda2f2ed8d6bdc8d1bd9b5b13b95570842d4 +size 9907128960 diff --git a/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ3_XXS.gguf b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ3_XXS.gguf new file mode 100644 index 0000000..fa92688 --- /dev/null +++ b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaf95ab68f6f2531faf6369d19319690d703738be1c0a590329e594637e7afcf +size 9280604800 diff --git a/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ4_NL.gguf b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ4_NL.gguf new file mode 100644 index 0000000..38be668 --- /dev/null +++ b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:257998e6f9191f851e9b1330586a9adb549407df572f2b3bf72fde84577d259f +size 13468027520 diff --git a/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ4_XS.gguf b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ4_XS.gguf new file mode 100644 index 0000000..0c68aee --- /dev/null +++ b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a25b77aa876d0761b8d813a633f599fb1da1e6d46ca9032440ba52af9d3518c +size 12758928000 diff --git a/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q2_K.gguf b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q2_K.gguf new file mode 100644 index 0000000..9b912aa --- /dev/null +++ b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49ff862ff14894f2dd6fbbed3c47572a0fe3ad7d1b2d965d785ad09a12b23915 +size 8890337920 diff --git a/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q2_K_L.gguf b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q2_K_L.gguf new file mode 100644 index 0000000..83af31b --- /dev/null +++ b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8885f4070dbc79f746090850a96850043c1edc6a54975fe1172165fc130d69c +size 9545697920 diff --git a/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q3_K_L.gguf b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q3_K_L.gguf new file mode 100644 index 0000000..456569f --- /dev/null +++ b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12d433638ea9aa6e169b869dbac0f4310c6167f2a7374fbf9a23196e13a86f01 +size 12400773760 diff --git a/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q3_K_M.gguf b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q3_K_M.gguf new file mode 100644 index 0000000..2f03a68 --- /dev/null +++ b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fcb5009a56064a9ba00bc0ee974254a064f02971caaa48945c58d9ce94b954b +size 11474094720 diff --git a/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q3_K_S.gguf b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q3_K_S.gguf new file mode 100644 index 0000000..c44dd6f --- /dev/null +++ b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c5d06d69f5d7c2c2558f95005b48fd7a6dfd444903c6a017c5323eeb02701ac +size 10400287360 diff --git a/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q3_K_XL.gguf b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q3_K_XL.gguf new file mode 100644 index 0000000..2922a3f --- /dev/null +++ b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed9fd7d3a2b2f46cb673be46fba0535b3c5e7ebe289c3095c02a2812b1c60291 +size 12987976320 diff --git a/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q4_0.gguf b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q4_0.gguf new file mode 100644 index 0000000..cfbfce3 --- /dev/null +++ b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba7a25eb9e48c154404331ad2a7831dff40a8006aed9baf9891972b776f2f4b8 +size 13494241920 diff --git a/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q4_1.gguf b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q4_1.gguf new file mode 100644 index 0000000..5e0cccf --- /dev/null +++ b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:675607b09a3110adc545ce93eeb020a91f3e318cb13831ecea3e02463eaa282d +size 14873119360 diff --git a/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q4_K_L.gguf b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q4_K_L.gguf new file mode 100644 index 0000000..4a53e43 --- /dev/null +++ b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9f9c6e5cc0f3c52339e8a416ee32472fc000f08dd6dff0a1169a2f62cb84920 +size 14831995520 diff --git a/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q4_K_M.gguf b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q4_K_M.gguf new file mode 100644 index 0000000..a52db56 --- /dev/null +++ b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec796b1f4c3e5b52267d1cb5c7077f27da278b6f7e9d41b1257c668891000d46 +size 14333921920 diff --git a/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q4_K_S.gguf b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q4_K_S.gguf new file mode 100644 index 0000000..70fe8ee --- /dev/null +++ b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d9623e23088376a0e6d7d9b56e387c9b5b6863ec3a3df3fe9e0b16e81f5fb9e +size 13549292160 diff --git a/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q5_K_L.gguf b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q5_K_L.gguf new file mode 100644 index 0000000..8c3bf51 --- /dev/null +++ b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:709cc37d88b31d5e311b313ce7b7b8138a2d247d9796939891d4d6a13978b672 +size 17178184320 diff --git a/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q5_K_M.gguf b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q5_K_M.gguf new file mode 100644 index 0000000..c7bcab1 --- /dev/null +++ b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac14a6b7a0aa865c22337e0f56d56ac87d7ba564e88cc62804653bdc2a0115a6 +size 16763996800 diff --git a/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q5_K_S.gguf b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q5_K_S.gguf new file mode 100644 index 0000000..bbfd5bb --- /dev/null +++ b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f95745590d3dcd159a309fcd60ed2cc5bbb14ab23678f25f6d844e181497fb62 +size 16304425600 diff --git a/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q6_K.gguf b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q6_K.gguf new file mode 100644 index 0000000..b1e4ef3 --- /dev/null +++ b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:128b7bc31b605874a65fafb700bd3e528614aca45cbbded6875472869983e3fb +size 19345951360 diff --git a/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q6_K_L.gguf b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q6_K_L.gguf new file mode 100644 index 0000000..d4622c6 --- /dev/null +++ b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9700ec60ea3c0f051fc48894f79c57e72d1b52f370685d4bdb8480d056b98ba +size 19671009920 diff --git a/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q8_0.gguf b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q8_0.gguf new file mode 100644 index 0000000..af14fa7 --- /dev/null +++ b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ce3a010b56e0bdb3e2baf079449dad78797cff5f4b28637eaeceb068a138234 +size 25054792320 diff --git a/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-bf16.gguf b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-bf16.gguf new file mode 100644 index 0000000..e8a0e0e --- /dev/null +++ b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8d4ad4259c588dff9c26872dae70fefa6ebd0b42d373c8cd377e4a602c9ffc4 +size 47153531200 diff --git a/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b.imatrix b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b.imatrix new file mode 100644 index 0000000..b4bed42 --- /dev/null +++ b/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c16fa090182e1d596f2c8730ba900e62ffa6b50e446a0b3ddac6c2ed9ed521bb +size 10003538 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b538fa4 --- /dev/null +++ b/README.md @@ -0,0 +1,246 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +language: +- en +- ar +- de +- fr +- es +- hi +- pt +- ja +- ko +tags: +- general-purpose +- roleplay +- storywriting +- chemistry +- biology +- code +- climate +- axolotl +- text-generation-inference +- finetune +- legal +- medical +- finance +datasets: +- PocketDoc/Dans-Prosemaxx-RP +- PocketDoc/Dans-Personamaxx-Logs-2 +- PocketDoc/Dans-Personamaxx-VN +- PocketDoc/Dans-Kinomaxx-VanillaBackrooms +- PocketDoc/Dans-Prosemaxx-Gutenberg +- PocketDoc/Dans-Prosemaxx-Cowriter-3-XL +- PocketDoc/Dans-Prosemaxx-Adventure +- PocketDoc/Dans-Failuremaxx-Adventure-3 +- PocketDoc/Dans-Prosemaxx-InstructWriter-ZeroShot-2 +- PocketDoc/Dans-Prosemaxx-InstructWriter-ZeroShot-3 +- PocketDoc/Dans-Prosemaxx-InstructWriter-Continue-2 +- PocketDoc/Dans-Prosemaxx-Instructwriter-Long +- PocketDoc/Dans-Prosemaxx-RepRemover-1 +- PocketDoc/Dans-MemoryCore-CoreCurriculum-Small +- AquaV/US-Army-Survival-Sharegpt +- AquaV/Multi-Environment-Operations-Sharegpt +- AquaV/Resistance-Sharegpt +- AquaV/Interrogation-Sharegpt +- AquaV/Chemical-Biological-Safety-Applications-Sharegpt +- AquaV/Energetic-Materials-Sharegpt +- PocketDoc/Dans-Mathmaxx +- PJMixers/Math-Multiturn-1K-ShareGPT +- PocketDoc/Dans-Taskmaxx +- PocketDoc/Dans-Taskmaxx-DataPrepper +- PocketDoc/Dans-Taskmaxx-ConcurrentQA-Reworked +- PocketDoc/Dans-Taskmaxx-TableGPT +- PocketDoc/Dans-Taskmaxx-SciRIFF +- PocketDoc/Dans-Taskmaxx-Edit +- PocketDoc/Dans-Toolmaxx-Agent +- PocketDoc/Dans-Toolmaxx-ShellCommands +- PocketDoc/Dans-Toolmaxx-Functions-Toolbench +- PocketDoc/Dans-Toolmaxx-Functions-ToolACE +- PocketDoc/Dans-Toolmaxx-Functions-apigen-subset +- PocketDoc/Dans-Assistantmaxx-OpenAssistant2 +- PocketDoc/Dans-Assistantmaxx-Opus-Merge-2 +- PocketDoc/Dans-Assistantmaxx-sonnetorca-subset +- PocketDoc/Dans-Assistantmaxx-sonnetorca-subset-2 +- PocketDoc/Dans-Assistantmaxx-Synthia +- PocketDoc/Dans-Assistantmaxx-ASL +- PocketDoc/Dans-Assistantmaxx-PersonaLLM-Opus +- PocketDoc/Dans-Assistantmaxx-LongAlign +- PocketDoc/Dans-Assistantmaxx-OpenLeecher-Instruct +- PocketDoc/Dans-Assistantmaxx-Tulu3-IF +- PocketDoc/Dans-Systemmaxx +- PocketDoc/Dans-Logicmaxx-SAT-AP +- PJMixers/grimulkan_theory-of-mind-ShareGPT +- PJMixers/grimulkan_physical-reasoning-ShareGPT +- PocketDoc/Dans-Reasoningmaxx-NaturalReasoning +- PocketDoc/Dans-Reasoningmaxx-WebInstruct +- PocketDoc/Dans-Reasoningmaxx-GeneralReasoning +- PocketDoc/Dans-Assistantmaxx-ClosedInstruct +base_model: PocketDoc/Dans-PersonalityEngine-V1.3.0-24b +thumbnail: https://huggingface.co/PocketDoc/Dans-PersonalityEngine-V1.3.0-24b/resolve/main/resources/pe.png +base_model_relation: quantized +license: apache-2.0 +--- + +## Llamacpp imatrix Quantizations of Dans-PersonalityEngine-V1.3.0-24b by PocketDoc + +Using llama.cpp release b5466 for quantization. + +Original model: https://huggingface.co/PocketDoc/Dans-PersonalityEngine-V1.3.0-24b + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) + +Run them in [LM Studio](https://lmstudio.ai/) + +Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project + +## Prompt format + +``` +[gMASK]<|system|>{system_prompt}<|endoftext|><|user|>{prompt}<|endoftext|><|assistant|> +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Dans-PersonalityEngine-V1.3.0-24b-bf16.gguf](https://huggingface.co/bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF/blob/main/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-bf16.gguf) | bf16 | 47.15GB | false | Full BF16 weights. | +| [Dans-PersonalityEngine-V1.3.0-24b-Q8_0.gguf](https://huggingface.co/bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF/blob/main/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q8_0.gguf) | Q8_0 | 25.05GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Dans-PersonalityEngine-V1.3.0-24b-Q6_K_L.gguf](https://huggingface.co/bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF/blob/main/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q6_K_L.gguf) | Q6_K_L | 19.67GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Dans-PersonalityEngine-V1.3.0-24b-Q6_K.gguf](https://huggingface.co/bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF/blob/main/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q6_K.gguf) | Q6_K | 19.35GB | false | Very high quality, near perfect, *recommended*. | +| [Dans-PersonalityEngine-V1.3.0-24b-Q5_K_L.gguf](https://huggingface.co/bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF/blob/main/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q5_K_L.gguf) | Q5_K_L | 17.18GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Dans-PersonalityEngine-V1.3.0-24b-Q5_K_M.gguf](https://huggingface.co/bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF/blob/main/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q5_K_M.gguf) | Q5_K_M | 16.76GB | false | High quality, *recommended*. | +| [Dans-PersonalityEngine-V1.3.0-24b-Q5_K_S.gguf](https://huggingface.co/bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF/blob/main/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q5_K_S.gguf) | Q5_K_S | 16.30GB | false | High quality, *recommended*. | +| [Dans-PersonalityEngine-V1.3.0-24b-Q4_1.gguf](https://huggingface.co/bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF/blob/main/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q4_1.gguf) | Q4_1 | 14.87GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Dans-PersonalityEngine-V1.3.0-24b-Q4_K_L.gguf](https://huggingface.co/bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF/blob/main/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q4_K_L.gguf) | Q4_K_L | 14.83GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Dans-PersonalityEngine-V1.3.0-24b-Q4_K_M.gguf](https://huggingface.co/bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF/blob/main/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q4_K_M.gguf) | Q4_K_M | 14.33GB | false | Good quality, default size for most use cases, *recommended*. | +| [Dans-PersonalityEngine-V1.3.0-24b-Q4_K_S.gguf](https://huggingface.co/bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF/blob/main/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q4_K_S.gguf) | Q4_K_S | 13.55GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Dans-PersonalityEngine-V1.3.0-24b-Q4_0.gguf](https://huggingface.co/bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF/blob/main/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q4_0.gguf) | Q4_0 | 13.49GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Dans-PersonalityEngine-V1.3.0-24b-IQ4_NL.gguf](https://huggingface.co/bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF/blob/main/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ4_NL.gguf) | IQ4_NL | 13.47GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Dans-PersonalityEngine-V1.3.0-24b-Q3_K_XL.gguf](https://huggingface.co/bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF/blob/main/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q3_K_XL.gguf) | Q3_K_XL | 12.99GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Dans-PersonalityEngine-V1.3.0-24b-IQ4_XS.gguf](https://huggingface.co/bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF/blob/main/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ4_XS.gguf) | IQ4_XS | 12.76GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Dans-PersonalityEngine-V1.3.0-24b-Q3_K_L.gguf](https://huggingface.co/bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF/blob/main/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q3_K_L.gguf) | Q3_K_L | 12.40GB | false | Lower quality but usable, good for low RAM availability. | +| [Dans-PersonalityEngine-V1.3.0-24b-Q3_K_M.gguf](https://huggingface.co/bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF/blob/main/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q3_K_M.gguf) | Q3_K_M | 11.47GB | false | Low quality. | +| [Dans-PersonalityEngine-V1.3.0-24b-IQ3_M.gguf](https://huggingface.co/bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF/blob/main/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ3_M.gguf) | IQ3_M | 10.65GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Dans-PersonalityEngine-V1.3.0-24b-Q3_K_S.gguf](https://huggingface.co/bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF/blob/main/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q3_K_S.gguf) | Q3_K_S | 10.40GB | false | Low quality, not recommended. | +| [Dans-PersonalityEngine-V1.3.0-24b-IQ3_XS.gguf](https://huggingface.co/bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF/blob/main/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ3_XS.gguf) | IQ3_XS | 9.91GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Dans-PersonalityEngine-V1.3.0-24b-Q2_K_L.gguf](https://huggingface.co/bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF/blob/main/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q2_K_L.gguf) | Q2_K_L | 9.55GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Dans-PersonalityEngine-V1.3.0-24b-IQ3_XXS.gguf](https://huggingface.co/bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF/blob/main/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ3_XXS.gguf) | IQ3_XXS | 9.28GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Dans-PersonalityEngine-V1.3.0-24b-Q2_K.gguf](https://huggingface.co/bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF/blob/main/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q2_K.gguf) | Q2_K | 8.89GB | false | Very low quality but surprisingly usable. | +| [Dans-PersonalityEngine-V1.3.0-24b-IQ2_M.gguf](https://huggingface.co/bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF/blob/main/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ2_M.gguf) | IQ2_M | 8.11GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | +| [Dans-PersonalityEngine-V1.3.0-24b-IQ2_S.gguf](https://huggingface.co/bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF/blob/main/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ2_S.gguf) | IQ2_S | 7.48GB | false | Low quality, uses SOTA techniques to be usable. | +| [Dans-PersonalityEngine-V1.3.0-24b-IQ2_XS.gguf](https://huggingface.co/bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF/blob/main/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-IQ2_XS.gguf) | IQ2_XS | 7.21GB | false | Low quality, uses SOTA techniques to be usable. | + +## Embed/output weights + +Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. + +## Downloading using huggingface-cli + +
+ Click to view download instructions + +First, make sure you have hugginface-cli installed: + +``` +pip install -U "huggingface_hub[cli]" +``` + +Then, you can target the specific file you want: + +``` +huggingface-cli download bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF --include "PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q4_K_M.gguf" --local-dir ./ +``` + +If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run: + +``` +huggingface-cli download bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF --include "PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q8_0) or download them all in place (./) + +
+ +## ARM/AVX information + +Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass. + +Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggerganov/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly. + +As of llama.cpp build [b4282](https://github.com/ggerganov/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0. + +Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggerganov/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase. + +
+ Click to view Q4_0_X_X information (deprecated + +I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking. + +
+ Click to view benchmarks on an AVX2 system (EPYC7702) + +| model | size | params | backend | threads | test | t/s | % (vs Q4_0) | +| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% | + +Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation + +
+ +
+ +## Which file should I choose? + +
+ Click here for details + +A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) + +The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have. + +If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM. + +If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total. + +Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'. + +If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M. + +If you want to get more into the weeds, you can check out this extremely useful feature chart: + +[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix) + +But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size. + +These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide. + +
+ +## Credits + +Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset. + +Thank you ZeroWw for the inspiration to experiment with embed/output. + +Thank you to LM Studio for sponsoring my work. + +Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file