commit de5bea47c3651fd1465088557489441a57b7d914 Author: ModelHub XC Date: Mon Sep 14 08:24:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53d7257 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 \ No newline at end of file diff --git a/HelpingAI_Dhanishtha-2.0-preview-0825-IQ2_M.gguf b/HelpingAI_Dhanishtha-2.0-preview-0825-IQ2_M.gguf new file mode 100644 index 0000000..cc625c6 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-0825-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52ea63b523acd5f85754eebdf64bb4b9b31aecc0feccbb6959cc2bfc38dd08e0 +size 5322941600 diff --git a/HelpingAI_Dhanishtha-2.0-preview-0825-IQ2_S.gguf b/HelpingAI_Dhanishtha-2.0-preview-0825-IQ2_S.gguf new file mode 100644 index 0000000..4162c89 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-0825-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:014aaea69afd412f3503e07bc9d291ba2a2604c11f0d750f7f65785301b337ae +size 4963312800 diff --git a/HelpingAI_Dhanishtha-2.0-preview-0825-IQ3_M.gguf b/HelpingAI_Dhanishtha-2.0-preview-0825-IQ3_M.gguf new file mode 100644 index 0000000..430682a --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-0825-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8560248c06c2e6a680ec5b8ee72316763b52f2e73e6f561f0ba52f73bb7ecc88 +size 6883410080 diff --git a/HelpingAI_Dhanishtha-2.0-preview-0825-IQ3_XS.gguf b/HelpingAI_Dhanishtha-2.0-preview-0825-IQ3_XS.gguf new file mode 100644 index 0000000..5273d5c --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-0825-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63ee96bf96e04ddd2356ce103e200726e6eee313bfa21e8f2ba8d24ee55ed611 +size 6375301280 diff --git a/HelpingAI_Dhanishtha-2.0-preview-0825-IQ3_XXS.gguf b/HelpingAI_Dhanishtha-2.0-preview-0825-IQ3_XXS.gguf new file mode 100644 index 0000000..262e84f --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-0825-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9498fc3fa2bb0d477bb296381b1a753744cea714b1f66f554e271c5da86198c0 +size 5942666400 diff --git a/HelpingAI_Dhanishtha-2.0-preview-0825-IQ4_NL.gguf b/HelpingAI_Dhanishtha-2.0-preview-0825-IQ4_NL.gguf new file mode 100644 index 0000000..eb5d768 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-0825-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:569028b4f410de19408a0fbaffcfb3ca610d7a0cf86f06cb84ad6b526637f283 +size 8541363360 diff --git a/HelpingAI_Dhanishtha-2.0-preview-0825-IQ4_XS.gguf b/HelpingAI_Dhanishtha-2.0-preview-0825-IQ4_XS.gguf new file mode 100644 index 0000000..3e68118 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-0825-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cb2c3c6dfdf28b5277e45ce1678d316c29645dcd63893cf4707fca75c815e53 +size 8110730400 diff --git a/HelpingAI_Dhanishtha-2.0-preview-0825-Q2_K.gguf b/HelpingAI_Dhanishtha-2.0-preview-0825-Q2_K.gguf new file mode 100644 index 0000000..e82cd3f --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-0825-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19660e02d0f5e714f3f311f4df14bbd70eb63e1a7b95ff63fe22144b5d4d4683 +size 5753984160 diff --git a/HelpingAI_Dhanishtha-2.0-preview-0825-Q2_K_L.gguf b/HelpingAI_Dhanishtha-2.0-preview-0825-Q2_K_L.gguf new file mode 100644 index 0000000..9432a76 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-0825-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:466ce2531a06786aa48e4f36c6b7575b86196d1c79685c8d3075465b9bcfee65 +size 6513664160 diff --git a/HelpingAI_Dhanishtha-2.0-preview-0825-Q3_K_L.gguf b/HelpingAI_Dhanishtha-2.0-preview-0825-Q3_K_L.gguf new file mode 100644 index 0000000..d54a3d0 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-0825-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cca785f04f3565a7e7a0f168c50ec9b60aade1d1fec2f3ab1fea777bfc9061ce +size 7900651680 diff --git a/HelpingAI_Dhanishtha-2.0-preview-0825-Q3_K_M.gguf b/HelpingAI_Dhanishtha-2.0-preview-0825-Q3_K_M.gguf new file mode 100644 index 0000000..2e16649 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-0825-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e0f42d20809ef2096cb79d53c126661d31ea1300a7f3cc2c6a65db8f31cbab7 +size 7321313440 diff --git a/HelpingAI_Dhanishtha-2.0-preview-0825-Q3_K_S.gguf b/HelpingAI_Dhanishtha-2.0-preview-0825-Q3_K_S.gguf new file mode 100644 index 0000000..7a1f68d --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-0825-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bd611332f4af6d46c290b104a1373535821db79071f171e20ca0389b8fe56bb +size 6657106080 diff --git a/HelpingAI_Dhanishtha-2.0-preview-0825-Q3_K_XL.gguf b/HelpingAI_Dhanishtha-2.0-preview-0825-Q3_K_XL.gguf new file mode 100644 index 0000000..8efdac8 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-0825-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26c28474e84009f6db6ea34132fc455afa8f02e18a0cfddd2fc569414ead2574 +size 8581324960 diff --git a/HelpingAI_Dhanishtha-2.0-preview-0825-Q4_0.gguf b/HelpingAI_Dhanishtha-2.0-preview-0825-Q4_0.gguf new file mode 100644 index 0000000..1cc7ed7 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-0825-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37605d39dc55d2b50d599fe6953b7b5816903c4d1983d225f27d99796b6be05f +size 8543001760 diff --git a/HelpingAI_Dhanishtha-2.0-preview-0825-Q4_1.gguf b/HelpingAI_Dhanishtha-2.0-preview-0825-Q4_1.gguf new file mode 100644 index 0000000..fbb0914 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-0825-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc0b40920c028fd0c5c09604d394fd07389ec0e321cc49ad6031ffb50ce13bf8 +size 9389522080 diff --git a/HelpingAI_Dhanishtha-2.0-preview-0825-Q4_K_L.gguf b/HelpingAI_Dhanishtha-2.0-preview-0825-Q4_K_L.gguf new file mode 100644 index 0000000..8aabd3b --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-0825-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69cfd77c8d8e442a44e1a1c2eca8ab3b62181c6f1e811ea225e478bc7522c42d +size 9579110560 diff --git a/HelpingAI_Dhanishtha-2.0-preview-0825-Q4_K_M.gguf b/HelpingAI_Dhanishtha-2.0-preview-0825-Q4_K_M.gguf new file mode 100644 index 0000000..46e038c --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-0825-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b33d0a60847b03e75486c7954ce952ac2a6e677666e93e07d68a8d3e3024d50 +size 9001753760 diff --git a/HelpingAI_Dhanishtha-2.0-preview-0825-Q4_K_S.gguf b/HelpingAI_Dhanishtha-2.0-preview-0825-Q4_K_S.gguf new file mode 100644 index 0000000..9f65b13 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-0825-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ab799931f7c792c9c87b93bc1c9f7a9698985390c91d7d33d991b9f362bf6b3 +size 8573476000 diff --git a/HelpingAI_Dhanishtha-2.0-preview-0825-Q5_K_L.gguf b/HelpingAI_Dhanishtha-2.0-preview-0825-Q5_K_L.gguf new file mode 100644 index 0000000..f7fa8d6 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-0825-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71663cdc849b06e096992cda95f44f2070affb6d9d051c0ec6160b5c2c4526f3 +size 10994688160 diff --git a/HelpingAI_Dhanishtha-2.0-preview-0825-Q5_K_M.gguf b/HelpingAI_Dhanishtha-2.0-preview-0825-Q5_K_M.gguf new file mode 100644 index 0000000..131f37b --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-0825-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa6901003b815a13c3892a767ea0cd545e89ab0b3974869b0e7871c4b4b4f68f +size 10514570400 diff --git a/HelpingAI_Dhanishtha-2.0-preview-0825-Q5_K_S.gguf b/HelpingAI_Dhanishtha-2.0-preview-0825-Q5_K_S.gguf new file mode 100644 index 0000000..4dbcb6b --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-0825-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1da623ad228d9adc9f4ad2c391e3bc41c3e285c51f288af1b075588a4ea5843b +size 10263895200 diff --git a/HelpingAI_Dhanishtha-2.0-preview-0825-Q6_K.gguf b/HelpingAI_Dhanishtha-2.0-preview-0825-Q6_K.gguf new file mode 100644 index 0000000..2e0609b --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-0825-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a71b61bc0ba5e03aba307de77eb90e555b04da7dc38134cc3929722c1acfc5f0 +size 12121938080 diff --git a/HelpingAI_Dhanishtha-2.0-preview-0825-Q6_K_L.gguf b/HelpingAI_Dhanishtha-2.0-preview-0825-Q6_K_L.gguf new file mode 100644 index 0000000..42ed882 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-0825-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fe60cc0caa2e3b956971736a97d7bc890f73e87c83ba4b2df81efb6f6357b24 +size 12498739360 diff --git a/HelpingAI_Dhanishtha-2.0-preview-0825-Q8_0.gguf b/HelpingAI_Dhanishtha-2.0-preview-0825-Q8_0.gguf new file mode 100644 index 0000000..2d24cb0 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-0825-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cec20d3d9823066f30211aab004152f1c9e357cec90c281240db56b5e70f266d +size 15698534560 diff --git a/HelpingAI_Dhanishtha-2.0-preview-0825-bf16.gguf b/HelpingAI_Dhanishtha-2.0-preview-0825-bf16.gguf new file mode 100644 index 0000000..15b56a5 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-0825-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b466ced382c537b0c1ffa594115bbc62bb284250da7f974d948e42325cf78e46 +size 29543423840 diff --git a/HelpingAI_Dhanishtha-2.0-preview-0825-imatrix.gguf b/HelpingAI_Dhanishtha-2.0-preview-0825-imatrix.gguf new file mode 100644 index 0000000..631d1ba --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-0825-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af11c3e7e3d491e8c4e91451f7faf4ea54513bc3d20d64691a48884573082845 +size 7743584 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fea36f8 --- /dev/null +++ b/README.md @@ -0,0 +1,171 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model_relation: quantized +base_model: HelpingAI/Dhanishtha-2.0-preview-0825 +--- + +## Llamacpp imatrix Quantizations of Dhanishtha-2.0-preview-0825 by HelpingAI + +Using llama.cpp release b6014 for quantization. + +Original model: https://huggingface.co/HelpingAI/Dhanishtha-2.0-preview-0825 + +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 + +``` +<|im_start|>system +{system_prompt}<|im_end|> +<|im_start|>user +{prompt}<|im_end|> +<|im_start|>assistant +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Dhanishtha-2.0-preview-0825-bf16.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-0825-bf16.gguf) | bf16 | 29.54GB | false | Full BF16 weights. | +| [Dhanishtha-2.0-preview-0825-Q8_0.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-0825-Q8_0.gguf) | Q8_0 | 15.70GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Dhanishtha-2.0-preview-0825-Q6_K_L.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-0825-Q6_K_L.gguf) | Q6_K_L | 12.50GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Dhanishtha-2.0-preview-0825-Q6_K.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-0825-Q6_K.gguf) | Q6_K | 12.12GB | false | Very high quality, near perfect, *recommended*. | +| [Dhanishtha-2.0-preview-0825-Q5_K_L.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-0825-Q5_K_L.gguf) | Q5_K_L | 10.99GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Dhanishtha-2.0-preview-0825-Q5_K_M.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-0825-Q5_K_M.gguf) | Q5_K_M | 10.51GB | false | High quality, *recommended*. | +| [Dhanishtha-2.0-preview-0825-Q5_K_S.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-0825-Q5_K_S.gguf) | Q5_K_S | 10.26GB | false | High quality, *recommended*. | +| [Dhanishtha-2.0-preview-0825-Q4_K_L.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-0825-Q4_K_L.gguf) | Q4_K_L | 9.58GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Dhanishtha-2.0-preview-0825-Q4_1.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-0825-Q4_1.gguf) | Q4_1 | 9.39GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Dhanishtha-2.0-preview-0825-Q4_K_M.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-0825-Q4_K_M.gguf) | Q4_K_M | 9.00GB | false | Good quality, default size for most use cases, *recommended*. | +| [Dhanishtha-2.0-preview-0825-Q3_K_XL.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-0825-Q3_K_XL.gguf) | Q3_K_XL | 8.58GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Dhanishtha-2.0-preview-0825-Q4_K_S.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-0825-Q4_K_S.gguf) | Q4_K_S | 8.57GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Dhanishtha-2.0-preview-0825-Q4_0.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-0825-Q4_0.gguf) | Q4_0 | 8.54GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Dhanishtha-2.0-preview-0825-IQ4_NL.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-0825-IQ4_NL.gguf) | IQ4_NL | 8.54GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Dhanishtha-2.0-preview-0825-IQ4_XS.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-0825-IQ4_XS.gguf) | IQ4_XS | 8.11GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Dhanishtha-2.0-preview-0825-Q3_K_L.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-0825-Q3_K_L.gguf) | Q3_K_L | 7.90GB | false | Lower quality but usable, good for low RAM availability. | +| [Dhanishtha-2.0-preview-0825-Q3_K_M.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-0825-Q3_K_M.gguf) | Q3_K_M | 7.32GB | false | Low quality. | +| [Dhanishtha-2.0-preview-0825-IQ3_M.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-0825-IQ3_M.gguf) | IQ3_M | 6.88GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Dhanishtha-2.0-preview-0825-Q3_K_S.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-0825-Q3_K_S.gguf) | Q3_K_S | 6.66GB | false | Low quality, not recommended. | +| [Dhanishtha-2.0-preview-0825-Q2_K_L.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-0825-Q2_K_L.gguf) | Q2_K_L | 6.51GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Dhanishtha-2.0-preview-0825-IQ3_XS.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-0825-IQ3_XS.gguf) | IQ3_XS | 6.38GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Dhanishtha-2.0-preview-0825-IQ3_XXS.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-0825-IQ3_XXS.gguf) | IQ3_XXS | 5.94GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Dhanishtha-2.0-preview-0825-Q2_K.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-0825-Q2_K.gguf) | Q2_K | 5.75GB | false | Very low quality but surprisingly usable. | +| [Dhanishtha-2.0-preview-0825-IQ2_M.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-0825-IQ2_M.gguf) | IQ2_M | 5.32GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | +| [Dhanishtha-2.0-preview-0825-IQ2_S.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-0825-IQ2_S.gguf) | IQ2_S | 4.96GB | 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/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF --include "HelpingAI_Dhanishtha-2.0-preview-0825-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/HelpingAI_Dhanishtha-2.0-preview-0825-GGUF --include "HelpingAI_Dhanishtha-2.0-preview-0825-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (HelpingAI_Dhanishtha-2.0-preview-0825-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