commit 2ab05f71cee67188a299dd0004def79952d51f7b Author: ModelHub XC Date: Thu Jul 30 14:59:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/HelpingAI_Dhanishtha-2.0-preview-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..da6abf3 --- /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 + +HelpingAI_Dhanishtha-2.0-preview.imatrix filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/HelpingAI_Dhanishtha-2.0-preview-IQ2_M.gguf b/HelpingAI_Dhanishtha-2.0-preview-IQ2_M.gguf new file mode 100644 index 0000000..7ad6999 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7065c6960737bb0d92a7c12af850f1a099e5654c36ce3ee4aa228e5a676e04e3 +size 5322941984 diff --git a/HelpingAI_Dhanishtha-2.0-preview-IQ2_S.gguf b/HelpingAI_Dhanishtha-2.0-preview-IQ2_S.gguf new file mode 100644 index 0000000..2871373 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24bf58da1cfa3b6e2663f4d8f81d5e0705695df895c553bbf3787a7852d0fb3d +size 4963313184 diff --git a/HelpingAI_Dhanishtha-2.0-preview-IQ3_M.gguf b/HelpingAI_Dhanishtha-2.0-preview-IQ3_M.gguf new file mode 100644 index 0000000..a4e75da --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ef6d1e40fbe4d41e58950b654a6e1fe53b8eadd10b66e97846589d99caae38c +size 6883410464 diff --git a/HelpingAI_Dhanishtha-2.0-preview-IQ3_XS.gguf b/HelpingAI_Dhanishtha-2.0-preview-IQ3_XS.gguf new file mode 100644 index 0000000..291ea1b --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9449cfa57b681ad445b0065fec8e9b2db7d54dd68ea4f16404606e88ed33ace +size 6375301664 diff --git a/HelpingAI_Dhanishtha-2.0-preview-IQ3_XXS.gguf b/HelpingAI_Dhanishtha-2.0-preview-IQ3_XXS.gguf new file mode 100644 index 0000000..5f349b3 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:734be93538aeb1f8e88f2c990b477facaa9362f1188f521abed77e0bf70a3a2e +size 5942666784 diff --git a/HelpingAI_Dhanishtha-2.0-preview-IQ4_NL.gguf b/HelpingAI_Dhanishtha-2.0-preview-IQ4_NL.gguf new file mode 100644 index 0000000..7a71291 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a138be1e5e10712bd2fcaa4b1378f6f715c4a1116496e4d2bd646cc9fc836955 +size 8541363744 diff --git a/HelpingAI_Dhanishtha-2.0-preview-IQ4_XS.gguf b/HelpingAI_Dhanishtha-2.0-preview-IQ4_XS.gguf new file mode 100644 index 0000000..df60bc2 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d5139e01b0810277c6c9c8d583135d154986268faaa2c985320690a7f92da1f +size 8110730784 diff --git a/HelpingAI_Dhanishtha-2.0-preview-Q2_K.gguf b/HelpingAI_Dhanishtha-2.0-preview-Q2_K.gguf new file mode 100644 index 0000000..47323d6 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:218eabeada922fdaeedb3fe4c473092893cdabd745f51ef8d6e7ab6dd2322707 +size 5753984544 diff --git a/HelpingAI_Dhanishtha-2.0-preview-Q2_K_L.gguf b/HelpingAI_Dhanishtha-2.0-preview-Q2_K_L.gguf new file mode 100644 index 0000000..2beab1d --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2928cd1d64e622bd909104780ed7861dc69a5d7ca2dd2a53f1ec5c8dddd8e6ac +size 6513664544 diff --git a/HelpingAI_Dhanishtha-2.0-preview-Q3_K_L.gguf b/HelpingAI_Dhanishtha-2.0-preview-Q3_K_L.gguf new file mode 100644 index 0000000..7b577ca --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:577e1f84515879deed32a70649c3f01b0fd64b38299319b0218a8cf19422edb1 +size 7900652064 diff --git a/HelpingAI_Dhanishtha-2.0-preview-Q3_K_M.gguf b/HelpingAI_Dhanishtha-2.0-preview-Q3_K_M.gguf new file mode 100644 index 0000000..d79383e --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8626ab1d1ca9caf3340312eb1cc7f3d671f32511e20109b527a28bd443e43904 +size 7321313824 diff --git a/HelpingAI_Dhanishtha-2.0-preview-Q3_K_S.gguf b/HelpingAI_Dhanishtha-2.0-preview-Q3_K_S.gguf new file mode 100644 index 0000000..109580a --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e25b26838041e258135d0f7ae4d595f8cf174f2e41fda064fd81b4d237d54a0 +size 6657106464 diff --git a/HelpingAI_Dhanishtha-2.0-preview-Q3_K_XL.gguf b/HelpingAI_Dhanishtha-2.0-preview-Q3_K_XL.gguf new file mode 100644 index 0000000..ca51ee7 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6abea2f40361980fe6062acbb4c39fe5187278cbcb46c665acb1760a4288bd78 +size 8581325344 diff --git a/HelpingAI_Dhanishtha-2.0-preview-Q4_0.gguf b/HelpingAI_Dhanishtha-2.0-preview-Q4_0.gguf new file mode 100644 index 0000000..6956752 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6758df6cc4fab9f0328c8ce528d99da08aa7a0c92ccacf0181d4badc64eb1e1 +size 8543002144 diff --git a/HelpingAI_Dhanishtha-2.0-preview-Q4_1.gguf b/HelpingAI_Dhanishtha-2.0-preview-Q4_1.gguf new file mode 100644 index 0000000..99a4408 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b2bbae462f234c133a7f8293bdfdd3071e7dd26f0920b54f3a9280b2923db79 +size 9389522464 diff --git a/HelpingAI_Dhanishtha-2.0-preview-Q4_K_L.gguf b/HelpingAI_Dhanishtha-2.0-preview-Q4_K_L.gguf new file mode 100644 index 0000000..4a8be2d --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dd5cd3d0e7dc7eaf4cc4b50be11630f5a71771e5b6e7cf80ee49b3fc4860e58 +size 9579110944 diff --git a/HelpingAI_Dhanishtha-2.0-preview-Q4_K_M.gguf b/HelpingAI_Dhanishtha-2.0-preview-Q4_K_M.gguf new file mode 100644 index 0000000..667662b --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:026a1f80187c9ecdd0227816a35661f3b6b7abe85971121b4c1c25b6cdd7ab86 +size 9001754144 diff --git a/HelpingAI_Dhanishtha-2.0-preview-Q4_K_S.gguf b/HelpingAI_Dhanishtha-2.0-preview-Q4_K_S.gguf new file mode 100644 index 0000000..584a556 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6696a9b88cb0ed8bfcee91469fd8ab7875dda922d1eafa7931b6c13987916a33 +size 8573476384 diff --git a/HelpingAI_Dhanishtha-2.0-preview-Q5_K_L.gguf b/HelpingAI_Dhanishtha-2.0-preview-Q5_K_L.gguf new file mode 100644 index 0000000..b827ceb --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a64dd24d209e57a95607da50077d8f8256e9269ee60814955c4d1ed52916a455 +size 10994688544 diff --git a/HelpingAI_Dhanishtha-2.0-preview-Q5_K_M.gguf b/HelpingAI_Dhanishtha-2.0-preview-Q5_K_M.gguf new file mode 100644 index 0000000..3fd16a5 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:479f4417ff8dbe74b0a7e8e7c0578fa7627dbd9d80cf0b14678647122156b68c +size 10514570784 diff --git a/HelpingAI_Dhanishtha-2.0-preview-Q5_K_S.gguf b/HelpingAI_Dhanishtha-2.0-preview-Q5_K_S.gguf new file mode 100644 index 0000000..b5a5417 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e3d6d6ff4eb353f44eedb9ccf16b5e6af718ed42211e612c9a87c95d76db7c1 +size 10263895584 diff --git a/HelpingAI_Dhanishtha-2.0-preview-Q6_K.gguf b/HelpingAI_Dhanishtha-2.0-preview-Q6_K.gguf new file mode 100644 index 0000000..b90d18f --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e27476fc6466cd77c03ddd03379607bd719b840a5743250ea3928f6ed95f767c +size 12121938464 diff --git a/HelpingAI_Dhanishtha-2.0-preview-Q6_K_L.gguf b/HelpingAI_Dhanishtha-2.0-preview-Q6_K_L.gguf new file mode 100644 index 0000000..1b07e41 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a33ad1d0c80fb6b3869d089b9a43e788cbaf94e96297971207fa0899b9bcf67f +size 12498739744 diff --git a/HelpingAI_Dhanishtha-2.0-preview-Q8_0.gguf b/HelpingAI_Dhanishtha-2.0-preview-Q8_0.gguf new file mode 100644 index 0000000..aee4049 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28ebd59368525a8edd04a0101c8c485f9f6b0910e3b70e34fdaec3ff83b7770f +size 15698534944 diff --git a/HelpingAI_Dhanishtha-2.0-preview-bf16.gguf b/HelpingAI_Dhanishtha-2.0-preview-bf16.gguf new file mode 100644 index 0000000..c5cacc0 --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4e40663a0f966ce8e16655818e0716ed1eb56f7f68555bda5d91194c249e4f5 +size 29543424256 diff --git a/HelpingAI_Dhanishtha-2.0-preview.imatrix b/HelpingAI_Dhanishtha-2.0-preview.imatrix new file mode 100644 index 0000000..c196f2f --- /dev/null +++ b/HelpingAI_Dhanishtha-2.0-preview.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41da09a561ae3d3a68132803241d54a5f85af90e6f5c93b7a3101eb94eb15e87 +size 7709778 diff --git a/README.md b/README.md new file mode 100644 index 0000000..30adcad --- /dev/null +++ b/README.md @@ -0,0 +1,236 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model: HelpingAI/Dhanishtha-2.0-preview +base_model_relation: quantized +license: apache-2.0 +language: +- en +- hi +- zh +- es +- fr +- de +- ja +- ko +- ar +- pt +- ru +- it +- nl +- tr +- pl +- sv +- da +- 'no' +- fi +- he +- th +- vi +- id +- ms +- tl +- sw +- yo +- zu +- am +- bn +- gu +- kn +- ml +- mr +- ne +- or +- pa +- ta +- te +- ur +- multilingual +tags: +- reasoning +- intermediate-thinking +- transformers +- conversational +- bilingual +widget: +- text: 'Solve this riddle step by step: I am taken from a mine, and shut up in a + wooden case, from which I am never released, and yet I am used by almost everybody. + What am I?' + example_title: Complex Riddle Solving +- text: Explain the philosophical implications of artificial consciousness and think + through different perspectives. + example_title: Philosophical Reasoning +- text: Help me understand quantum mechanics, but take your time to think through + the explanation. + example_title: Educational Explanation +datasets: +- Abhaykoul/Dhanishtha-R1 +- open-thoughts/OpenThoughts-114k +- Abhaykoul/Dhanishtha-2.0-SUPERTHINKER +- Abhaykoul/Dhanishtha-2.0 +--- + +## Llamacpp imatrix Quantizations of Dhanishtha-2.0-preview by HelpingAI + +Using llama.cpp release b5760 for quantization. + +Original model: https://huggingface.co/HelpingAI/Dhanishtha-2.0-preview + +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-bf16.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-bf16.gguf) | bf16 | 29.54GB | false | Full BF16 weights. | +| [Dhanishtha-2.0-preview-Q8_0.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-Q8_0.gguf) | Q8_0 | 15.70GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Dhanishtha-2.0-preview-Q6_K_L.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-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-Q6_K.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-Q6_K.gguf) | Q6_K | 12.12GB | false | Very high quality, near perfect, *recommended*. | +| [Dhanishtha-2.0-preview-Q5_K_L.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-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-Q5_K_M.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-Q5_K_M.gguf) | Q5_K_M | 10.51GB | false | High quality, *recommended*. | +| [Dhanishtha-2.0-preview-Q5_K_S.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-Q5_K_S.gguf) | Q5_K_S | 10.26GB | false | High quality, *recommended*. | +| [Dhanishtha-2.0-preview-Q4_K_L.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-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-Q4_1.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-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-Q4_K_M.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-Q4_K_M.gguf) | Q4_K_M | 9.00GB | false | Good quality, default size for most use cases, *recommended*. | +| [Dhanishtha-2.0-preview-Q3_K_XL.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-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-Q4_K_S.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-Q4_K_S.gguf) | Q4_K_S | 8.57GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Dhanishtha-2.0-preview-Q4_0.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-Q4_0.gguf) | Q4_0 | 8.54GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Dhanishtha-2.0-preview-IQ4_NL.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-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-IQ4_XS.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-IQ4_XS.gguf) | IQ4_XS | 8.11GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Dhanishtha-2.0-preview-Q3_K_L.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-Q3_K_L.gguf) | Q3_K_L | 7.90GB | false | Lower quality but usable, good for low RAM availability. | +| [Dhanishtha-2.0-preview-Q3_K_M.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-Q3_K_M.gguf) | Q3_K_M | 7.32GB | false | Low quality. | +| [Dhanishtha-2.0-preview-IQ3_M.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-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-Q3_K_S.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-Q3_K_S.gguf) | Q3_K_S | 6.66GB | false | Low quality, not recommended. | +| [Dhanishtha-2.0-preview-Q2_K_L.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-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-IQ3_XS.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-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-IQ3_XXS.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-IQ3_XXS.gguf) | IQ3_XXS | 5.94GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Dhanishtha-2.0-preview-Q2_K.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-Q2_K.gguf) | Q2_K | 5.75GB | false | Very low quality but surprisingly usable. | +| [Dhanishtha-2.0-preview-IQ2_M.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-IQ2_M.gguf) | IQ2_M | 5.32GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | +| [Dhanishtha-2.0-preview-IQ2_S.gguf](https://huggingface.co/bartowski/HelpingAI_Dhanishtha-2.0-preview-GGUF/blob/main/HelpingAI_Dhanishtha-2.0-preview-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-GGUF --include "HelpingAI_Dhanishtha-2.0-preview-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-GGUF --include "HelpingAI_Dhanishtha-2.0-preview-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (HelpingAI_Dhanishtha-2.0-preview-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