commit 124c3129856edc6813641b860279735625df069b Author: ModelHub XC Date: Wed Apr 22 04:42:41 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Diophantus-14B-R1-Instruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d9d44e6 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt 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 +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz 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 +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl 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 +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* 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 +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Diophantus-14B-R1-Instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Diophantus-14B-R1-Instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Diophantus-14B-R1-Instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Diophantus-14B-R1-Instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Diophantus-14B-R1-Instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Diophantus-14B-R1-Instruct.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Diophantus-14B-R1-Instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Diophantus-14B-R1-Instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Diophantus-14B-R1-Instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Diophantus-14B-R1-Instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Diophantus-14B-R1-Instruct.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Diophantus-14B-R1-Instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Diophantus-14B-R1-Instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Diophantus-14B-R1-Instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Diophantus-14B-R1-Instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Diophantus-14B-R1-Instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Diophantus-14B-R1-Instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Diophantus-14B-R1-Instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Diophantus-14B-R1-Instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Diophantus-14B-R1-Instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Diophantus-14B-R1-Instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Diophantus-14B-R1-Instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Diophantus-14B-R1-Instruct.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Diophantus-14B-R1-Instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Diophantus-14B-R1-Instruct.i1-IQ1_M.gguf b/Diophantus-14B-R1-Instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..9963fba --- /dev/null +++ b/Diophantus-14B-R1-Instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef7af4b4a1db1658e037082e7cfb7fff7610ace78c29c25ccfe00ce33c42b122 +size 3872309152 diff --git a/Diophantus-14B-R1-Instruct.i1-IQ1_S.gguf b/Diophantus-14B-R1-Instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..ff02bcd --- /dev/null +++ b/Diophantus-14B-R1-Instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c07d7d9c1ceca63e33a48f67dd58a1400fe4ba075774ccb2c82fed8fce6b633a +size 3607994272 diff --git a/Diophantus-14B-R1-Instruct.i1-IQ2_M.gguf b/Diophantus-14B-R1-Instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..a3e1f1e --- /dev/null +++ b/Diophantus-14B-R1-Instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f038332ab91e63d655b221969b5c86e41a5562e336345fd5d95932a724c99839 +size 5356146592 diff --git a/Diophantus-14B-R1-Instruct.i1-IQ2_S.gguf b/Diophantus-14B-R1-Instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..f966865 --- /dev/null +++ b/Diophantus-14B-R1-Instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d6249e48854541a23160796746122c1619417fac549fa3dcb0e992635f4c59e +size 5003726752 diff --git a/Diophantus-14B-R1-Instruct.i1-IQ2_XS.gguf b/Diophantus-14B-R1-Instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..b097e7a --- /dev/null +++ b/Diophantus-14B-R1-Instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:341d6a9cf4dc4f9f222211d20d1a9964900449fc889a9cc99c27e7d95d9bd1fa +size 4704575392 diff --git a/Diophantus-14B-R1-Instruct.i1-IQ2_XXS.gguf b/Diophantus-14B-R1-Instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..3620953 --- /dev/null +++ b/Diophantus-14B-R1-Instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5507cd3df248d251701c326ed0429a10dac1ea9e54a21bd91610e51134c679f +size 4312833952 diff --git a/Diophantus-14B-R1-Instruct.i1-IQ3_M.gguf b/Diophantus-14B-R1-Instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..2640dde --- /dev/null +++ b/Diophantus-14B-R1-Instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f50bd2dcfcfe8a9ea8cd9ca8602c02fd7888fff83dc806012c4ccf863c0c3f6 +size 6916538272 diff --git a/Diophantus-14B-R1-Instruct.i1-IQ3_S.gguf b/Diophantus-14B-R1-Instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..1eba030 --- /dev/null +++ b/Diophantus-14B-R1-Instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96a2031555006671e6fb15d8e8d16071a0e78cb32fb32a42e1109824330a4c57 +size 6693019552 diff --git a/Diophantus-14B-R1-Instruct.i1-IQ3_XS.gguf b/Diophantus-14B-R1-Instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..15b1325 --- /dev/null +++ b/Diophantus-14B-R1-Instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31a2d804add984f8f2cf04d1b33df4993c66458370ef2563e9ae618f3f31ad6a +size 6383361952 diff --git a/Diophantus-14B-R1-Instruct.i1-IQ3_XXS.gguf b/Diophantus-14B-R1-Instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..1017e16 --- /dev/null +++ b/Diophantus-14B-R1-Instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60005f4a654dab6a2e97397c4b73f29a5b8cae69a263c5f15f24a3d40be1b888 +size 5946707872 diff --git a/Diophantus-14B-R1-Instruct.i1-IQ4_NL.gguf b/Diophantus-14B-R1-Instruct.i1-IQ4_NL.gguf new file mode 100644 index 0000000..6d0a20f --- /dev/null +++ b/Diophantus-14B-R1-Instruct.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05012e68fe614a73401a59cb373b4c5d4037e64e8e3cc6225420e8b4e00691b2 +size 8549183392 diff --git a/Diophantus-14B-R1-Instruct.i1-IQ4_XS.gguf b/Diophantus-14B-R1-Instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..ac0a724 --- /dev/null +++ b/Diophantus-14B-R1-Instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2baa197da49c6efc64720eb86893d32b74c28ded8e51c9febc25909af3d28683 +size 8119840672 diff --git a/Diophantus-14B-R1-Instruct.i1-Q2_K.gguf b/Diophantus-14B-R1-Instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..4f7dcc0 --- /dev/null +++ b/Diophantus-14B-R1-Instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8e52c1faa9a9cc78d8d171b0812ded66dbe7ba56b49bf929214dba6841bdf7d +size 5770497952 diff --git a/Diophantus-14B-R1-Instruct.i1-Q2_K_S.gguf b/Diophantus-14B-R1-Instruct.i1-Q2_K_S.gguf new file mode 100644 index 0000000..b7c8a86 --- /dev/null +++ b/Diophantus-14B-R1-Instruct.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37df921f0bb6beb3971c342f88235e8105e5e019ef741c4c33b4fac05563b9fe +size 5397188512 diff --git a/Diophantus-14B-R1-Instruct.i1-Q3_K_L.gguf b/Diophantus-14B-R1-Instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..a007be1 --- /dev/null +++ b/Diophantus-14B-R1-Instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0d59d5a7b0ab08e76cf546f28ccc322488ddca40d5014ddce0e43996bebc781 +size 7924768672 diff --git a/Diophantus-14B-R1-Instruct.i1-Q3_K_M.gguf b/Diophantus-14B-R1-Instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..846b967 --- /dev/null +++ b/Diophantus-14B-R1-Instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:453324ac9e4f17e8814c30b49e00b2fdb4e5f7cf01b2219ecdfd20d8817a9728 +size 7339204512 diff --git a/Diophantus-14B-R1-Instruct.i1-Q3_K_S.gguf b/Diophantus-14B-R1-Instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..15bc550 --- /dev/null +++ b/Diophantus-14B-R1-Instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edb094d24c742954f1923b92326929669f04d2b75035b519f18028608541782f +size 6659596192 diff --git a/Diophantus-14B-R1-Instruct.i1-Q4_0.gguf b/Diophantus-14B-R1-Instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..8b99f86 --- /dev/null +++ b/Diophantus-14B-R1-Instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af6c181f96332334400579c111a76e35447b174115d70e4bcfd599c5be0cc902 +size 8544268192 diff --git a/Diophantus-14B-R1-Instruct.i1-Q4_1.gguf b/Diophantus-14B-R1-Instruct.i1-Q4_1.gguf new file mode 100644 index 0000000..5373ddf --- /dev/null +++ b/Diophantus-14B-R1-Instruct.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76bd07b17991ffad9d0890fb0aec7ebbe6928bc1dfeff763c02aa5a812fd2893 +size 9392140192 diff --git a/Diophantus-14B-R1-Instruct.i1-Q4_K_M.gguf b/Diophantus-14B-R1-Instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..24ce107 --- /dev/null +++ b/Diophantus-14B-R1-Instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7014bea9093b2c016f26a2031d1239f2d2db1ceb1f1afed45c88b869b19b330b +size 8988110752 diff --git a/Diophantus-14B-R1-Instruct.i1-Q4_K_S.gguf b/Diophantus-14B-R1-Instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..6914b22 --- /dev/null +++ b/Diophantus-14B-R1-Instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26955a7a8180d128929b91482c09e962ea2ceae7d46cc29cbb234070bd4b2566 +size 8573431712 diff --git a/Diophantus-14B-R1-Instruct.i1-Q5_K_M.gguf b/Diophantus-14B-R1-Instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..aa40efe --- /dev/null +++ b/Diophantus-14B-R1-Instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:839d282a4af6ed9eb952baca16ebfdb9c4a9ea2500579597e274dd6ed1b2fbe7 +size 10508873632 diff --git a/Diophantus-14B-R1-Instruct.i1-Q5_K_S.gguf b/Diophantus-14B-R1-Instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..10e66ba --- /dev/null +++ b/Diophantus-14B-R1-Instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9526c952cf16286c9e90b05f505bb596147c71dc00bb5a6914c703d2f9fb99b9 +size 10266554272 diff --git a/Diophantus-14B-R1-Instruct.i1-Q6_K.gguf b/Diophantus-14B-R1-Instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..aacd6b4 --- /dev/null +++ b/Diophantus-14B-R1-Instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b96f02971443a46a178d58c9acc5e95423d0ee999f4fb6633a1c73eb7c984214 +size 12124684192 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c5716ef --- /dev/null +++ b/README.md @@ -0,0 +1,86 @@ +--- +base_model: prithivMLmods/Diophantus-14B-R1-Instruct +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- Code +- Reinforcement learning (RL) +- Math +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/prithivMLmods/Diophantus-14B-R1-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Diophantus-14B-R1-Instruct-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Diophantus-14B-R1-Instruct-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Diophantus-14B-R1-Instruct-i1-GGUF/resolve/main/Diophantus-14B-R1-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 3.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Diophantus-14B-R1-Instruct-i1-GGUF/resolve/main/Diophantus-14B-R1-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 4.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Diophantus-14B-R1-Instruct-i1-GGUF/resolve/main/Diophantus-14B-R1-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Diophantus-14B-R1-Instruct-i1-GGUF/resolve/main/Diophantus-14B-R1-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Diophantus-14B-R1-Instruct-i1-GGUF/resolve/main/Diophantus-14B-R1-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Diophantus-14B-R1-Instruct-i1-GGUF/resolve/main/Diophantus-14B-R1-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Diophantus-14B-R1-Instruct-i1-GGUF/resolve/main/Diophantus-14B-R1-Instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.5 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Diophantus-14B-R1-Instruct-i1-GGUF/resolve/main/Diophantus-14B-R1-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Diophantus-14B-R1-Instruct-i1-GGUF/resolve/main/Diophantus-14B-R1-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Diophantus-14B-R1-Instruct-i1-GGUF/resolve/main/Diophantus-14B-R1-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.5 | | +| [GGUF](https://huggingface.co/mradermacher/Diophantus-14B-R1-Instruct-i1-GGUF/resolve/main/Diophantus-14B-R1-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Diophantus-14B-R1-Instruct-i1-GGUF/resolve/main/Diophantus-14B-R1-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 6.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Diophantus-14B-R1-Instruct-i1-GGUF/resolve/main/Diophantus-14B-R1-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 7.0 | | +| [GGUF](https://huggingface.co/mradermacher/Diophantus-14B-R1-Instruct-i1-GGUF/resolve/main/Diophantus-14B-R1-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Diophantus-14B-R1-Instruct-i1-GGUF/resolve/main/Diophantus-14B-R1-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Diophantus-14B-R1-Instruct-i1-GGUF/resolve/main/Diophantus-14B-R1-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.2 | | +| [GGUF](https://huggingface.co/mradermacher/Diophantus-14B-R1-Instruct-i1-GGUF/resolve/main/Diophantus-14B-R1-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 8.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Diophantus-14B-R1-Instruct-i1-GGUF/resolve/main/Diophantus-14B-R1-Instruct.i1-IQ4_NL.gguf) | i1-IQ4_NL | 8.6 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Diophantus-14B-R1-Instruct-i1-GGUF/resolve/main/Diophantus-14B-R1-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Diophantus-14B-R1-Instruct-i1-GGUF/resolve/main/Diophantus-14B-R1-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Diophantus-14B-R1-Instruct-i1-GGUF/resolve/main/Diophantus-14B-R1-Instruct.i1-Q4_1.gguf) | i1-Q4_1 | 9.5 | | +| [GGUF](https://huggingface.co/mradermacher/Diophantus-14B-R1-Instruct-i1-GGUF/resolve/main/Diophantus-14B-R1-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.4 | | +| [GGUF](https://huggingface.co/mradermacher/Diophantus-14B-R1-Instruct-i1-GGUF/resolve/main/Diophantus-14B-R1-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.6 | | +| [GGUF](https://huggingface.co/mradermacher/Diophantus-14B-R1-Instruct-i1-GGUF/resolve/main/Diophantus-14B-R1-Instruct.i1-Q6_K.gguf) | i1-Q6_K | 12.2 | practically like static Q6_K | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..a1a8e13 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3420efa80752a26a801631007ef5038214cdffa6b4cd14aa3ab41529e5013e22 +size 8563597