commit 2942a70ad2f4a9bc2a4d7827255896bc92e6f4f2 Author: ModelHub XC Date: Tue May 19 14:30:57 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-Deepsync-3B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c9842cd --- /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 +Llama-Deepsync-3B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-3B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-3B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-3B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-3B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-3B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-3B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-3B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-3B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-3B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-3B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-3B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-3B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-3B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-3B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-3B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-3B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-3B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-3B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-3B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-3B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-3B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-3B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-3B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-Deepsync-3B.i1-IQ1_M.gguf b/Llama-Deepsync-3B.i1-IQ1_M.gguf new file mode 100644 index 0000000..2e1baa7 --- /dev/null +++ b/Llama-Deepsync-3B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ea467e7c445aea39e5eb0854397c4945cbaab03fe833422fdf3e039d148a3d4 +size 924192800 diff --git a/Llama-Deepsync-3B.i1-IQ1_S.gguf b/Llama-Deepsync-3B.i1-IQ1_S.gguf new file mode 100644 index 0000000..a6bb536 --- /dev/null +++ b/Llama-Deepsync-3B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e534fc6ce99c14f84b5f8b1c9d4bfc931ef9b4502ec61acf597f70314d50970e +size 868159520 diff --git a/Llama-Deepsync-3B.i1-IQ2_M.gguf b/Llama-Deepsync-3B.i1-IQ2_M.gguf new file mode 100644 index 0000000..cf98f40 --- /dev/null +++ b/Llama-Deepsync-3B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4c40a931e76da980de91c9af0b48ae7e49a537734f35a255600cce45c25ea2b +size 1229033504 diff --git a/Llama-Deepsync-3B.i1-IQ2_S.gguf b/Llama-Deepsync-3B.i1-IQ2_S.gguf new file mode 100644 index 0000000..e386de0 --- /dev/null +++ b/Llama-Deepsync-3B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58f56d8ffb5f92944e1385b755b2ebd336742803122a3165d839ff8eb9538bfa +size 1154322464 diff --git a/Llama-Deepsync-3B.i1-IQ2_XS.gguf b/Llama-Deepsync-3B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..91f538f --- /dev/null +++ b/Llama-Deepsync-3B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:810e3b14563d542d899a6d6e2cbd707f7a2813184cd6948c524f2360451b7421 +size 1100550176 diff --git a/Llama-Deepsync-3B.i1-IQ2_XXS.gguf b/Llama-Deepsync-3B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..beccc92 --- /dev/null +++ b/Llama-Deepsync-3B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97e1c46230981e8342211780fa6a971061f35b5f201259170fdbb6bc3d77cdae +size 1017581600 diff --git a/Llama-Deepsync-3B.i1-IQ3_M.gguf b/Llama-Deepsync-3B.i1-IQ3_M.gguf new file mode 100644 index 0000000..c609632 --- /dev/null +++ b/Llama-Deepsync-3B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d43884515a2a3c3d76838af1cc6f524b92321a5e96f0446abbb6c8b14b980508 +size 1599670304 diff --git a/Llama-Deepsync-3B.i1-IQ3_S.gguf b/Llama-Deepsync-3B.i1-IQ3_S.gguf new file mode 100644 index 0000000..f61fdbd --- /dev/null +++ b/Llama-Deepsync-3B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4105cab098e6cac3f92568141c9d46650d041bcfe616f8a806d063978212ec8e +size 1542850592 diff --git a/Llama-Deepsync-3B.i1-IQ3_XS.gguf b/Llama-Deepsync-3B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..541c428 --- /dev/null +++ b/Llama-Deepsync-3B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:725184630ebd6555e8cf8d241e313b992473bfb06539d8e0f92760bee901344d +size 1476790304 diff --git a/Llama-Deepsync-3B.i1-IQ3_XXS.gguf b/Llama-Deepsync-3B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..222f411 --- /dev/null +++ b/Llama-Deepsync-3B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d210ced40555387ebd9e177da1f164ca039fd87108b7465f521cb1b0058c6089 +size 1348767776 diff --git a/Llama-Deepsync-3B.i1-IQ4_NL.gguf b/Llama-Deepsync-3B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..64fae90 --- /dev/null +++ b/Llama-Deepsync-3B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5af8c57024a7c482c14bf6d944bc897e2c81bdbe6e0c2edd58ea922b991c1622 +size 1917192224 diff --git a/Llama-Deepsync-3B.i1-IQ4_XS.gguf b/Llama-Deepsync-3B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..c3e33be --- /dev/null +++ b/Llama-Deepsync-3B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3ea8e34a5dc0549e610f1c3d0f8e89c181f44fe53030e7bcbc8e91c9ff704d6 +size 1829111840 diff --git a/Llama-Deepsync-3B.i1-Q2_K.gguf b/Llama-Deepsync-3B.i1-Q2_K.gguf new file mode 100644 index 0000000..0b827f8 --- /dev/null +++ b/Llama-Deepsync-3B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00cae7aded979a5e45a939a6a529c901f9b6aef423dae5b1bf6357ccdfe91995 +size 1363937312 diff --git a/Llama-Deepsync-3B.i1-Q2_K_S.gguf b/Llama-Deepsync-3B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..fc5ca71 --- /dev/null +++ b/Llama-Deepsync-3B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:287b0fbb0ddb3fcbb81a92162427e97a5ac6975646dae9ad7f1935ba272cc577 +size 1274284064 diff --git a/Llama-Deepsync-3B.i1-Q3_K_L.gguf b/Llama-Deepsync-3B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..41ce7e0 --- /dev/null +++ b/Llama-Deepsync-3B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e3c63767ef6ed0acbccc0eca8b5c914c9c06f65cc4ae0a70b280fcb40738536 +size 1815349280 diff --git a/Llama-Deepsync-3B.i1-Q3_K_M.gguf b/Llama-Deepsync-3B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..94c5945 --- /dev/null +++ b/Llama-Deepsync-3B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e3b67a9a451197630f132a0a61af7fea25a231c7715f12b27551195992f2287 +size 1687160864 diff --git a/Llama-Deepsync-3B.i1-Q3_K_S.gguf b/Llama-Deepsync-3B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..e978b26 --- /dev/null +++ b/Llama-Deepsync-3B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a5d194350907065da6561a0c98e082c69766710d2a3679312104ac4bb7d9502 +size 1542850592 diff --git a/Llama-Deepsync-3B.i1-Q4_0.gguf b/Llama-Deepsync-3B.i1-Q4_0.gguf new file mode 100644 index 0000000..50cd434 --- /dev/null +++ b/Llama-Deepsync-3B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:568f3d7aa2907d64aae24ebefc963433127057ea0c5fcd6bc5079200e595580d +size 1921910816 diff --git a/Llama-Deepsync-3B.i1-Q4_1.gguf b/Llama-Deepsync-3B.i1-Q4_1.gguf new file mode 100644 index 0000000..8928457 --- /dev/null +++ b/Llama-Deepsync-3B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:455f2312ca738ed12512fa2a1293352be1898f0f5ece942bd10add50ddd6a0f1 +size 2093352992 diff --git a/Llama-Deepsync-3B.i1-Q4_K_M.gguf b/Llama-Deepsync-3B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..abfb330 --- /dev/null +++ b/Llama-Deepsync-3B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4e7d5f10743b2d3fc057a0509a789abad91127691534bff85d6f16fe0799992 +size 2019379232 diff --git a/Llama-Deepsync-3B.i1-Q4_K_S.gguf b/Llama-Deepsync-3B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..1bd1883 --- /dev/null +++ b/Llama-Deepsync-3B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b79799564cd1c16882ed500dac495bafc9eddb3ed6c403cb047bfee9ac2f212c +size 1928202272 diff --git a/Llama-Deepsync-3B.i1-Q5_K_M.gguf b/Llama-Deepsync-3B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..7d1f93e --- /dev/null +++ b/Llama-Deepsync-3B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d349861e0b181ed16f9e6941a6505c414c2dddf5a83773fbd64920d5f9a7d120 +size 2322155552 diff --git a/Llama-Deepsync-3B.i1-Q5_K_S.gguf b/Llama-Deepsync-3B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..2d2b941 --- /dev/null +++ b/Llama-Deepsync-3B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:677ea149581707c68dd4de68c48910e28fb0d67b5f7e7fce15f3c9649e9f0ad5 +size 2269513760 diff --git a/Llama-Deepsync-3B.i1-Q6_K.gguf b/Llama-Deepsync-3B.i1-Q6_K.gguf new file mode 100644 index 0000000..4819a26 --- /dev/null +++ b/Llama-Deepsync-3B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17ac3d4321cf5c5e133f07d97bf800a569ca85cea88f32635f1661a38ffd0a4c +size 2643855392 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ee354a9 --- /dev/null +++ b/README.md @@ -0,0 +1,91 @@ +--- +base_model: prithivMLmods/Llama-Deepsync-3B +language: +- en +- de +- fr +- it +- pt +- hi +- es +- th +library_name: transformers +license: creativeml-openrail-m +quantized_by: mradermacher +tags: +- Llama +- Code +- CoT +- Math +- Deepsync +- 3b +- ollama +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/prithivMLmods/Llama-Deepsync-3B + + +static quants are available at https://huggingface.co/mradermacher/Llama-Deepsync-3B-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/Llama-Deepsync-3B-i1-GGUF/resolve/main/Llama-Deepsync-3B.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-3B-i1-GGUF/resolve/main/Llama-Deepsync-3B.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-3B-i1-GGUF/resolve/main/Llama-Deepsync-3B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-3B-i1-GGUF/resolve/main/Llama-Deepsync-3B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-3B-i1-GGUF/resolve/main/Llama-Deepsync-3B.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-3B-i1-GGUF/resolve/main/Llama-Deepsync-3B.i1-IQ2_M.gguf) | i1-IQ2_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-3B-i1-GGUF/resolve/main/Llama-Deepsync-3B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-3B-i1-GGUF/resolve/main/Llama-Deepsync-3B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-3B-i1-GGUF/resolve/main/Llama-Deepsync-3B.i1-Q2_K.gguf) | i1-Q2_K | 1.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-3B-i1-GGUF/resolve/main/Llama-Deepsync-3B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-3B-i1-GGUF/resolve/main/Llama-Deepsync-3B.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-3B-i1-GGUF/resolve/main/Llama-Deepsync-3B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-3B-i1-GGUF/resolve/main/Llama-Deepsync-3B.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-3B-i1-GGUF/resolve/main/Llama-Deepsync-3B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-3B-i1-GGUF/resolve/main/Llama-Deepsync-3B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-3B-i1-GGUF/resolve/main/Llama-Deepsync-3B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-3B-i1-GGUF/resolve/main/Llama-Deepsync-3B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-3B-i1-GGUF/resolve/main/Llama-Deepsync-3B.i1-Q4_0.gguf) | i1-Q4_0 | 2.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-3B-i1-GGUF/resolve/main/Llama-Deepsync-3B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-3B-i1-GGUF/resolve/main/Llama-Deepsync-3B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-3B-i1-GGUF/resolve/main/Llama-Deepsync-3B.i1-Q4_1.gguf) | i1-Q4_1 | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-3B-i1-GGUF/resolve/main/Llama-Deepsync-3B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-3B-i1-GGUF/resolve/main/Llama-Deepsync-3B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-3B-i1-GGUF/resolve/main/Llama-Deepsync-3B.i1-Q6_K.gguf) | i1-Q6_K | 2.7 | 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..628d8c6 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ba74f7e175b99ca53e4c5af416cf387545a58333f1ff1fce3b5cb870b61f6fe +size 2988377