commit a193df750b2f7afc5ea4f47c627669d5ca7b17d4 Author: ModelHub XC Date: Thu May 21 15:04:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mellum-4b-sft-python-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f21ea73 --- /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 +Mellum-4b-sft-python.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-python.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-python.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-python.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-python.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-python.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-python.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-python.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-python.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-python.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-python.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-python.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-python.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-python.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-python.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-python.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-python.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-python.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-python.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-python.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-python.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-python.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-python.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-python.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mellum-4b-sft-python.i1-IQ1_M.gguf b/Mellum-4b-sft-python.i1-IQ1_M.gguf new file mode 100644 index 0000000..13262ae --- /dev/null +++ b/Mellum-4b-sft-python.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:419f52fbe11899fb68a6ba3325aeea36aafbab20476bf80344a680913525d64f +size 1361601824 diff --git a/Mellum-4b-sft-python.i1-IQ1_S.gguf b/Mellum-4b-sft-python.i1-IQ1_S.gguf new file mode 100644 index 0000000..b485f31 --- /dev/null +++ b/Mellum-4b-sft-python.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d053991de38ee3c4687eeec6567fe4b33c1c0bd00b2b85a6dd59d7ec5c8a5db +size 1312664864 diff --git a/Mellum-4b-sft-python.i1-IQ2_M.gguf b/Mellum-4b-sft-python.i1-IQ2_M.gguf new file mode 100644 index 0000000..2c972c2 --- /dev/null +++ b/Mellum-4b-sft-python.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0bee9970a23d6dc959c1013e652c4366641328656b4e0767634b3d20c640a94 +size 1681747232 diff --git a/Mellum-4b-sft-python.i1-IQ2_S.gguf b/Mellum-4b-sft-python.i1-IQ2_S.gguf new file mode 100644 index 0000000..bcbc0d3 --- /dev/null +++ b/Mellum-4b-sft-python.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d886b7a97803fed829f961e89863b49f2fefc8cad22cb7e54cc646f70b2738a4 +size 1616497952 diff --git a/Mellum-4b-sft-python.i1-IQ2_XS.gguf b/Mellum-4b-sft-python.i1-IQ2_XS.gguf new file mode 100644 index 0000000..704d200 --- /dev/null +++ b/Mellum-4b-sft-python.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:259117994e83495397b0633477952e3aff9c02aa6669a0f799cffffe00b594e5 +size 1517260064 diff --git a/Mellum-4b-sft-python.i1-IQ2_XXS.gguf b/Mellum-4b-sft-python.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..9af67f6 --- /dev/null +++ b/Mellum-4b-sft-python.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20ba1eb8d30e7c04260bd9db8cd79de707ed63675fec62c49fa408e15bab62d2 +size 1443163424 diff --git a/Mellum-4b-sft-python.i1-IQ3_M.gguf b/Mellum-4b-sft-python.i1-IQ3_M.gguf new file mode 100644 index 0000000..113b92d --- /dev/null +++ b/Mellum-4b-sft-python.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2572b00036dff2b39a260372075925261234766c42ab37f8009f7af22cdcb1d +size 2034941216 diff --git a/Mellum-4b-sft-python.i1-IQ3_S.gguf b/Mellum-4b-sft-python.i1-IQ3_S.gguf new file mode 100644 index 0000000..1bfd925 --- /dev/null +++ b/Mellum-4b-sft-python.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:655da325a0414cea743103b78f4a49266f21a6cf2d058e1a5ef1bd09019153d8 +size 1950227744 diff --git a/Mellum-4b-sft-python.i1-IQ3_XS.gguf b/Mellum-4b-sft-python.i1-IQ3_XS.gguf new file mode 100644 index 0000000..d90327a --- /dev/null +++ b/Mellum-4b-sft-python.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc489335c688a830c6b70de0d5d7c79be34351d21c6994b38cd0cf2d638826be +size 1868997920 diff --git a/Mellum-4b-sft-python.i1-IQ3_XXS.gguf b/Mellum-4b-sft-python.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..2cccbf7 --- /dev/null +++ b/Mellum-4b-sft-python.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:821eb2daf4c16aa60d8fe763765429791a137220a0ad18f2c72c39000c1be920 +size 1763585312 diff --git a/Mellum-4b-sft-python.i1-IQ4_NL.gguf b/Mellum-4b-sft-python.i1-IQ4_NL.gguf new file mode 100644 index 0000000..150cfe2 --- /dev/null +++ b/Mellum-4b-sft-python.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1c83df0072e253aad24024f44a8e696bd25b8c9c77ec2da76af95cd9dd0d666 +size 2342847776 diff --git a/Mellum-4b-sft-python.i1-IQ4_XS.gguf b/Mellum-4b-sft-python.i1-IQ4_XS.gguf new file mode 100644 index 0000000..6c60e4b --- /dev/null +++ b/Mellum-4b-sft-python.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a8f265dc6ab444f4d6d4bf3b4e4a15e234db2965cb880b7dd72a96de16255e8 +size 2250466592 diff --git a/Mellum-4b-sft-python.i1-Q2_K.gguf b/Mellum-4b-sft-python.i1-Q2_K.gguf new file mode 100644 index 0000000..72c5091 --- /dev/null +++ b/Mellum-4b-sft-python.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81eb92c4c29efe1ab8c7f897687779b61e881b5ce4b971514c229ecbe3d2c224 +size 1707496736 diff --git a/Mellum-4b-sft-python.i1-Q2_K_S.gguf b/Mellum-4b-sft-python.i1-Q2_K_S.gguf new file mode 100644 index 0000000..c590ce0 --- /dev/null +++ b/Mellum-4b-sft-python.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bce53f1ba3ebaf710d5e9f8933452e9a0985ddfb6204dc7978ff891ea9e95f35 +size 1659499808 diff --git a/Mellum-4b-sft-python.i1-Q3_K_L.gguf b/Mellum-4b-sft-python.i1-Q3_K_L.gguf new file mode 100644 index 0000000..95b34d0 --- /dev/null +++ b/Mellum-4b-sft-python.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35688cadd450eeec268931aec189163f07919b07f855e88a88975d0df1696596 +size 2238872864 diff --git a/Mellum-4b-sft-python.i1-Q3_K_M.gguf b/Mellum-4b-sft-python.i1-Q3_K_M.gguf new file mode 100644 index 0000000..fe9a22f --- /dev/null +++ b/Mellum-4b-sft-python.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2686e14f2c9ce807653955003592c14592487629b966c01b8e1d9da37e32a8e +size 2124483872 diff --git a/Mellum-4b-sft-python.i1-Q3_K_S.gguf b/Mellum-4b-sft-python.i1-Q3_K_S.gguf new file mode 100644 index 0000000..c2651d0 --- /dev/null +++ b/Mellum-4b-sft-python.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:328afb34a636083439bd0a27cae94816928d2510a3e3fc04912fd10b6a3606f7 +size 1950227744 diff --git a/Mellum-4b-sft-python.i1-Q4_0.gguf b/Mellum-4b-sft-python.i1-Q4_0.gguf new file mode 100644 index 0000000..e4901a7 --- /dev/null +++ b/Mellum-4b-sft-python.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c3ed146c2909cc44a2ea5282dc8b242c8138bf9f036e4bf638ae78ef10779e5 +size 2347603232 diff --git a/Mellum-4b-sft-python.i1-Q4_1.gguf b/Mellum-4b-sft-python.i1-Q4_1.gguf new file mode 100644 index 0000000..93b8a01 --- /dev/null +++ b/Mellum-4b-sft-python.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cca6a0b1b6b42c5f88f781b45cee4c071471bf499955b480966ea996e92c6224 +size 2575164704 diff --git a/Mellum-4b-sft-python.i1-Q4_K_M.gguf b/Mellum-4b-sft-python.i1-Q4_K_M.gguf new file mode 100644 index 0000000..9ae87eb --- /dev/null +++ b/Mellum-4b-sft-python.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8aaee1b5e64c39367f5c3a3ff075fde4bd17a450e323756e9e09690779b1963 +size 2605172000 diff --git a/Mellum-4b-sft-python.i1-Q4_K_S.gguf b/Mellum-4b-sft-python.i1-Q4_K_S.gguf new file mode 100644 index 0000000..000df3a --- /dev/null +++ b/Mellum-4b-sft-python.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f73709412b8a969d0eb870b3522159bcc0c0e1dfbc3b0ac1df65a1a05ff0d2b2 +size 2447430944 diff --git a/Mellum-4b-sft-python.i1-Q5_K_M.gguf b/Mellum-4b-sft-python.i1-Q5_K_M.gguf new file mode 100644 index 0000000..6aa7cc0 --- /dev/null +++ b/Mellum-4b-sft-python.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37ec1efca2dc05f024ae92c69e66c987a1da0b90c98dae3a241897b523d59acc +size 2983544096 diff --git a/Mellum-4b-sft-python.i1-Q5_K_S.gguf b/Mellum-4b-sft-python.i1-Q5_K_S.gguf new file mode 100644 index 0000000..87025fc --- /dev/null +++ b/Mellum-4b-sft-python.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49ad1eb75720e71c7f36e32a885842550e213be0fce864b4a09890acc52ff95a +size 2855036192 diff --git a/Mellum-4b-sft-python.i1-Q6_K.gguf b/Mellum-4b-sft-python.i1-Q6_K.gguf new file mode 100644 index 0000000..4d5308c --- /dev/null +++ b/Mellum-4b-sft-python.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:715c3535af617448d87b90de00d64f7a9a10926f97030dc9789257f91f058f5b +size 3485429024 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9a07f38 --- /dev/null +++ b/README.md @@ -0,0 +1,88 @@ +--- +base_model: JetBrains/Mellum-4b-sft-python +datasets: +- bigcode/the-stack +- bigcode/the-stack-v2 +- bigcode/starcoderdata +- bigcode/commitpack +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- code +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/JetBrains/Mellum-4b-sft-python + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Mellum-4b-sft-python-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Mellum-4b-sft-python-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/Mellum-4b-sft-python-i1-GGUF/resolve/main/Mellum-4b-sft-python.i1-IQ1_S.gguf) | i1-IQ1_S | 1.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-python-i1-GGUF/resolve/main/Mellum-4b-sft-python.i1-IQ1_M.gguf) | i1-IQ1_M | 1.5 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-python-i1-GGUF/resolve/main/Mellum-4b-sft-python.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-python-i1-GGUF/resolve/main/Mellum-4b-sft-python.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-python-i1-GGUF/resolve/main/Mellum-4b-sft-python.i1-IQ2_S.gguf) | i1-IQ2_S | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-python-i1-GGUF/resolve/main/Mellum-4b-sft-python.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.8 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-python-i1-GGUF/resolve/main/Mellum-4b-sft-python.i1-IQ2_M.gguf) | i1-IQ2_M | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-python-i1-GGUF/resolve/main/Mellum-4b-sft-python.i1-Q2_K.gguf) | i1-Q2_K | 1.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-python-i1-GGUF/resolve/main/Mellum-4b-sft-python.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-python-i1-GGUF/resolve/main/Mellum-4b-sft-python.i1-IQ3_XS.gguf) | i1-IQ3_XS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-python-i1-GGUF/resolve/main/Mellum-4b-sft-python.i1-IQ3_S.gguf) | i1-IQ3_S | 2.1 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-python-i1-GGUF/resolve/main/Mellum-4b-sft-python.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.1 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-python-i1-GGUF/resolve/main/Mellum-4b-sft-python.i1-IQ3_M.gguf) | i1-IQ3_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-python-i1-GGUF/resolve/main/Mellum-4b-sft-python.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-python-i1-GGUF/resolve/main/Mellum-4b-sft-python.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-python-i1-GGUF/resolve/main/Mellum-4b-sft-python.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-python-i1-GGUF/resolve/main/Mellum-4b-sft-python.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.4 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-python-i1-GGUF/resolve/main/Mellum-4b-sft-python.i1-Q4_0.gguf) | i1-Q4_0 | 2.4 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-python-i1-GGUF/resolve/main/Mellum-4b-sft-python.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-python-i1-GGUF/resolve/main/Mellum-4b-sft-python.i1-Q4_1.gguf) | i1-Q4_1 | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-python-i1-GGUF/resolve/main/Mellum-4b-sft-python.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-python-i1-GGUF/resolve/main/Mellum-4b-sft-python.i1-Q5_K_S.gguf) | i1-Q5_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-python-i1-GGUF/resolve/main/Mellum-4b-sft-python.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-python-i1-GGUF/resolve/main/Mellum-4b-sft-python.i1-Q6_K.gguf) | i1-Q6_K | 3.6 | 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..b0f0359 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e14a3d67266f41f13ee962f435d0712c13fb34478b6e2c25424713ddcb700e5 +size 3209515