commit cc0c32a159a6c9d067d89026edfba5b0f94b32d7 Author: ModelHub XC Date: Fri Jun 5 04:06:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OLMo-2-1124-7B-SFT-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..70e7700 --- /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 +OLMo-2-1124-7B-SFT.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-SFT.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-SFT.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-SFT.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-SFT.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-SFT.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-SFT.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-SFT.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-SFT.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-SFT.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-SFT.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-SFT.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-SFT.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-SFT.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-SFT.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-SFT.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-SFT.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-SFT.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-SFT.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-SFT.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-SFT.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-SFT.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-SFT.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-SFT.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OLMo-2-1124-7B-SFT.i1-IQ1_M.gguf b/OLMo-2-1124-7B-SFT.i1-IQ1_M.gguf new file mode 100644 index 0000000..0e7ef81 --- /dev/null +++ b/OLMo-2-1124-7B-SFT.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ef3400733597b7b19a9a2d8dae3a1401533c6d8c8332181fd87f29a4292e1da +size 1939185664 diff --git a/OLMo-2-1124-7B-SFT.i1-IQ1_S.gguf b/OLMo-2-1124-7B-SFT.i1-IQ1_S.gguf new file mode 100644 index 0000000..66e9346 --- /dev/null +++ b/OLMo-2-1124-7B-SFT.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f2ab9d5e9bc02af02fd89b633e0c7a393ce44caece77cea07fb89666013d6e5 +size 1816797184 diff --git a/OLMo-2-1124-7B-SFT.i1-IQ2_M.gguf b/OLMo-2-1124-7B-SFT.i1-IQ2_M.gguf new file mode 100644 index 0000000..16e3898 --- /dev/null +++ b/OLMo-2-1124-7B-SFT.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:672a9594a34990c08f0102bb913a3ba39072f18e320251d191920c46432a29c9 +size 2676400128 diff --git a/OLMo-2-1124-7B-SFT.i1-IQ2_S.gguf b/OLMo-2-1124-7B-SFT.i1-IQ2_S.gguf new file mode 100644 index 0000000..6c74183 --- /dev/null +++ b/OLMo-2-1124-7B-SFT.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db8990e095d68286b4ca841455ae65699b0cfe8a1765e301a2da926a5dcc477b +size 2513215488 diff --git a/OLMo-2-1124-7B-SFT.i1-IQ2_XS.gguf b/OLMo-2-1124-7B-SFT.i1-IQ2_XS.gguf new file mode 100644 index 0000000..ab13797 --- /dev/null +++ b/OLMo-2-1124-7B-SFT.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b91ade1d62ffb7182dd1dfd7643a9908dd0abc98f591c1425ad6e6b542b3f917 +size 2323128320 diff --git a/OLMo-2-1124-7B-SFT.i1-IQ2_XXS.gguf b/OLMo-2-1124-7B-SFT.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..3822020 --- /dev/null +++ b/OLMo-2-1124-7B-SFT.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d2a53e9a496817647d1c9a61e603b480aed7eed8dbfb7937e7b0c505e2527f3 +size 2143166464 diff --git a/OLMo-2-1124-7B-SFT.i1-IQ3_M.gguf b/OLMo-2-1124-7B-SFT.i1-IQ3_M.gguf new file mode 100644 index 0000000..2dc7e2e --- /dev/null +++ b/OLMo-2-1124-7B-SFT.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c237c42958d610f0cc4604eab243971b058e82bd15d56662de295d9a2fc5c814 +size 3468697600 diff --git a/OLMo-2-1124-7B-SFT.i1-IQ3_S.gguf b/OLMo-2-1124-7B-SFT.i1-IQ3_S.gguf new file mode 100644 index 0000000..18198eb --- /dev/null +++ b/OLMo-2-1124-7B-SFT.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fb782368bb058826d91013769ff4f85967c2293a9b6cddb4efe59a8ed4c7ecc +size 3302137856 diff --git a/OLMo-2-1124-7B-SFT.i1-IQ3_XS.gguf b/OLMo-2-1124-7B-SFT.i1-IQ3_XS.gguf new file mode 100644 index 0000000..c206a80 --- /dev/null +++ b/OLMo-2-1124-7B-SFT.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24a93323d49bd531d9890a0821cbfa981db40591769342497bcdd6310ed94480 +size 3150356480 diff --git a/OLMo-2-1124-7B-SFT.i1-IQ3_XXS.gguf b/OLMo-2-1124-7B-SFT.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..de643cb --- /dev/null +++ b/OLMo-2-1124-7B-SFT.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ec620c5c16a27f39243ce7a985618decb86ecba5cc79e764ea3ec58ac9ba6f4 +size 2902040576 diff --git a/OLMo-2-1124-7B-SFT.i1-IQ4_NL.gguf b/OLMo-2-1124-7B-SFT.i1-IQ4_NL.gguf new file mode 100644 index 0000000..dc1a386 --- /dev/null +++ b/OLMo-2-1124-7B-SFT.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fddffd1bd87436c7cc1745b2703d6ab6aba8f32d3c35f45f70b3f1605a614ed +size 4216823808 diff --git a/OLMo-2-1124-7B-SFT.i1-IQ4_XS.gguf b/OLMo-2-1124-7B-SFT.i1-IQ4_XS.gguf new file mode 100644 index 0000000..c51ed29 --- /dev/null +++ b/OLMo-2-1124-7B-SFT.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5973f93664d002cb780ca144bd9dbb075d0af4b782ef1c4f004c9db248cd9b4 +size 4001603584 diff --git a/OLMo-2-1124-7B-SFT.i1-Q2_K.gguf b/OLMo-2-1124-7B-SFT.i1-Q2_K.gguf new file mode 100644 index 0000000..9343daf --- /dev/null +++ b/OLMo-2-1124-7B-SFT.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d2b771fd0bae6244f0153dded074e2202231345e7aab2fdaf125272613ff398 +size 2858262528 diff --git a/OLMo-2-1124-7B-SFT.i1-Q2_K_S.gguf b/OLMo-2-1124-7B-SFT.i1-Q2_K_S.gguf new file mode 100644 index 0000000..17bda36 --- /dev/null +++ b/OLMo-2-1124-7B-SFT.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62a61683863ea0766dbc2a2b2028c3d767a8e2691c781c70438fdeb63a1aabd4 +size 2644942848 diff --git a/OLMo-2-1124-7B-SFT.i1-Q3_K_L.gguf b/OLMo-2-1124-7B-SFT.i1-Q3_K_L.gguf new file mode 100644 index 0000000..dd9146f --- /dev/null +++ b/OLMo-2-1124-7B-SFT.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b043fcb943b0b6eeb5b00dd06cad0d7ab4f9fc2564c59882bc66130d62360f16 +size 3950944256 diff --git a/OLMo-2-1124-7B-SFT.i1-Q3_K_M.gguf b/OLMo-2-1124-7B-SFT.i1-Q3_K_M.gguf new file mode 100644 index 0000000..5e370b4 --- /dev/null +++ b/OLMo-2-1124-7B-SFT.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1a3a1997bb6f978a322d8cd18fe94cc76436346f1b87f51bff29831110f21ea +size 3651837952 diff --git a/OLMo-2-1124-7B-SFT.i1-Q3_K_S.gguf b/OLMo-2-1124-7B-SFT.i1-Q3_K_S.gguf new file mode 100644 index 0000000..2346c1c --- /dev/null +++ b/OLMo-2-1124-7B-SFT.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcf6e298c553fc21e5c84bd97263159b2f7b25f165e98003a2f23d410beccdf9 +size 3302137856 diff --git a/OLMo-2-1124-7B-SFT.i1-Q4_0.gguf b/OLMo-2-1124-7B-SFT.i1-Q4_0.gguf new file mode 100644 index 0000000..7aff9d3 --- /dev/null +++ b/OLMo-2-1124-7B-SFT.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c91604f56658ff0adb3ecce65a8dd8f3df2401e265918b82de046672e2ab17d +size 4228096000 diff --git a/OLMo-2-1124-7B-SFT.i1-Q4_1.gguf b/OLMo-2-1124-7B-SFT.i1-Q4_1.gguf new file mode 100644 index 0000000..d8aa362 --- /dev/null +++ b/OLMo-2-1124-7B-SFT.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:645d741dcbec43024ddbffd322e4321e541e71ea89671961fa5c61d00e116463 +size 4647264256 diff --git a/OLMo-2-1124-7B-SFT.i1-Q4_K_M.gguf b/OLMo-2-1124-7B-SFT.i1-Q4_K_M.gguf new file mode 100644 index 0000000..4475f9c --- /dev/null +++ b/OLMo-2-1124-7B-SFT.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00694bfba7819883cbf2caa27d36f8379b1cc7a48a37938681daaa2597d221d5 +size 4472020992 diff --git a/OLMo-2-1124-7B-SFT.i1-Q4_K_S.gguf b/OLMo-2-1124-7B-SFT.i1-Q4_K_S.gguf new file mode 100644 index 0000000..2358b24 --- /dev/null +++ b/OLMo-2-1124-7B-SFT.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cfe7acdf7072c0da9e600c1fcd5425f7a2acb1f265cdf2c88cff1c3838de6e8 +size 4247756800 diff --git a/OLMo-2-1124-7B-SFT.i1-Q5_K_M.gguf b/OLMo-2-1124-7B-SFT.i1-Q5_K_M.gguf new file mode 100644 index 0000000..a5c9423 --- /dev/null +++ b/OLMo-2-1124-7B-SFT.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6c76611af967655ea33eb6b341296f91b5c4465e86c568776b81c7fd3c771c9 +size 5209169920 diff --git a/OLMo-2-1124-7B-SFT.i1-Q5_K_S.gguf b/OLMo-2-1124-7B-SFT.i1-Q5_K_S.gguf new file mode 100644 index 0000000..9defef1 --- /dev/null +++ b/OLMo-2-1124-7B-SFT.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54948ef192cbd05bb7e8855a28c7f125c98fedff5460e738ccb0d35804cd9188 +size 5077704704 diff --git a/OLMo-2-1124-7B-SFT.i1-Q6_K.gguf b/OLMo-2-1124-7B-SFT.i1-Q6_K.gguf new file mode 100644 index 0000000..d646c13 --- /dev/null +++ b/OLMo-2-1124-7B-SFT.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37867b2c6910c88443bb681f3784c847468079362c5a61f67b28cb5fdb417145 +size 5992390656 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e44ab2f --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: allenai/OLMo-2-1124-7B-SFT +datasets: +- allenai/tulu-3-sft-olmo-2-mixture +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/allenai/OLMo-2-1124-7B-SFT + + +static quants are available at https://huggingface.co/mradermacher/OLMo-2-1124-7B-SFT-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/OLMo-2-1124-7B-SFT-i1-GGUF/resolve/main/OLMo-2-1124-7B-SFT.i1-IQ1_S.gguf) | i1-IQ1_S | 1.9 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-SFT-i1-GGUF/resolve/main/OLMo-2-1124-7B-SFT.i1-IQ1_M.gguf) | i1-IQ1_M | 2.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-SFT-i1-GGUF/resolve/main/OLMo-2-1124-7B-SFT.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-SFT-i1-GGUF/resolve/main/OLMo-2-1124-7B-SFT.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-SFT-i1-GGUF/resolve/main/OLMo-2-1124-7B-SFT.i1-IQ2_S.gguf) | i1-IQ2_S | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-SFT-i1-GGUF/resolve/main/OLMo-2-1124-7B-SFT.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-SFT-i1-GGUF/resolve/main/OLMo-2-1124-7B-SFT.i1-IQ2_M.gguf) | i1-IQ2_M | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-SFT-i1-GGUF/resolve/main/OLMo-2-1124-7B-SFT.i1-Q2_K.gguf) | i1-Q2_K | 3.0 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-SFT-i1-GGUF/resolve/main/OLMo-2-1124-7B-SFT.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-SFT-i1-GGUF/resolve/main/OLMo-2-1124-7B-SFT.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-SFT-i1-GGUF/resolve/main/OLMo-2-1124-7B-SFT.i1-IQ3_S.gguf) | i1-IQ3_S | 3.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-SFT-i1-GGUF/resolve/main/OLMo-2-1124-7B-SFT.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-SFT-i1-GGUF/resolve/main/OLMo-2-1124-7B-SFT.i1-IQ3_M.gguf) | i1-IQ3_M | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-SFT-i1-GGUF/resolve/main/OLMo-2-1124-7B-SFT.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-SFT-i1-GGUF/resolve/main/OLMo-2-1124-7B-SFT.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.1 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-SFT-i1-GGUF/resolve/main/OLMo-2-1124-7B-SFT.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-SFT-i1-GGUF/resolve/main/OLMo-2-1124-7B-SFT.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.3 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-SFT-i1-GGUF/resolve/main/OLMo-2-1124-7B-SFT.i1-Q4_0.gguf) | i1-Q4_0 | 4.3 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-SFT-i1-GGUF/resolve/main/OLMo-2-1124-7B-SFT.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.3 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-SFT-i1-GGUF/resolve/main/OLMo-2-1124-7B-SFT.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-SFT-i1-GGUF/resolve/main/OLMo-2-1124-7B-SFT.i1-Q4_1.gguf) | i1-Q4_1 | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-SFT-i1-GGUF/resolve/main/OLMo-2-1124-7B-SFT.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-SFT-i1-GGUF/resolve/main/OLMo-2-1124-7B-SFT.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-SFT-i1-GGUF/resolve/main/OLMo-2-1124-7B-SFT.i1-Q6_K.gguf) | i1-Q6_K | 6.1 | 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..9376f22 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cbf2a18fe9660df39dea5f252219d775493d1ab8f7295d8c7e86fcdd82da782 +size 4562173