commit bf502a49851f6b16440d3be729d167446d7f0f46 Author: ModelHub XC Date: Wed Apr 22 06:18:54 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OLMoE-1B-7B-0125-DPO-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..161b167 --- /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 +OLMoE-1B-7B-0125-DPO.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-DPO.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-DPO.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-DPO.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-DPO.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-DPO.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-DPO.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-DPO.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-DPO.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-DPO.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-DPO.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-DPO.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-DPO.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-DPO.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-DPO.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-DPO.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-DPO.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-DPO.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-DPO.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-DPO.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-DPO.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-DPO.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-DPO.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-DPO.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OLMoE-1B-7B-0125-DPO.i1-IQ1_M.gguf b/OLMoE-1B-7B-0125-DPO.i1-IQ1_M.gguf new file mode 100644 index 0000000..3e27f84 --- /dev/null +++ b/OLMoE-1B-7B-0125-DPO.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90bb37926e7b2843ca2c5359cdc2573e2528ddb5456af7c12b7a99f527377f4e +size 1638393344 diff --git a/OLMoE-1B-7B-0125-DPO.i1-IQ1_S.gguf b/OLMoE-1B-7B-0125-DPO.i1-IQ1_S.gguf new file mode 100644 index 0000000..55aa406 --- /dev/null +++ b/OLMoE-1B-7B-0125-DPO.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8385df187b6c2f7dc5599cb5250e34b87c44634fca75d612ebfa369e34fdec4 +size 1490544128 diff --git a/OLMoE-1B-7B-0125-DPO.i1-IQ2_M.gguf b/OLMoE-1B-7B-0125-DPO.i1-IQ2_M.gguf new file mode 100644 index 0000000..748687d --- /dev/null +++ b/OLMoE-1B-7B-0125-DPO.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33a11433eed3643a986c7889a0e94b220b8d63eb12272018c17507f9f08869ba +size 2328333824 diff --git a/OLMoE-1B-7B-0125-DPO.i1-IQ2_S.gguf b/OLMoE-1B-7B-0125-DPO.i1-IQ2_S.gguf new file mode 100644 index 0000000..b7410d1 --- /dev/null +++ b/OLMoE-1B-7B-0125-DPO.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30759123a544e123d076f69d39035efba603b803ab828eb73b38dd23ea3953c6 +size 2131201536 diff --git a/OLMoE-1B-7B-0125-DPO.i1-IQ2_XS.gguf b/OLMoE-1B-7B-0125-DPO.i1-IQ2_XS.gguf new file mode 100644 index 0000000..112e534 --- /dev/null +++ b/OLMoE-1B-7B-0125-DPO.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e9e723e58a3e4d018a18f1723f024a71ab60c72cf40e9abb1de00c42dbe104e +size 2084038144 diff --git a/OLMoE-1B-7B-0125-DPO.i1-IQ2_XXS.gguf b/OLMoE-1B-7B-0125-DPO.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..f817cb2 --- /dev/null +++ b/OLMoE-1B-7B-0125-DPO.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75a945ec787663430f64cf94dd52c2690308a1f32eb72ea793b4b8767fd6a66a +size 1884808704 diff --git a/OLMoE-1B-7B-0125-DPO.i1-IQ3_M.gguf b/OLMoE-1B-7B-0125-DPO.i1-IQ3_M.gguf new file mode 100644 index 0000000..c80b010 --- /dev/null +++ b/OLMoE-1B-7B-0125-DPO.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7f73155086b3580404c19f627c19eb4af39cebc49cd4fb7d4ac239fe4608edd +size 3076544000 diff --git a/OLMoE-1B-7B-0125-DPO.i1-IQ3_S.gguf b/OLMoE-1B-7B-0125-DPO.i1-IQ3_S.gguf new file mode 100644 index 0000000..3d78589 --- /dev/null +++ b/OLMoE-1B-7B-0125-DPO.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ca5075580c6a7f2c967f45c3f8c1f971a75ee3380b6467716e703bde9db42d9 +size 3023066624 diff --git a/OLMoE-1B-7B-0125-DPO.i1-IQ3_XS.gguf b/OLMoE-1B-7B-0125-DPO.i1-IQ3_XS.gguf new file mode 100644 index 0000000..5341087 --- /dev/null +++ b/OLMoE-1B-7B-0125-DPO.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b079e1f3da4debbd3891fe1216bab9ddb38549b4aa82993f37ffed494700b7e +size 2865780224 diff --git a/OLMoE-1B-7B-0125-DPO.i1-IQ3_XXS.gguf b/OLMoE-1B-7B-0125-DPO.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..c9c0527 --- /dev/null +++ b/OLMoE-1B-7B-0125-DPO.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c7eb05f2295436384dab7ed9920e60ce242c9290a0ff580a4347a6e74b0cfb9 +size 2689568256 diff --git a/OLMoE-1B-7B-0125-DPO.i1-IQ4_NL.gguf b/OLMoE-1B-7B-0125-DPO.i1-IQ4_NL.gguf new file mode 100644 index 0000000..ddfd18b --- /dev/null +++ b/OLMoE-1B-7B-0125-DPO.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71e9f5b8830e5289519da2e30352d8ec45f09d0fab6ac872065d6ee398bfa98d +size 3928038912 diff --git a/OLMoE-1B-7B-0125-DPO.i1-IQ4_XS.gguf b/OLMoE-1B-7B-0125-DPO.i1-IQ4_XS.gguf new file mode 100644 index 0000000..8dbe08c --- /dev/null +++ b/OLMoE-1B-7B-0125-DPO.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b6e48537303e306b395887f38305941841cba0b02630e6871f911c97052cf8c +size 3715104256 diff --git a/OLMoE-1B-7B-0125-DPO.i1-Q2_K.gguf b/OLMoE-1B-7B-0125-DPO.i1-Q2_K.gguf new file mode 100644 index 0000000..5b8f1c3 --- /dev/null +++ b/OLMoE-1B-7B-0125-DPO.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47940092d8fb297c148a976519cd65dc9fe2dd7a920eb6f9209e410819c4b392 +size 2562764288 diff --git a/OLMoE-1B-7B-0125-DPO.i1-Q2_K_S.gguf b/OLMoE-1B-7B-0125-DPO.i1-Q2_K_S.gguf new file mode 100644 index 0000000..20471c2 --- /dev/null +++ b/OLMoE-1B-7B-0125-DPO.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6aa3b15f533136646e73b92e78cc7e6c9a0891810f986cc7fbd28fd45355ec34 +size 2393943552 diff --git a/OLMoE-1B-7B-0125-DPO.i1-Q3_K_L.gguf b/OLMoE-1B-7B-0125-DPO.i1-Q3_K_L.gguf new file mode 100644 index 0000000..9f0526b --- /dev/null +++ b/OLMoE-1B-7B-0125-DPO.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffa763336266e5ba60b0a9232264331c5aa81d2e22542297921c664fb20298ef +size 3611317760 diff --git a/OLMoE-1B-7B-0125-DPO.i1-Q3_K_M.gguf b/OLMoE-1B-7B-0125-DPO.i1-Q3_K_M.gguf new file mode 100644 index 0000000..8f41a54 --- /dev/null +++ b/OLMoE-1B-7B-0125-DPO.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c49a29e301baed1f9b0ffe86eba68b87eb40f7a4fb398350424d68edcaf4de52 +size 3343930880 diff --git a/OLMoE-1B-7B-0125-DPO.i1-Q3_K_S.gguf b/OLMoE-1B-7B-0125-DPO.i1-Q3_K_S.gguf new file mode 100644 index 0000000..65f73e4 --- /dev/null +++ b/OLMoE-1B-7B-0125-DPO.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae735a62b17825162c2ce0517dd0e107cba8bb6b2a4fc6afdc87c896bbb54d19 +size 3023066624 diff --git a/OLMoE-1B-7B-0125-DPO.i1-Q4_0.gguf b/OLMoE-1B-7B-0125-DPO.i1-Q4_0.gguf new file mode 100644 index 0000000..fa3b042 --- /dev/null +++ b/OLMoE-1B-7B-0125-DPO.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cce7862b0d04001fceab5163cb1674b603eed47ccb16399ad06beee532114e1d +size 3944816128 diff --git a/OLMoE-1B-7B-0125-DPO.i1-Q4_1.gguf b/OLMoE-1B-7B-0125-DPO.i1-Q4_1.gguf new file mode 100644 index 0000000..88e4a22 --- /dev/null +++ b/OLMoE-1B-7B-0125-DPO.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc7080fd6bd1494319b822f299fa32a8246cf9cfabf31ab9079717c81a48537d +size 4353908224 diff --git a/OLMoE-1B-7B-0125-DPO.i1-Q4_K_M.gguf b/OLMoE-1B-7B-0125-DPO.i1-Q4_K_M.gguf new file mode 100644 index 0000000..36380ec --- /dev/null +++ b/OLMoE-1B-7B-0125-DPO.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bd144d4df5c97eb26a6a1ab17aa871b74d77424efcbdb501ad292b33480f0bb +size 4213513728 diff --git a/OLMoE-1B-7B-0125-DPO.i1-Q4_K_S.gguf b/OLMoE-1B-7B-0125-DPO.i1-Q4_K_S.gguf new file mode 100644 index 0000000..caa595c --- /dev/null +++ b/OLMoE-1B-7B-0125-DPO.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c356e21ab41f90148a25aee1d19e9ad2404d77c2a9d9bd7a759d845111c1dc0 +size 3963690496 diff --git a/OLMoE-1B-7B-0125-DPO.i1-Q5_K_M.gguf b/OLMoE-1B-7B-0125-DPO.i1-Q5_K_M.gguf new file mode 100644 index 0000000..819971b --- /dev/null +++ b/OLMoE-1B-7B-0125-DPO.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56ed56337b04a9690d6afe7c90ef6abe24b94cfd7e5eb1cd6b8dbd38d1a54a37 +size 4926840320 diff --git a/OLMoE-1B-7B-0125-DPO.i1-Q5_K_S.gguf b/OLMoE-1B-7B-0125-DPO.i1-Q5_K_S.gguf new file mode 100644 index 0000000..9e6a5f5 --- /dev/null +++ b/OLMoE-1B-7B-0125-DPO.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3eae7846c5a0ced4b4fbb804103c5b9efb92a515798337e6aecbf50eeffd3ce5 +size 4779777536 diff --git a/OLMoE-1B-7B-0125-DPO.i1-Q6_K.gguf b/OLMoE-1B-7B-0125-DPO.i1-Q6_K.gguf new file mode 100644 index 0000000..087b83c --- /dev/null +++ b/OLMoE-1B-7B-0125-DPO.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f959d86ee2ddf3a2866d72e52f26d4bec9da9795c0d4f2140c82dfa7cf5ba52 +size 5684749824 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3a17179 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: allenai/OLMoE-1B-7B-0125-DPO +datasets: +- allenai/olmoe-0125-1b-7b-preference-mix +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/allenai/OLMoE-1B-7B-0125-DPO + + +static quants are available at https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-DPO-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/OLMoE-1B-7B-0125-DPO-i1-GGUF/resolve/main/OLMoE-1B-7B-0125-DPO.i1-IQ1_S.gguf) | i1-IQ1_S | 1.6 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-DPO-i1-GGUF/resolve/main/OLMoE-1B-7B-0125-DPO.i1-IQ1_M.gguf) | i1-IQ1_M | 1.7 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-DPO-i1-GGUF/resolve/main/OLMoE-1B-7B-0125-DPO.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-DPO-i1-GGUF/resolve/main/OLMoE-1B-7B-0125-DPO.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-DPO-i1-GGUF/resolve/main/OLMoE-1B-7B-0125-DPO.i1-IQ2_S.gguf) | i1-IQ2_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-DPO-i1-GGUF/resolve/main/OLMoE-1B-7B-0125-DPO.i1-IQ2_M.gguf) | i1-IQ2_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-DPO-i1-GGUF/resolve/main/OLMoE-1B-7B-0125-DPO.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.5 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-DPO-i1-GGUF/resolve/main/OLMoE-1B-7B-0125-DPO.i1-Q2_K.gguf) | i1-Q2_K | 2.7 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-DPO-i1-GGUF/resolve/main/OLMoE-1B-7B-0125-DPO.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-DPO-i1-GGUF/resolve/main/OLMoE-1B-7B-0125-DPO.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-DPO-i1-GGUF/resolve/main/OLMoE-1B-7B-0125-DPO.i1-IQ3_S.gguf) | i1-IQ3_S | 3.1 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-DPO-i1-GGUF/resolve/main/OLMoE-1B-7B-0125-DPO.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.1 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-DPO-i1-GGUF/resolve/main/OLMoE-1B-7B-0125-DPO.i1-IQ3_M.gguf) | i1-IQ3_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-DPO-i1-GGUF/resolve/main/OLMoE-1B-7B-0125-DPO.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-DPO-i1-GGUF/resolve/main/OLMoE-1B-7B-0125-DPO.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-DPO-i1-GGUF/resolve/main/OLMoE-1B-7B-0125-DPO.i1-IQ4_XS.gguf) | i1-IQ4_XS | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-DPO-i1-GGUF/resolve/main/OLMoE-1B-7B-0125-DPO.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-DPO-i1-GGUF/resolve/main/OLMoE-1B-7B-0125-DPO.i1-Q4_0.gguf) | i1-Q4_0 | 4.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-DPO-i1-GGUF/resolve/main/OLMoE-1B-7B-0125-DPO.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.1 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-DPO-i1-GGUF/resolve/main/OLMoE-1B-7B-0125-DPO.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-DPO-i1-GGUF/resolve/main/OLMoE-1B-7B-0125-DPO.i1-Q4_1.gguf) | i1-Q4_1 | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-DPO-i1-GGUF/resolve/main/OLMoE-1B-7B-0125-DPO.i1-Q5_K_S.gguf) | i1-Q5_K_S | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-DPO-i1-GGUF/resolve/main/OLMoE-1B-7B-0125-DPO.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-DPO-i1-GGUF/resolve/main/OLMoE-1B-7B-0125-DPO.i1-Q6_K.gguf) | i1-Q6_K | 5.8 | 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..ae711b1 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a0aeaab4d8c8287d5c49d756102e3fe379ad289183e538cb4e8236ffe1b7fc8 +size 21631411