commit c005e1f4e45876a0081bf35f68437222eabe6614 Author: ModelHub XC Date: Mon May 18 06:33:29 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Med-Llama-3.1-8B-DeepSeek67B-Distilled-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0a03702 --- /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 +Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ1_M.gguf b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ1_M.gguf new file mode 100644 index 0000000..06e61ca --- /dev/null +++ b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5855757e799af3ec0f2f7df9872590ebc99f30ae12d9d473dac7f873eaaf4c1f +size 2161972800 diff --git a/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ1_S.gguf b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ1_S.gguf new file mode 100644 index 0000000..9025679 --- /dev/null +++ b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:899136810452f2167c234f55c9451fde930f005b9096ca8754de9af255a1fce4 +size 2019628608 diff --git a/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ2_M.gguf b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ2_M.gguf new file mode 100644 index 0000000..c9f3aae --- /dev/null +++ b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31d56f785b810cc04338d2b055a503f6044296530a75855e3b545ec3afe4f9b8 +size 2948281920 diff --git a/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ2_S.gguf b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ2_S.gguf new file mode 100644 index 0000000..2f1794e --- /dev/null +++ b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:160f510d1e186ed81ddf9ca653e4c1eafc5d83d7799d2c2f33076c56b82a2e02 +size 2758489664 diff --git a/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ2_XS.gguf b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ2_XS.gguf new file mode 100644 index 0000000..ab96edd --- /dev/null +++ b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1106c9b000e15c5a6dba167ac2c17bc0597b114a95e47c5fb57a4c18b86ed60 +size 2605782592 diff --git a/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ2_XXS.gguf b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..ca40051 --- /dev/null +++ b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc7918c3044be54c9b350710116bd27d4bb4de0a008b1f99d2d388a68a292e06 +size 2399213120 diff --git a/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ3_M.gguf b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ3_M.gguf new file mode 100644 index 0000000..17557c5 --- /dev/null +++ b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1af66fff59a6547c7ae3eec46277c72c5e87b6bf01946e8a8a390fa8af918f0a +size 3784824384 diff --git a/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ3_S.gguf b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ3_S.gguf new file mode 100644 index 0000000..a4eb34f --- /dev/null +++ b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c2f1c61ef04f45565777b20defa4ef5da7998ef38738e148f7f253c023940a9 +size 3682326080 diff --git a/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ3_XS.gguf b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ3_XS.gguf new file mode 100644 index 0000000..ec5d2f5 --- /dev/null +++ b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:040ab060de7341bec5ea99bcee8c5d4c65769dda887dc3f7ac3e264cc0029da5 +size 3518748224 diff --git a/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ3_XXS.gguf b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..eabd888 --- /dev/null +++ b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9b21dee580dddb815126f293f80f058d0ec0229456e5ca00ea85d05a3a938e4 +size 3274913344 diff --git a/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ4_NL.gguf b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ4_NL.gguf new file mode 100644 index 0000000..2daf60e --- /dev/null +++ b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed1f2b7722745856162131b6e602129dc024ea4e48b718eac21ada902d3a43ed +size 4677989952 diff --git a/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ4_XS.gguf b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ4_XS.gguf new file mode 100644 index 0000000..75a0d6c --- /dev/null +++ b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b466f5873d8d88dfe8c31afeaaef8c7a791826be688727399b948d7f3cd2ff2 +size 4447663680 diff --git a/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q2_K.gguf b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q2_K.gguf new file mode 100644 index 0000000..85d2d43 --- /dev/null +++ b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f76be79f32976c4a2b0f1345298d3d5fa100ac7c75f3baf7f34bc74c0015e3d +size 3179132480 diff --git a/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q2_K_S.gguf b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q2_K_S.gguf new file mode 100644 index 0000000..f56d7a8 --- /dev/null +++ b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe9eff2c7787094af0964e2c0c4ab8d84e718ad805ebe0ab347262688ec47ebb +size 2988815936 diff --git a/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q3_K_L.gguf b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q3_K_L.gguf new file mode 100644 index 0000000..3fc1dac --- /dev/null +++ b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:598c6b3bd1057b696d124119681a5befa48196d6ee138c1fb69b5c151886c09a +size 4321957440 diff --git a/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q3_K_M.gguf b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q3_K_M.gguf new file mode 100644 index 0000000..2a31605 --- /dev/null +++ b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce6ebb2036adb2b559803125e5baee61f4febf8ab541aa080cb93f3d7aa14e7d +size 4018918976 diff --git a/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q3_K_S.gguf b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q3_K_S.gguf new file mode 100644 index 0000000..d9e8525 --- /dev/null +++ b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b5b8954852e9052b8c72dc41dbeec54f9f173cc1a2597d3cee2812ec3983348 +size 3664500288 diff --git a/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q4_0.gguf b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q4_0.gguf new file mode 100644 index 0000000..b230e39 --- /dev/null +++ b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af4b52e39bdd2ab4216923f315379fc98380b03589430fbf9ca726cada643b03 +size 4675892800 diff --git a/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q4_1.gguf b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q4_1.gguf new file mode 100644 index 0000000..34f5f60 --- /dev/null +++ b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c95aaa2fa3621eb2a86f6f37b9d304f06befe614a2cb1d1639bfe368980ec9f +size 5130253888 diff --git a/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q4_K_M.gguf b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q4_K_M.gguf new file mode 100644 index 0000000..998212b --- /dev/null +++ b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a05f864bfa8508e67a5c2870a33a92da8df12a35649c2f235da31d6064152380 +size 4920735296 diff --git a/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q4_K_S.gguf b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q4_K_S.gguf new file mode 100644 index 0000000..0e6b8b4 --- /dev/null +++ b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8da94b88c7c57a87156b2cfc19eb16a046350348d2c0f27435e2b4ce1d06d2e1 +size 4692670016 diff --git a/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q5_K_M.gguf b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q5_K_M.gguf new file mode 100644 index 0000000..c19cb75 --- /dev/null +++ b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dadefee0a4b924bb5a90756515e871abaeaf0987e870d01ed76e3a4658c789f +size 5732988480 diff --git a/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q5_K_S.gguf b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q5_K_S.gguf new file mode 100644 index 0000000..6af92f4 --- /dev/null +++ b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c48dfd77615a31894df1ea5d75f5a9fb607b1ec1015ccb09982aba50eca101f1 +size 5599295040 diff --git a/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q6_K.gguf b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q6_K.gguf new file mode 100644 index 0000000..939eb08 --- /dev/null +++ b/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f8fe7d760fd40470eee9ee9d19d8e39ce9cb23cae6115a84bad1a1ad6b35ae1 +size 6596007488 diff --git a/README.md b/README.md new file mode 100644 index 0000000..087df53 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: enesarda22/Med-Llama-3.1-8B-DeepSeek67B-Distilled +datasets: +- bigbio/med_qa +- qiaojin/PubMedQA +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/enesarda22/Med-Llama-3.1-8B-DeepSeek67B-Distilled + + +static quants are available at https://huggingface.co/mradermacher/Med-Llama-3.1-8B-DeepSeek67B-Distilled-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/Med-Llama-3.1-8B-DeepSeek67B-Distilled-i1-GGUF/resolve/main/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.1-8B-DeepSeek67B-Distilled-i1-GGUF/resolve/main/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.1-8B-DeepSeek67B-Distilled-i1-GGUF/resolve/main/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.1-8B-DeepSeek67B-Distilled-i1-GGUF/resolve/main/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.1-8B-DeepSeek67B-Distilled-i1-GGUF/resolve/main/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.1-8B-DeepSeek67B-Distilled-i1-GGUF/resolve/main/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.1-8B-DeepSeek67B-Distilled-i1-GGUF/resolve/main/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.1-8B-DeepSeek67B-Distilled-i1-GGUF/resolve/main/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.1-8B-DeepSeek67B-Distilled-i1-GGUF/resolve/main/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.1-8B-DeepSeek67B-Distilled-i1-GGUF/resolve/main/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.1-8B-DeepSeek67B-Distilled-i1-GGUF/resolve/main/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.1-8B-DeepSeek67B-Distilled-i1-GGUF/resolve/main/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.1-8B-DeepSeek67B-Distilled-i1-GGUF/resolve/main/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.1-8B-DeepSeek67B-Distilled-i1-GGUF/resolve/main/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.1-8B-DeepSeek67B-Distilled-i1-GGUF/resolve/main/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.1-8B-DeepSeek67B-Distilled-i1-GGUF/resolve/main/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.1-8B-DeepSeek67B-Distilled-i1-GGUF/resolve/main/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.1-8B-DeepSeek67B-Distilled-i1-GGUF/resolve/main/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.1-8B-DeepSeek67B-Distilled-i1-GGUF/resolve/main/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.1-8B-DeepSeek67B-Distilled-i1-GGUF/resolve/main/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.1-8B-DeepSeek67B-Distilled-i1-GGUF/resolve/main/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.1-8B-DeepSeek67B-Distilled-i1-GGUF/resolve/main/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.1-8B-DeepSeek67B-Distilled-i1-GGUF/resolve/main/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.1-8B-DeepSeek67B-Distilled-i1-GGUF/resolve/main/Med-Llama-3.1-8B-DeepSeek67B-Distilled.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | 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..c10a71f --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0980975c391ce789252de19e1c3afe736ec2439a89c82a98ecabb77f9f7579b6 +size 4988157