commit ebd864bfa3be2c8217f8268150c3942ea13a49d2 Author: ModelHub XC Date: Tue Apr 14 00:30:05 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/BioXP-0.5B-MedMCQA-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6532237 --- /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 +BioXP-0.5B-MedMCQA.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +BioXP-0.5B-MedMCQA.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +BioXP-0.5B-MedMCQA.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +BioXP-0.5B-MedMCQA.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +BioXP-0.5B-MedMCQA.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +BioXP-0.5B-MedMCQA.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +BioXP-0.5B-MedMCQA.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +BioXP-0.5B-MedMCQA.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +BioXP-0.5B-MedMCQA.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +BioXP-0.5B-MedMCQA.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +BioXP-0.5B-MedMCQA.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +BioXP-0.5B-MedMCQA.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +BioXP-0.5B-MedMCQA.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +BioXP-0.5B-MedMCQA.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BioXP-0.5B-MedMCQA.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +BioXP-0.5B-MedMCQA.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BioXP-0.5B-MedMCQA.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BioXP-0.5B-MedMCQA.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +BioXP-0.5B-MedMCQA.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +BioXP-0.5B-MedMCQA.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BioXP-0.5B-MedMCQA.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BioXP-0.5B-MedMCQA.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BioXP-0.5B-MedMCQA.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BioXP-0.5B-MedMCQA.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/BioXP-0.5B-MedMCQA.i1-IQ1_M.gguf b/BioXP-0.5B-MedMCQA.i1-IQ1_M.gguf new file mode 100644 index 0000000..f31ef08 --- /dev/null +++ b/BioXP-0.5B-MedMCQA.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2c5916795e738e44815a205dd3d3da6b2d99cf4b047e7eb383d153973417007 +size 317975264 diff --git a/BioXP-0.5B-MedMCQA.i1-IQ1_S.gguf b/BioXP-0.5B-MedMCQA.i1-IQ1_S.gguf new file mode 100644 index 0000000..a63db28 --- /dev/null +++ b/BioXP-0.5B-MedMCQA.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:226d85004f508a4a362c3543c22bbf15ad2c3a3d633753ecd92a47fca0f2b97e +size 315830240 diff --git a/BioXP-0.5B-MedMCQA.i1-IQ2_M.gguf b/BioXP-0.5B-MedMCQA.i1-IQ2_M.gguf new file mode 100644 index 0000000..0aa8260 --- /dev/null +++ b/BioXP-0.5B-MedMCQA.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03371a42b0659b2308723bb915f0d6615adc613ab32b1bc07a851d1db9b66547 +size 328598240 diff --git a/BioXP-0.5B-MedMCQA.i1-IQ2_S.gguf b/BioXP-0.5B-MedMCQA.i1-IQ2_S.gguf new file mode 100644 index 0000000..149ce23 --- /dev/null +++ b/BioXP-0.5B-MedMCQA.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b9d20d98d774310b8bf705fd9f910fd13e216ab3f4a2af80775ca3bc52e2c6f +size 325738208 diff --git a/BioXP-0.5B-MedMCQA.i1-IQ2_XS.gguf b/BioXP-0.5B-MedMCQA.i1-IQ2_XS.gguf new file mode 100644 index 0000000..287761b --- /dev/null +++ b/BioXP-0.5B-MedMCQA.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a0149738336b037a9d2b2235fafc52f8813030fff81b10cf54804140a747cbe +size 324410336 diff --git a/BioXP-0.5B-MedMCQA.i1-IQ2_XXS.gguf b/BioXP-0.5B-MedMCQA.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..49956dc --- /dev/null +++ b/BioXP-0.5B-MedMCQA.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:267e07d51518aa5b690842f4097eee7bbd0f5f978b791fc0c576e46fd3afe793 +size 321550304 diff --git a/BioXP-0.5B-MedMCQA.i1-IQ3_M.gguf b/BioXP-0.5B-MedMCQA.i1-IQ3_M.gguf new file mode 100644 index 0000000..806daa2 --- /dev/null +++ b/BioXP-0.5B-MedMCQA.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d375a5185b38cc1c8bc2e02f95740029c594f7749050adf770617b50b42c4995 +size 342753248 diff --git a/BioXP-0.5B-MedMCQA.i1-IQ3_S.gguf b/BioXP-0.5B-MedMCQA.i1-IQ3_S.gguf new file mode 100644 index 0000000..0590400 --- /dev/null +++ b/BioXP-0.5B-MedMCQA.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cf946d30b32682b49ab31f6ac33b837483bc68317311f3fcfc427596d0a0248 +size 338608352 diff --git a/BioXP-0.5B-MedMCQA.i1-IQ3_XS.gguf b/BioXP-0.5B-MedMCQA.i1-IQ3_XS.gguf new file mode 100644 index 0000000..ce082de --- /dev/null +++ b/BioXP-0.5B-MedMCQA.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25b6277f7d0c0456d46f7ef2793e329f3c2155e76f5f028b360e3b6751ccbf4b +size 338608352 diff --git a/BioXP-0.5B-MedMCQA.i1-IQ3_XXS.gguf b/BioXP-0.5B-MedMCQA.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..71c1115 --- /dev/null +++ b/BioXP-0.5B-MedMCQA.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae40917a7eb9d641ed33b2ee9472f4176cfa37629dc13de6360d0cc79e2c49bf +size 333705440 diff --git a/BioXP-0.5B-MedMCQA.i1-IQ4_NL.gguf b/BioXP-0.5B-MedMCQA.i1-IQ4_NL.gguf new file mode 100644 index 0000000..a2ef7f3 --- /dev/null +++ b/BioXP-0.5B-MedMCQA.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aed1e0de0c67b5a27b3997c9dde7b3dde5a07aa6d57c83590b33536cdd2e8426 +size 352671968 diff --git a/BioXP-0.5B-MedMCQA.i1-IQ4_XS.gguf b/BioXP-0.5B-MedMCQA.i1-IQ4_XS.gguf new file mode 100644 index 0000000..dd240d3 --- /dev/null +++ b/BioXP-0.5B-MedMCQA.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4a09b5400ff1f4e74088d8dac5cdf0f045581d63e6e6a301a96fa78799541c7 +size 349403360 diff --git a/BioXP-0.5B-MedMCQA.i1-Q2_K.gguf b/BioXP-0.5B-MedMCQA.i1-Q2_K.gguf new file mode 100644 index 0000000..45f182c --- /dev/null +++ b/BioXP-0.5B-MedMCQA.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1f82098261e79ef2b9f88297e2074d2260e48d5a8591e2bee246e062bc273da +size 338608352 diff --git a/BioXP-0.5B-MedMCQA.i1-Q2_K_S.gguf b/BioXP-0.5B-MedMCQA.i1-Q2_K_S.gguf new file mode 100644 index 0000000..e97419e --- /dev/null +++ b/BioXP-0.5B-MedMCQA.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22f22b87aa65bcc6734f27e536da3f3c2af2a6b65c689481adb6ae0d04143d65 +size 331049696 diff --git a/BioXP-0.5B-MedMCQA.i1-Q3_K_L.gguf b/BioXP-0.5B-MedMCQA.i1-Q3_K_L.gguf new file mode 100644 index 0000000..910f1be --- /dev/null +++ b/BioXP-0.5B-MedMCQA.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba921a3c6b14dbbf8c03ab0f62f7f96e1cd28902b0a95dc182a8dc12dec7b985 +size 369359072 diff --git a/BioXP-0.5B-MedMCQA.i1-Q3_K_M.gguf b/BioXP-0.5B-MedMCQA.i1-Q3_K_M.gguf new file mode 100644 index 0000000..cae5977 --- /dev/null +++ b/BioXP-0.5B-MedMCQA.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f39d4cdff85e8121e44c438583cfd3bd7fb1cf801ad207dc07badd42ca90b452 +size 355467488 diff --git a/BioXP-0.5B-MedMCQA.i1-Q3_K_S.gguf b/BioXP-0.5B-MedMCQA.i1-Q3_K_S.gguf new file mode 100644 index 0000000..752cbfa --- /dev/null +++ b/BioXP-0.5B-MedMCQA.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a903487fe5318c347bbfff430cf5092a0cc9425f277b4b77b7374dda199a3a32 +size 338264288 diff --git a/BioXP-0.5B-MedMCQA.i1-Q4_0.gguf b/BioXP-0.5B-MedMCQA.i1-Q4_0.gguf new file mode 100644 index 0000000..7a3046e --- /dev/null +++ b/BioXP-0.5B-MedMCQA.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4abf04ad94c236f8b8a464c7d8b9e6329a7e63f4194e7cca3feca6c6b8ed2410 +size 352973024 diff --git a/BioXP-0.5B-MedMCQA.i1-Q4_1.gguf b/BioXP-0.5B-MedMCQA.i1-Q4_1.gguf new file mode 100644 index 0000000..5889105 --- /dev/null +++ b/BioXP-0.5B-MedMCQA.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ce3e06dfd85dda8f2b7c52690701254dea900ec46c1c1bb1388003259d99577 +size 374520032 diff --git a/BioXP-0.5B-MedMCQA.i1-Q4_K_M.gguf b/BioXP-0.5B-MedMCQA.i1-Q4_K_M.gguf new file mode 100644 index 0000000..a77f358 --- /dev/null +++ b/BioXP-0.5B-MedMCQA.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdf98a7172f3917bf847d0265254db82334b427f77cdaa2b03808c5ab1257e54 +size 397808864 diff --git a/BioXP-0.5B-MedMCQA.i1-Q4_K_S.gguf b/BioXP-0.5B-MedMCQA.i1-Q4_K_S.gguf new file mode 100644 index 0000000..5e4457c --- /dev/null +++ b/BioXP-0.5B-MedMCQA.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23d512a0df414724e23eae871a1372bfae9c33509dd25a9a6f9ec660402891a7 +size 385472736 diff --git a/BioXP-0.5B-MedMCQA.i1-Q5_K_M.gguf b/BioXP-0.5B-MedMCQA.i1-Q5_K_M.gguf new file mode 100644 index 0000000..95914e5 --- /dev/null +++ b/BioXP-0.5B-MedMCQA.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:588384390876266ee9fc32ea05a249585226ec865895d892eae8bb6d98fbf847 +size 420087008 diff --git a/BioXP-0.5B-MedMCQA.i1-Q5_K_S.gguf b/BioXP-0.5B-MedMCQA.i1-Q5_K_S.gguf new file mode 100644 index 0000000..3e6fd2e --- /dev/null +++ b/BioXP-0.5B-MedMCQA.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e73802ae59014985f914bf93718ef2414a6b0040f110c4433c9ea2defdc66a17 +size 412711136 diff --git a/BioXP-0.5B-MedMCQA.i1-Q6_K.gguf b/BioXP-0.5B-MedMCQA.i1-Q6_K.gguf new file mode 100644 index 0000000..ae03d60 --- /dev/null +++ b/BioXP-0.5B-MedMCQA.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f44f498250b0b8169812a04e9fc5f1930889f02e8ec3aa486e091e6f453c9bd5 +size 505737440 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0a84169 --- /dev/null +++ b/README.md @@ -0,0 +1,93 @@ +--- +base_model: abaryan/BioXP-0.5B-MedMCQA +datasets: +- openlifescienceai/medmcqa +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- grpo +- rl +- biomed +- medmcqa +- medical +- explainableAI +- XAI +- tramsformers +- trl +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/abaryan/BioXP-0.5B-MedMCQA + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#BioXP-0.5B-MedMCQA-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/BioXP-0.5B-MedMCQA-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/BioXP-0.5B-MedMCQA-i1-GGUF/resolve/main/BioXP-0.5B-MedMCQA.i1-IQ1_S.gguf) | i1-IQ1_S | 0.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/BioXP-0.5B-MedMCQA-i1-GGUF/resolve/main/BioXP-0.5B-MedMCQA.i1-IQ1_M.gguf) | i1-IQ1_M | 0.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/BioXP-0.5B-MedMCQA-i1-GGUF/resolve/main/BioXP-0.5B-MedMCQA.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/BioXP-0.5B-MedMCQA-i1-GGUF/resolve/main/BioXP-0.5B-MedMCQA.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/BioXP-0.5B-MedMCQA-i1-GGUF/resolve/main/BioXP-0.5B-MedMCQA.i1-IQ2_S.gguf) | i1-IQ2_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/BioXP-0.5B-MedMCQA-i1-GGUF/resolve/main/BioXP-0.5B-MedMCQA.i1-IQ2_M.gguf) | i1-IQ2_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/BioXP-0.5B-MedMCQA-i1-GGUF/resolve/main/BioXP-0.5B-MedMCQA.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/BioXP-0.5B-MedMCQA-i1-GGUF/resolve/main/BioXP-0.5B-MedMCQA.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/BioXP-0.5B-MedMCQA-i1-GGUF/resolve/main/BioXP-0.5B-MedMCQA.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/BioXP-0.5B-MedMCQA-i1-GGUF/resolve/main/BioXP-0.5B-MedMCQA.i1-IQ3_S.gguf) | i1-IQ3_S | 0.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/BioXP-0.5B-MedMCQA-i1-GGUF/resolve/main/BioXP-0.5B-MedMCQA.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/BioXP-0.5B-MedMCQA-i1-GGUF/resolve/main/BioXP-0.5B-MedMCQA.i1-Q2_K.gguf) | i1-Q2_K | 0.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/BioXP-0.5B-MedMCQA-i1-GGUF/resolve/main/BioXP-0.5B-MedMCQA.i1-IQ3_M.gguf) | i1-IQ3_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/BioXP-0.5B-MedMCQA-i1-GGUF/resolve/main/BioXP-0.5B-MedMCQA.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/BioXP-0.5B-MedMCQA-i1-GGUF/resolve/main/BioXP-0.5B-MedMCQA.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/BioXP-0.5B-MedMCQA-i1-GGUF/resolve/main/BioXP-0.5B-MedMCQA.i1-Q4_0.gguf) | i1-Q4_0 | 0.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/BioXP-0.5B-MedMCQA-i1-GGUF/resolve/main/BioXP-0.5B-MedMCQA.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.5 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/BioXP-0.5B-MedMCQA-i1-GGUF/resolve/main/BioXP-0.5B-MedMCQA.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/BioXP-0.5B-MedMCQA-i1-GGUF/resolve/main/BioXP-0.5B-MedMCQA.i1-Q4_1.gguf) | i1-Q4_1 | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/BioXP-0.5B-MedMCQA-i1-GGUF/resolve/main/BioXP-0.5B-MedMCQA.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/BioXP-0.5B-MedMCQA-i1-GGUF/resolve/main/BioXP-0.5B-MedMCQA.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BioXP-0.5B-MedMCQA-i1-GGUF/resolve/main/BioXP-0.5B-MedMCQA.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/BioXP-0.5B-MedMCQA-i1-GGUF/resolve/main/BioXP-0.5B-MedMCQA.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/BioXP-0.5B-MedMCQA-i1-GGUF/resolve/main/BioXP-0.5B-MedMCQA.i1-Q6_K.gguf) | i1-Q6_K | 0.6 | 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..fbd68d5 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcb441518e82681271d33b21ecccdab2360b63e65b2ae38ec72eaaf13b62eddf +size 988597