commit afb753b6598c648b3b7ab8a20b0fb27a8ac9716a Author: ModelHub XC Date: Sun Oct 4 18:35:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-medx_v3-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..54fa069 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.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 +Llama-medx_v3.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama-medx_v3.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-medx_v3.i1-IQ1_M.gguf b/Llama-medx_v3.i1-IQ1_M.gguf new file mode 100644 index 0000000..6cdfd11 --- /dev/null +++ b/Llama-medx_v3.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beceaea63e09d1da1fac0d019f0ab92b194b2e4124a27e071bbfc8380f7ba5ee +size 2161980544 diff --git a/Llama-medx_v3.i1-IQ1_S.gguf b/Llama-medx_v3.i1-IQ1_S.gguf new file mode 100644 index 0000000..109c0e1 --- /dev/null +++ b/Llama-medx_v3.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52a8d898bef96bae07958ff63a2f117d1420a0928b6d735334df6260dfadf245 +size 2019636352 diff --git a/Llama-medx_v3.i1-IQ2_M.gguf b/Llama-medx_v3.i1-IQ2_M.gguf new file mode 100644 index 0000000..c80e843 --- /dev/null +++ b/Llama-medx_v3.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20d35453e53fe84871d4320d48bc78cdc75ed16ae9146823a42a817328086193 +size 2948290496 diff --git a/Llama-medx_v3.i1-IQ2_S.gguf b/Llama-medx_v3.i1-IQ2_S.gguf new file mode 100644 index 0000000..61e7181 --- /dev/null +++ b/Llama-medx_v3.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:574da8a0e69f37c37ad4f5f55fb6c7ba975fe1229a127bbbd056cb7b7a4c1f1f +size 2758498240 diff --git a/Llama-medx_v3.i1-IQ2_XS.gguf b/Llama-medx_v3.i1-IQ2_XS.gguf new file mode 100644 index 0000000..44d7c97 --- /dev/null +++ b/Llama-medx_v3.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6ae1b534650a4078b5af26d1c22ad384d2c24ba209353658ab6f72657c1e230 +size 2605790336 diff --git a/Llama-medx_v3.i1-IQ2_XXS.gguf b/Llama-medx_v3.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..7d95b5e --- /dev/null +++ b/Llama-medx_v3.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f6d4073856eec34bbabccf23d75a98ae996c66faff25da7e8947aff8d0db532 +size 2399220864 diff --git a/Llama-medx_v3.i1-IQ3_M.gguf b/Llama-medx_v3.i1-IQ3_M.gguf new file mode 100644 index 0000000..9563993 --- /dev/null +++ b/Llama-medx_v3.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c09ae6dba5ef4ce9f687e57a73081a3eb7790d97aff834074f7b555c8ae6149 +size 3784834048 diff --git a/Llama-medx_v3.i1-IQ3_S.gguf b/Llama-medx_v3.i1-IQ3_S.gguf new file mode 100644 index 0000000..5cfd40e --- /dev/null +++ b/Llama-medx_v3.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2d25ef85bf524a0b27189e4b42c58dc4a93e54329e33b9c8c0ecd3d2199e54c +size 3682335744 diff --git a/Llama-medx_v3.i1-IQ3_XS.gguf b/Llama-medx_v3.i1-IQ3_XS.gguf new file mode 100644 index 0000000..bd5f0cc --- /dev/null +++ b/Llama-medx_v3.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd0c6418f100dfb8aff553e74ae1b08c6f4ad5f12f1045cceab82290c411cdfd +size 3518757888 diff --git a/Llama-medx_v3.i1-IQ3_XXS.gguf b/Llama-medx_v3.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..c12c5ef --- /dev/null +++ b/Llama-medx_v3.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55fc921cfcb4b886dfb04489360a321cbc71d28a7426002f068467798b32b956 +size 3274921920 diff --git a/Llama-medx_v3.i1-IQ4_NL.gguf b/Llama-medx_v3.i1-IQ4_NL.gguf new file mode 100644 index 0000000..7326605 --- /dev/null +++ b/Llama-medx_v3.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70ebb79ebabd66bf1cff3fa81fa70bac0755032b02c85c09eab6647123fa956b +size 4678000704 diff --git a/Llama-medx_v3.i1-IQ4_XS.gguf b/Llama-medx_v3.i1-IQ4_XS.gguf new file mode 100644 index 0000000..9bc1af2 --- /dev/null +++ b/Llama-medx_v3.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e91bbfab51ba5d6861482abd20f2c0bdd46250bb64e0018f3b8a161e1bae61d7 +size 4447674176 diff --git a/Llama-medx_v3.i1-Q2_K.gguf b/Llama-medx_v3.i1-Q2_K.gguf new file mode 100644 index 0000000..68c84a7 --- /dev/null +++ b/Llama-medx_v3.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de4f14bdce17c2273f46cf777dc5f70085712b0d6e185dd4c380a34f6cf2e3e2 +size 3179141312 diff --git a/Llama-medx_v3.i1-Q2_K_S.gguf b/Llama-medx_v3.i1-Q2_K_S.gguf new file mode 100644 index 0000000..45b7540 --- /dev/null +++ b/Llama-medx_v3.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90d35328e5f5b2e1710d1b682edf21dafe6a191d5665a1343edaf1af69b4e981 +size 2988824768 diff --git a/Llama-medx_v3.i1-Q3_K_L.gguf b/Llama-medx_v3.i1-Q3_K_L.gguf new file mode 100644 index 0000000..06575e5 --- /dev/null +++ b/Llama-medx_v3.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11e62ef5b14505ff4869166282ef4eebd9044d43038052cd86d25f4e836c9f73 +size 4321967104 diff --git a/Llama-medx_v3.i1-Q3_K_M.gguf b/Llama-medx_v3.i1-Q3_K_M.gguf new file mode 100644 index 0000000..36fa1d5 --- /dev/null +++ b/Llama-medx_v3.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96bd752d97bc422ae0c0826fc9a39a82289173b08cc182e9f35b3ecdc2133fca +size 4018928640 diff --git a/Llama-medx_v3.i1-Q3_K_S.gguf b/Llama-medx_v3.i1-Q3_K_S.gguf new file mode 100644 index 0000000..a28b806 --- /dev/null +++ b/Llama-medx_v3.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b6e88cd0799a5e34128387fecd1fc290b5fca06c09eeda5dda0ce2a1797ee6c +size 3664509952 diff --git a/Llama-medx_v3.i1-Q4_0.gguf b/Llama-medx_v3.i1-Q4_0.gguf new file mode 100644 index 0000000..767f859 --- /dev/null +++ b/Llama-medx_v3.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4425365843d70a585674c0934671f23e6a4959da8fa79f86c34b9d3b48a39ef9 +size 4675903552 diff --git a/Llama-medx_v3.i1-Q4_1.gguf b/Llama-medx_v3.i1-Q4_1.gguf new file mode 100644 index 0000000..a23c6de --- /dev/null +++ b/Llama-medx_v3.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f996300eb8dd9db58a3c6b2f63fade9e446877942e3db389bde5ba3f74f2681c +size 5130265152 diff --git a/Llama-medx_v3.i1-Q4_K_M.gguf b/Llama-medx_v3.i1-Q4_K_M.gguf new file mode 100644 index 0000000..005fe6a --- /dev/null +++ b/Llama-medx_v3.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd9597bcdc0a62d484e37117c6a9cec46cc2acf6ee2c4dedcea01939214abb07 +size 4920746048 diff --git a/Llama-medx_v3.i1-Q4_K_S.gguf b/Llama-medx_v3.i1-Q4_K_S.gguf new file mode 100644 index 0000000..4f04548 --- /dev/null +++ b/Llama-medx_v3.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4112d11fdb9f9a6c5a4c26b442dd0ef3ab1bd1500d23d3d63af0c2d7b29ce7c4 +size 4692680768 diff --git a/Llama-medx_v3.i1-Q5_K_M.gguf b/Llama-medx_v3.i1-Q5_K_M.gguf new file mode 100644 index 0000000..90a96f7 --- /dev/null +++ b/Llama-medx_v3.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a828905c930596ad4e781a4faf1bd72a8d7e3d762ecfcf3c0b9c724723187be +size 5733000256 diff --git a/Llama-medx_v3.i1-Q5_K_S.gguf b/Llama-medx_v3.i1-Q5_K_S.gguf new file mode 100644 index 0000000..5508d12 --- /dev/null +++ b/Llama-medx_v3.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47d08d08699da9a24829f24cbc154940a4a238f79a6699152fd517239f4c185b +size 5599306816 diff --git a/Llama-medx_v3.i1-Q6_K.gguf b/Llama-medx_v3.i1-Q6_K.gguf new file mode 100644 index 0000000..cade0d4 --- /dev/null +++ b/Llama-medx_v3.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b27fd352b9e8c41925681fbd1c1c207cf637bbb1efc7cdb5dd47c045ebdcd28 +size 6596020352 diff --git a/README.md b/README.md new file mode 100644 index 0000000..744b69b --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: skumar9/Llama-medx_v3 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/skumar9/Llama-medx_v3 + + +static quants are available at https://huggingface.co/mradermacher/Llama-medx_v3-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/Llama-medx_v3-i1-GGUF/resolve/main/Llama-medx_v3.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-i1-GGUF/resolve/main/Llama-medx_v3.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-i1-GGUF/resolve/main/Llama-medx_v3.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-i1-GGUF/resolve/main/Llama-medx_v3.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-i1-GGUF/resolve/main/Llama-medx_v3.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-i1-GGUF/resolve/main/Llama-medx_v3.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-i1-GGUF/resolve/main/Llama-medx_v3.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-i1-GGUF/resolve/main/Llama-medx_v3.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-i1-GGUF/resolve/main/Llama-medx_v3.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-i1-GGUF/resolve/main/Llama-medx_v3.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-i1-GGUF/resolve/main/Llama-medx_v3.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-i1-GGUF/resolve/main/Llama-medx_v3.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-i1-GGUF/resolve/main/Llama-medx_v3.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-i1-GGUF/resolve/main/Llama-medx_v3.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-i1-GGUF/resolve/main/Llama-medx_v3.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-i1-GGUF/resolve/main/Llama-medx_v3.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-i1-GGUF/resolve/main/Llama-medx_v3.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-i1-GGUF/resolve/main/Llama-medx_v3.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-i1-GGUF/resolve/main/Llama-medx_v3.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-i1-GGUF/resolve/main/Llama-medx_v3.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-i1-GGUF/resolve/main/Llama-medx_v3.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-i1-GGUF/resolve/main/Llama-medx_v3.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-i1-GGUF/resolve/main/Llama-medx_v3.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-medx_v3-i1-GGUF/resolve/main/Llama-medx_v3.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. + +