commit 980c4806653b6f56ad40ce791a8be6d12bf56a24 Author: ModelHub XC Date: Sat Jun 6 22:32:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-Math-14B-Instruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c71d813 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,58 @@ +*.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 +Qwen2.5-Math-14B-Instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-14B-Instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-Math-14B-Instruct.i1-IQ1_M.gguf b/Qwen2.5-Math-14B-Instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..6b9b660 --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6a1778222fbe5783fb23359f5e36d47792fb17e032c0e46c2205858c2fd9ab0 +size 3872309856 diff --git a/Qwen2.5-Math-14B-Instruct.i1-IQ1_S.gguf b/Qwen2.5-Math-14B-Instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..d808994 --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:025abd40fbb45f42296984bbec90d358d32dd6bde79968332beace5d148f996b +size 3607994976 diff --git a/Qwen2.5-Math-14B-Instruct.i1-IQ2_M.gguf b/Qwen2.5-Math-14B-Instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..5d6b97e --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:563ae772c4387d90012e306f9f78dbd43d5a00821d5ecce367d938fe4cc8a044 +size 5356147296 diff --git a/Qwen2.5-Math-14B-Instruct.i1-IQ2_S.gguf b/Qwen2.5-Math-14B-Instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..f3f6366 --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05cfc8945f2b8543926b785e1dc0e45bb83eab76ade783d74620d687d66f15a8 +size 5003727456 diff --git a/Qwen2.5-Math-14B-Instruct.i1-IQ2_XS.gguf b/Qwen2.5-Math-14B-Instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..dc3f73a --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af4c0170986421cbe5306f4d1d271fd49e75be4c5311e22ff978047fc98b5f25 +size 4704576096 diff --git a/Qwen2.5-Math-14B-Instruct.i1-IQ2_XXS.gguf b/Qwen2.5-Math-14B-Instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..0be6c53 --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f2cd4dfcf1bf8baebab7d501fc4743cbb41f6162c185ee7cdce93568e1b07f0 +size 4312834656 diff --git a/Qwen2.5-Math-14B-Instruct.i1-IQ3_M.gguf b/Qwen2.5-Math-14B-Instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..ceae75b --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f18f1b7d1b5d7d05b79b64bd2792ff57043938dc2a68e18d7b48f2657a86a92b +size 6916538976 diff --git a/Qwen2.5-Math-14B-Instruct.i1-IQ3_S.gguf b/Qwen2.5-Math-14B-Instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..c94f28d --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46b820baba55568e86ac99fd1077ec05016987e8f5c118d8fced945a12e2bb35 +size 6693020256 diff --git a/Qwen2.5-Math-14B-Instruct.i1-IQ3_XS.gguf b/Qwen2.5-Math-14B-Instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..0f6d2f6 --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e17982e89bebaca308e830dd643853eec1a39f1e5f251fc518e2a3b3f23ac03 +size 6383362656 diff --git a/Qwen2.5-Math-14B-Instruct.i1-IQ3_XXS.gguf b/Qwen2.5-Math-14B-Instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..4324ee8 --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bae4037bf26385988f29ba830a0a3ee2a19e9b9784431cbeb9e5180fe27ce8a8 +size 5946708576 diff --git a/Qwen2.5-Math-14B-Instruct.i1-IQ4_XS.gguf b/Qwen2.5-Math-14B-Instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..735dec4 --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65c8e41c30b7da0b7e9ea1a7038751fd58be4ccd41b48c975a4272530eda0352 +size 8119841376 diff --git a/Qwen2.5-Math-14B-Instruct.i1-Q2_K.gguf b/Qwen2.5-Math-14B-Instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..176a19b --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbb9f8e0bb9b377695eda5e19280e643c1f8e9affef68d4c076af80482ee1b5d +size 5770498656 diff --git a/Qwen2.5-Math-14B-Instruct.i1-Q2_K_S.gguf b/Qwen2.5-Math-14B-Instruct.i1-Q2_K_S.gguf new file mode 100644 index 0000000..4103839 --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e2886af77e36e187b04c5d734ff703aef584bff66f4603dd8c846971b3bf92a +size 5397189216 diff --git a/Qwen2.5-Math-14B-Instruct.i1-Q3_K_L.gguf b/Qwen2.5-Math-14B-Instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..3c7361b --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e2deb52df79430c12c5b6b705670a31d04ecc9f579b2874f838cfebfa6e9ace +size 7924769376 diff --git a/Qwen2.5-Math-14B-Instruct.i1-Q3_K_M.gguf b/Qwen2.5-Math-14B-Instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..84c2c69 --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f50ca18db8861e901f30937da06becdf2cf9a41dc0d62337a391dec542083be +size 7339205216 diff --git a/Qwen2.5-Math-14B-Instruct.i1-Q3_K_S.gguf b/Qwen2.5-Math-14B-Instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..1609e12 --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9613d18fb6acda1e0f34a4eb8c4c039c8760e7299ed667bc0adacd96b0e758d1 +size 6659596896 diff --git a/Qwen2.5-Math-14B-Instruct.i1-Q4_0.gguf b/Qwen2.5-Math-14B-Instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..4fbb6ef --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bb34c7f74b57f54243d26ccd56972edaab9e22235ea2d650f5c04e8617f4a60 +size 8544268896 diff --git a/Qwen2.5-Math-14B-Instruct.i1-Q4_K_M.gguf b/Qwen2.5-Math-14B-Instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..39a0958 --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc716ff6ef6cbf1382c12bfe4052ec8bada1c067d7f6c71e28c366f70c904e06 +size 8988111456 diff --git a/Qwen2.5-Math-14B-Instruct.i1-Q4_K_S.gguf b/Qwen2.5-Math-14B-Instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..6ea28cf --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82c3d1a0e97b0f904a27d90770bc24bb01ec014fd05b26dbc5558e045fbc624c +size 8573432416 diff --git a/Qwen2.5-Math-14B-Instruct.i1-Q5_K_M.gguf b/Qwen2.5-Math-14B-Instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..b1847ae --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35aa49e12fb2d6c4be150defc80c5729a0fd7b133ccdcab59bed42e597928aa8 +size 10508874336 diff --git a/Qwen2.5-Math-14B-Instruct.i1-Q5_K_S.gguf b/Qwen2.5-Math-14B-Instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..4d860cf --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:623924f203d7a9a5dd15b4154375cb2504c93c29d6a56765ca2768898d08db83 +size 10266554976 diff --git a/Qwen2.5-Math-14B-Instruct.i1-Q6_K.gguf b/Qwen2.5-Math-14B-Instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..cc510af --- /dev/null +++ b/Qwen2.5-Math-14B-Instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07445d7ed23950a43da4eb1eec5caa60d7db9bc574e177346310dc4d7c3b8a6d +size 12124684896 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fcb5e39 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: qingy2024/Qwen2.5-Math-14B-Instruct-Preview +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/qingy2024/Qwen2.5-Math-14B-Instruct-Preview + + +static quants are available at https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-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/Qwen2.5-Math-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 3.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 4.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.5 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 6.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 7.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 8.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-14B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Math-14B-Instruct.i1-Q6_K.gguf) | i1-Q6_K | 12.2 | 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..2911c8c --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cd041df13973daa267fd54dd0d988e6a86bb554065627b8df912b5c1c9c7b23 +size 8563597