commit 4018296c031a29f172d70ce41df49bcbe03ffdee Author: ModelHub XC Date: Sun Jul 19 02:25:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-Coder-32B-Instruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..df2971c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.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-Coder-32B-Instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-32B-Instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-32B-Instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-32B-Instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-32B-Instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-32B-Instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-32B-Instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-32B-Instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-32B-Instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-32B-Instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-32B-Instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-32B-Instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-32B-Instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-32B-Instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-32B-Instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-32B-Instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-32B-Instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-32B-Instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-32B-Instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-32B-Instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-32B-Instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-Coder-32B-Instruct.i1-IQ1_M.gguf b/Qwen2.5-Coder-32B-Instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..4568765 --- /dev/null +++ b/Qwen2.5-Coder-32B-Instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e27029e9696235987d104b3e31ae2d00349519ac24e67ad3db3a8dc1470ab411 +size 7932161408 diff --git a/Qwen2.5-Coder-32B-Instruct.i1-IQ1_S.gguf b/Qwen2.5-Coder-32B-Instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..23f4711 --- /dev/null +++ b/Qwen2.5-Coder-32B-Instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2cc2e6c8aba347b4121ec79bf407ed8fd40319da2d403f930be3e9f882b16dd +size 7274507648 diff --git a/Qwen2.5-Coder-32B-Instruct.i1-IQ2_M.gguf b/Qwen2.5-Coder-32B-Instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..a2bca3b --- /dev/null +++ b/Qwen2.5-Coder-32B-Instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1d70023d8a1776ec3ef3082e9801fd87965906fd991b79edf7477f3573cb750 +size 11264441728 diff --git a/Qwen2.5-Coder-32B-Instruct.i1-IQ2_S.gguf b/Qwen2.5-Coder-32B-Instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..cb0050f --- /dev/null +++ b/Qwen2.5-Coder-32B-Instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dddd3f8728bd25a1407a90eca8c8e10bfc8062a7161c43b8fb23ca6c0e01d4d8 +size 10387570048 diff --git a/Qwen2.5-Coder-32B-Instruct.i1-IQ2_XS.gguf b/Qwen2.5-Coder-32B-Instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..87c4ff5 --- /dev/null +++ b/Qwen2.5-Coder-32B-Instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0e8878d09c19e9291337d7f567c36c8121e0ad94ee41b259c458769c8c02d84 +size 9957551488 diff --git a/Qwen2.5-Coder-32B-Instruct.i1-IQ2_XXS.gguf b/Qwen2.5-Coder-32B-Instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..f83f525 --- /dev/null +++ b/Qwen2.5-Coder-32B-Instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4d0103b5f7aa202b5b02122222af2619969425238e210263a683d5e7a36c9bc +size 9028251008 diff --git a/Qwen2.5-Coder-32B-Instruct.i1-IQ3_M.gguf b/Qwen2.5-Coder-32B-Instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..32f2a69 --- /dev/null +++ b/Qwen2.5-Coder-32B-Instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3936b5b3753b015936020d0396d9a4d957c8671bc22a998b86b42eb8dd77007e +size 14810123648 diff --git a/Qwen2.5-Coder-32B-Instruct.i1-IQ3_S.gguf b/Qwen2.5-Coder-32B-Instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..bf8207a --- /dev/null +++ b/Qwen2.5-Coder-32B-Instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fc6ca19ce1090dc679e313584159516c910959bd4b82e018e23633bd909453e +size 14436896128 diff --git a/Qwen2.5-Coder-32B-Instruct.i1-IQ3_XS.gguf b/Qwen2.5-Coder-32B-Instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..e63e381 --- /dev/null +++ b/Qwen2.5-Coder-32B-Instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc4c22ad22f8aa6a1ff2187330ea529c0a00804744cd3af4f009a2c8275c60ef +size 13705514368 diff --git a/Qwen2.5-Coder-32B-Instruct.i1-IQ3_XXS.gguf b/Qwen2.5-Coder-32B-Instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..6eaa3bc --- /dev/null +++ b/Qwen2.5-Coder-32B-Instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:916c37fb4de4b2420206074d32f9a4787972530be7387984a936add5e2ba8829 +size 12839271808 diff --git a/Qwen2.5-Coder-32B-Instruct.i1-IQ4_XS.gguf b/Qwen2.5-Coder-32B-Instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..e6e124c --- /dev/null +++ b/Qwen2.5-Coder-32B-Instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba5ca949c4890ae2646f3dac2f7afbe93774d42e9ea9b1cc539ef5853ce7f055 +size 17693154688 diff --git a/Qwen2.5-Coder-32B-Instruct.i1-Q2_K.gguf b/Qwen2.5-Coder-32B-Instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..44fd73a --- /dev/null +++ b/Qwen2.5-Coder-32B-Instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac46d170cc871849262025bb9c8c35b5d6c6063c03bb891aa4b0f203088f4aa8 +size 12313099648 diff --git a/Qwen2.5-Coder-32B-Instruct.i1-Q3_K_L.gguf b/Qwen2.5-Coder-32B-Instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..df13742 --- /dev/null +++ b/Qwen2.5-Coder-32B-Instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b356d1845cc75f86028d3705ac44a30b15e18e2448e081708c1c7d71f1cd25a5 +size 17247079808 diff --git a/Qwen2.5-Coder-32B-Instruct.i1-Q3_K_M.gguf b/Qwen2.5-Coder-32B-Instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..071d652 --- /dev/null +++ b/Qwen2.5-Coder-32B-Instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a9d8f15d8253313555772695663492964aa028d35e5fb1f1b2677c6810aba52 +size 15935049088 diff --git a/Qwen2.5-Coder-32B-Instruct.i1-Q3_K_S.gguf b/Qwen2.5-Coder-32B-Instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..2bc4c7f --- /dev/null +++ b/Qwen2.5-Coder-32B-Instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25efcf9ad76ba4fe26a7d040ab4c06e578b28db89bdb51eb45c56e36dee230d0 +size 14392331648 diff --git a/Qwen2.5-Coder-32B-Instruct.i1-Q4_0.gguf b/Qwen2.5-Coder-32B-Instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..9a24122 --- /dev/null +++ b/Qwen2.5-Coder-32B-Instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b73ded8373d273ad5e3d4ee793d1be31fbbade6a08f407c6b76ff00047d051d4 +size 18711010688 diff --git a/Qwen2.5-Coder-32B-Instruct.i1-Q4_K_M.gguf b/Qwen2.5-Coder-32B-Instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..a804ba1 --- /dev/null +++ b/Qwen2.5-Coder-32B-Instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9aae3499806ccc3a53673a239dcb2ae5a7cde38e125ba9ad9da8ccdeacb00b1 +size 19851337088 diff --git a/Qwen2.5-Coder-32B-Instruct.i1-Q4_K_S.gguf b/Qwen2.5-Coder-32B-Instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..80a6237 --- /dev/null +++ b/Qwen2.5-Coder-32B-Instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae26c311cd942b3759a9479bc365eaee258d6c3c87e8e4861a9ae9cb4a6f21cd +size 18784411008 diff --git a/Qwen2.5-Coder-32B-Instruct.i1-Q5_K_M.gguf b/Qwen2.5-Coder-32B-Instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..4cb67b4 --- /dev/null +++ b/Qwen2.5-Coder-32B-Instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c57322540fb2dc928103db8233c539998dfa9fdfc8af75e5e8259c736235432f +size 23262158208 diff --git a/Qwen2.5-Coder-32B-Instruct.i1-Q5_K_S.gguf b/Qwen2.5-Coder-32B-Instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..ab3bb5c --- /dev/null +++ b/Qwen2.5-Coder-32B-Instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f0ed7067f4f4b097068f1f5723873dc73f54c6c119baf527eb33b6d8acd8d5c +size 22638255488 diff --git a/Qwen2.5-Coder-32B-Instruct.i1-Q6_K.gguf b/Qwen2.5-Coder-32B-Instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..5ee3a6b --- /dev/null +++ b/Qwen2.5-Coder-32B-Instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28c062dbd683d19b2f9aef74921f8feacdf91a22ae98f84ad4327ac1683203b3 +size 26886155648 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e3ee431 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: Qwen/Qwen2.5-Coder-32B-Instruct +language: +- en +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct/blob/main/LICENSE +quantized_by: mradermacher +tags: +- code +- codeqwen +- chat +- qwen +- qwen-coder +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct + + +static quants are available at https://huggingface.co/mradermacher/Qwen2.5-Coder-32B-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-Coder-32B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Coder-32B-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 7.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-32B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Coder-32B-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-32B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Coder-32B-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-32B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Coder-32B-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-32B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Coder-32B-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 10.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-32B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Coder-32B-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 11.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-32B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Coder-32B-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-32B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Coder-32B-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-32B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Coder-32B-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-32B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Coder-32B-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-32B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Coder-32B-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 14.5 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-32B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Coder-32B-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-32B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Coder-32B-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-32B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Coder-32B-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-32B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Coder-32B-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-32B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Coder-32B-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 18.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-32B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Coder-32B-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-32B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Coder-32B-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-32B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Coder-32B-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-32B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Coder-32B-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-32B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Coder-32B-Instruct.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | 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..ec23a6a --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72b5df7a6a27092bad89553689e41d34a80fcd5ba05bc232bfa9278a50125fdd +size 14957085