commit 59ce6e324be11a2c41c680a23cdfa3c79f253c76 Author: ModelHub XC Date: Sat May 2 02:29:07 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen-7B-Chat-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4cfac95 --- /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 +Qwen-7B-Chat.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen-7B-Chat.i1-IQ1_M.gguf b/Qwen-7B-Chat.i1-IQ1_M.gguf new file mode 100644 index 0000000..99f4ac6 --- /dev/null +++ b/Qwen-7B-Chat.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1d8c378a44227348afe936fb7143faee80ad3e1d1a1a17d55147f18e9a4ac88 +size 2097960640 diff --git a/Qwen-7B-Chat.i1-IQ1_S.gguf b/Qwen-7B-Chat.i1-IQ1_S.gguf new file mode 100644 index 0000000..1c7dc69 --- /dev/null +++ b/Qwen-7B-Chat.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a383efd594df490df2292c4cabccbd8e6333fc975f5916c9f6d59d9a17045cd1 +size 1962989248 diff --git a/Qwen-7B-Chat.i1-IQ2_M.gguf b/Qwen-7B-Chat.i1-IQ2_M.gguf new file mode 100644 index 0000000..6ef3f44 --- /dev/null +++ b/Qwen-7B-Chat.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb7d18621db40dd158022b4e15af872e63ebb6f5f86bd2341424c6642e09122a +size 2856634048 diff --git a/Qwen-7B-Chat.i1-IQ2_S.gguf b/Qwen-7B-Chat.i1-IQ2_S.gguf new file mode 100644 index 0000000..959c349 --- /dev/null +++ b/Qwen-7B-Chat.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dac4604389b7083cdd1b2e5eca9432d3431f54f646b6718150370490042ed94e +size 2676672192 diff --git a/Qwen-7B-Chat.i1-IQ2_XS.gguf b/Qwen-7B-Chat.i1-IQ2_XS.gguf new file mode 100644 index 0000000..9efcd6b --- /dev/null +++ b/Qwen-7B-Chat.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe083d6b52250afa74a65db6838ad0dd240be99d947248e34e9d526bf12c8b1d +size 2519652032 diff --git a/Qwen-7B-Chat.i1-IQ2_XXS.gguf b/Qwen-7B-Chat.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..3cd80ad --- /dev/null +++ b/Qwen-7B-Chat.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1957e1bb5326116ee29adee5606f97ae7bf0af85cd8cb9eee80216cd1ab95243 +size 2322912960 diff --git a/Qwen-7B-Chat.i1-IQ3_M.gguf b/Qwen-7B-Chat.i1-IQ3_M.gguf new file mode 100644 index 0000000..148db41 --- /dev/null +++ b/Qwen-7B-Chat.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af6e1f2f43c847d97bea04adc13f5381346dc49dd69e67caa60de3edf50b7d19 +size 3878319808 diff --git a/Qwen-7B-Chat.i1-IQ3_S.gguf b/Qwen-7B-Chat.i1-IQ3_S.gguf new file mode 100644 index 0000000..1dc2d7d --- /dev/null +++ b/Qwen-7B-Chat.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4749d165bd0e8391e5eaaf89f8fc040b6f3701adc2018a7f09629a5e0eb68d76 +size 3569153728 diff --git a/Qwen-7B-Chat.i1-IQ3_XS.gguf b/Qwen-7B-Chat.i1-IQ3_XS.gguf new file mode 100644 index 0000000..94bd665 --- /dev/null +++ b/Qwen-7B-Chat.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d905c2817e4d9e7f8fc3baf848f27fe1aa202dd8f9707f71190ce972555a372c +size 3467704000 diff --git a/Qwen-7B-Chat.i1-IQ3_XXS.gguf b/Qwen-7B-Chat.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..dd6b050 --- /dev/null +++ b/Qwen-7B-Chat.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb0f7a0fc9b65ea78daa44e2d4468ce1d84169713af4fa11e92a29b193fd6281 +size 3208103616 diff --git a/Qwen-7B-Chat.i1-IQ4_NL.gguf b/Qwen-7B-Chat.i1-IQ4_NL.gguf new file mode 100644 index 0000000..6c587f0 --- /dev/null +++ b/Qwen-7B-Chat.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82e7f9c1dfee394d46ca37bad69101387a595f15bfe72780b793578068412ca1 +size 4511901376 diff --git a/Qwen-7B-Chat.i1-IQ4_XS.gguf b/Qwen-7B-Chat.i1-IQ4_XS.gguf new file mode 100644 index 0000000..61d0c4d --- /dev/null +++ b/Qwen-7B-Chat.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ce20f87283297c2c28682e93199e1a0cfac7cf083bfac34cc21ad806b0c76b3 +size 4290078400 diff --git a/Qwen-7B-Chat.i1-Q2_K.gguf b/Qwen-7B-Chat.i1-Q2_K.gguf new file mode 100644 index 0000000..a492d40 --- /dev/null +++ b/Qwen-7B-Chat.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:669df23388af199e55b752d1349c5070894a832bfdb39c6a838145546bb9a112 +size 3049293504 diff --git a/Qwen-7B-Chat.i1-Q2_K_S.gguf b/Qwen-7B-Chat.i1-Q2_K_S.gguf new file mode 100644 index 0000000..60fd573 --- /dev/null +++ b/Qwen-7B-Chat.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:254ed664afb040b98571b0bfe861213dfeae3ef3307f2dfafac5dcc302fab23d +size 2890499776 diff --git a/Qwen-7B-Chat.i1-Q3_K_L.gguf b/Qwen-7B-Chat.i1-Q3_K_L.gguf new file mode 100644 index 0000000..1d59b70 --- /dev/null +++ b/Qwen-7B-Chat.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaedea923abf06dc0d6f70d76e8e172a10fadd2cb0d6ba18ad18fa7513703f2b +size 4293457600 diff --git a/Qwen-7B-Chat.i1-Q3_K_M.gguf b/Qwen-7B-Chat.i1-Q3_K_M.gguf new file mode 100644 index 0000000..a061c5a --- /dev/null +++ b/Qwen-7B-Chat.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e46f93f264d3c58ef687b5c2b5bff45dd1161f53622c3965d99afb02ffb4663 +size 4057265856 diff --git a/Qwen-7B-Chat.i1-Q3_K_S.gguf b/Qwen-7B-Chat.i1-Q3_K_S.gguf new file mode 100644 index 0000000..7d53692 --- /dev/null +++ b/Qwen-7B-Chat.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec343e4cb88899deb63593a8117fcf9fb61ad4d4f82e7d68a3b5441232d88b73 +size 3569153728 diff --git a/Qwen-7B-Chat.i1-Q4_0.gguf b/Qwen-7B-Chat.i1-Q4_0.gguf new file mode 100644 index 0000000..9ab5f61 --- /dev/null +++ b/Qwen-7B-Chat.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e46c194568904558f86817f896f459f026b37ff0c4eeaaa1e93ed8ba384114f +size 4523173568 diff --git a/Qwen-7B-Chat.i1-Q4_1.gguf b/Qwen-7B-Chat.i1-Q4_1.gguf new file mode 100644 index 0000000..1b8ebb5 --- /dev/null +++ b/Qwen-7B-Chat.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eacaa9dca8f71c58e2f5a974cd9e1048d576b4d78d0c31802fa23ed38b19822 +size 4955547328 diff --git a/Qwen-7B-Chat.i1-Q4_K_M.gguf b/Qwen-7B-Chat.i1-Q4_K_M.gguf new file mode 100644 index 0000000..db36d46 --- /dev/null +++ b/Qwen-7B-Chat.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c78ea480785d348078ece81a0c1c63c1e6d370b04816a8c9f4073688ff36cc95 +size 4899219136 diff --git a/Qwen-7B-Chat.i1-Q4_K_S.gguf b/Qwen-7B-Chat.i1-Q4_K_S.gguf new file mode 100644 index 0000000..6c53db9 --- /dev/null +++ b/Qwen-7B-Chat.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffdd53ee47f68918197bd6f71bdc2d9b0f844b883c025712eadfa217859ebf0a +size 4534445760 diff --git a/Qwen-7B-Chat.i1-Q5_K_M.gguf b/Qwen-7B-Chat.i1-Q5_K_M.gguf new file mode 100644 index 0000000..f5bca61 --- /dev/null +++ b/Qwen-7B-Chat.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43f6ed59b60c53942ce948ced5c0eda54ea45047fb6bc3740dad72bd3d2bcb05 +size 5708916416 diff --git a/Qwen-7B-Chat.i1-Q5_K_S.gguf b/Qwen-7B-Chat.i1-Q5_K_S.gguf new file mode 100644 index 0000000..803d8b5 --- /dev/null +++ b/Qwen-7B-Chat.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d08e32b72d5e47af25b54954f80d41c3c7495a5903844a0cb69cef698a46fcd +size 5399193280 diff --git a/Qwen-7B-Chat.i1-Q6_K.gguf b/Qwen-7B-Chat.i1-Q6_K.gguf new file mode 100644 index 0000000..f731ad3 --- /dev/null +++ b/Qwen-7B-Chat.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d0dacb8e409212b1f335f6ffa781058e14a8480dcd5467b9ea443992127eb86 +size 6341940928 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c1ce84c --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: Qwen/Qwen-7B-Chat +language: +- zh +- en +library_name: transformers +license: other +license_link: https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT +license_name: tongyi-qianwen-license-agreement +quantized_by: mradermacher +tags: +- qwen +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Qwen/Qwen-7B-Chat + + +static quants are available at https://huggingface.co/mradermacher/Qwen-7B-Chat-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/Qwen-7B-Chat-i1-GGUF/resolve/main/Qwen-7B-Chat.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-i1-GGUF/resolve/main/Qwen-7B-Chat.i1-IQ1_M.gguf) | i1-IQ1_M | 2.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-i1-GGUF/resolve/main/Qwen-7B-Chat.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-i1-GGUF/resolve/main/Qwen-7B-Chat.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-i1-GGUF/resolve/main/Qwen-7B-Chat.i1-IQ2_S.gguf) | i1-IQ2_S | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-i1-GGUF/resolve/main/Qwen-7B-Chat.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-i1-GGUF/resolve/main/Qwen-7B-Chat.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.0 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-i1-GGUF/resolve/main/Qwen-7B-Chat.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-i1-GGUF/resolve/main/Qwen-7B-Chat.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-i1-GGUF/resolve/main/Qwen-7B-Chat.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-i1-GGUF/resolve/main/Qwen-7B-Chat.i1-IQ3_S.gguf) | i1-IQ3_S | 3.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-i1-GGUF/resolve/main/Qwen-7B-Chat.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.7 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-i1-GGUF/resolve/main/Qwen-7B-Chat.i1-IQ3_M.gguf) | i1-IQ3_M | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-i1-GGUF/resolve/main/Qwen-7B-Chat.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-i1-GGUF/resolve/main/Qwen-7B-Chat.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-i1-GGUF/resolve/main/Qwen-7B-Chat.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-i1-GGUF/resolve/main/Qwen-7B-Chat.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.6 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-i1-GGUF/resolve/main/Qwen-7B-Chat.i1-Q4_0.gguf) | i1-Q4_0 | 4.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-i1-GGUF/resolve/main/Qwen-7B-Chat.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-i1-GGUF/resolve/main/Qwen-7B-Chat.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-i1-GGUF/resolve/main/Qwen-7B-Chat.i1-Q4_1.gguf) | i1-Q4_1 | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-i1-GGUF/resolve/main/Qwen-7B-Chat.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-i1-GGUF/resolve/main/Qwen-7B-Chat.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-i1-GGUF/resolve/main/Qwen-7B-Chat.i1-Q6_K.gguf) | i1-Q6_K | 6.4 | 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..713b3d6 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a59399ea5214fe474f30a8aa1fc1a398b459da8b5048c97d20f65ffb921c8713 +size 3511633