commit 9eceb66e8683dadb32a7b69e32ec6dacd6751567 Author: ModelHub XC Date: Sun May 17 21:19:58 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/KviGPT-7b-Chat-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3d1b6ab --- /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 +KviGPT-7b-Chat.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KviGPT-7b-Chat.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +KviGPT-7b-Chat.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KviGPT-7b-Chat.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +KviGPT-7b-Chat.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KviGPT-7b-Chat.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KviGPT-7b-Chat.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +KviGPT-7b-Chat.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +KviGPT-7b-Chat.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +KviGPT-7b-Chat.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +KviGPT-7b-Chat.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KviGPT-7b-Chat.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +KviGPT-7b-Chat.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KviGPT-7b-Chat.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +KviGPT-7b-Chat.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KviGPT-7b-Chat.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +KviGPT-7b-Chat.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +KviGPT-7b-Chat.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +KviGPT-7b-Chat.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +KviGPT-7b-Chat.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KviGPT-7b-Chat.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +KviGPT-7b-Chat.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +KviGPT-7b-Chat.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +KviGPT-7b-Chat.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KviGPT-7b-Chat.i1-IQ1_M.gguf b/KviGPT-7b-Chat.i1-IQ1_M.gguf new file mode 100644 index 0000000..49c331f --- /dev/null +++ b/KviGPT-7b-Chat.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:969d5a9b00976962b2507a98f060fd92e3987de8f2e143ca04231bba26155c63 +size 791683840 diff --git a/KviGPT-7b-Chat.i1-IQ1_S.gguf b/KviGPT-7b-Chat.i1-IQ1_S.gguf new file mode 100644 index 0000000..e332172 --- /dev/null +++ b/KviGPT-7b-Chat.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e58c5c4b6f2dc37539aebfa1448d3e44bacbe6fc900edaa96ac863686472c53 +size 740369152 diff --git a/KviGPT-7b-Chat.i1-IQ2_M.gguf b/KviGPT-7b-Chat.i1-IQ2_M.gguf new file mode 100644 index 0000000..14b23d4 --- /dev/null +++ b/KviGPT-7b-Chat.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75db8295c6e8bb272bf8e5be9c9527ce309c50ab26cbaca9cea1d719abea9e63 +size 1099002112 diff --git a/KviGPT-7b-Chat.i1-IQ2_S.gguf b/KviGPT-7b-Chat.i1-IQ2_S.gguf new file mode 100644 index 0000000..d41c925 --- /dev/null +++ b/KviGPT-7b-Chat.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3b0bbd06f822b064597d01c9304be76b6084b145fa7ea7ee476823a372a657a +size 1030582528 diff --git a/KviGPT-7b-Chat.i1-IQ2_XS.gguf b/KviGPT-7b-Chat.i1-IQ2_XS.gguf new file mode 100644 index 0000000..d850997 --- /dev/null +++ b/KviGPT-7b-Chat.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:476e8662fc237619cc31b8e21a0388465c39bffb2f521862cb5d7dce87ba29d8 +size 952705792 diff --git a/KviGPT-7b-Chat.i1-IQ2_XXS.gguf b/KviGPT-7b-Chat.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..dc71fdf --- /dev/null +++ b/KviGPT-7b-Chat.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9f6c2857ebd225cfa906a9735de940f4750418aa062f36c99fae701060b3da1 +size 877208320 diff --git a/KviGPT-7b-Chat.i1-IQ3_M.gguf b/KviGPT-7b-Chat.i1-IQ3_M.gguf new file mode 100644 index 0000000..c2075a5 --- /dev/null +++ b/KviGPT-7b-Chat.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac5bd3937ebc68d3b162b762de0f60720cada845154c3421cbecd05fdbf52bc9 +size 1428739840 diff --git a/KviGPT-7b-Chat.i1-IQ3_S.gguf b/KviGPT-7b-Chat.i1-IQ3_S.gguf new file mode 100644 index 0000000..29ac3e9 --- /dev/null +++ b/KviGPT-7b-Chat.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58e97a0168acbd73bf23a671a35358006664b508098e57a03d38d3259813d4e8 +size 1358550784 diff --git a/KviGPT-7b-Chat.i1-IQ3_XS.gguf b/KviGPT-7b-Chat.i1-IQ3_XS.gguf new file mode 100644 index 0000000..48e58cb --- /dev/null +++ b/KviGPT-7b-Chat.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c51c1ad86bf9d3533396106cc2bf7df3f230d214ba6ac373ce8c3f218e5f7d0e +size 1294849792 diff --git a/KviGPT-7b-Chat.i1-IQ3_XXS.gguf b/KviGPT-7b-Chat.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..e71923b --- /dev/null +++ b/KviGPT-7b-Chat.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16b2e4b667d1d7fbf3d4162e22b36a2049504aa4f839c9c27fdcabc97dc28c57 +size 1193373952 diff --git a/KviGPT-7b-Chat.i1-IQ4_XS.gguf b/KviGPT-7b-Chat.i1-IQ4_XS.gguf new file mode 100644 index 0000000..1051585 --- /dev/null +++ b/KviGPT-7b-Chat.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f267b5cf9b65a9c8325fd5ba52fc4428c531a7ba8c58d12ec7047d205f0a9863 +size 1649943808 diff --git a/KviGPT-7b-Chat.i1-Q2_K.gguf b/KviGPT-7b-Chat.i1-Q2_K.gguf new file mode 100644 index 0000000..7392a01 --- /dev/null +++ b/KviGPT-7b-Chat.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f4ac0a57f3b92815954e841f82279e47797c2b9cb8b2e3696b8372592ea3ad9 +size 1174505728 diff --git a/KviGPT-7b-Chat.i1-Q3_K_L.gguf b/KviGPT-7b-Chat.i1-Q3_K_L.gguf new file mode 100644 index 0000000..15cc49f --- /dev/null +++ b/KviGPT-7b-Chat.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3be50586cc110c234f5dd3349cded1510357090233df99bd9218130a0d34f411 +size 1631049472 diff --git a/KviGPT-7b-Chat.i1-Q3_K_M.gguf b/KviGPT-7b-Chat.i1-Q3_K_M.gguf new file mode 100644 index 0000000..10a0b5f --- /dev/null +++ b/KviGPT-7b-Chat.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67ec98b9156cfbdef9a0c30442a5f2d78e00e7fa6255c79ee36695b896ac59d9 +size 1504433920 diff --git a/KviGPT-7b-Chat.i1-Q3_K_S.gguf b/KviGPT-7b-Chat.i1-Q3_K_S.gguf new file mode 100644 index 0000000..f3345fd --- /dev/null +++ b/KviGPT-7b-Chat.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc08099f34c6d77f1dbbae07f192b1161555a8fe93c2e461fc2ea63aa97ef4f0 +size 1358550784 diff --git a/KviGPT-7b-Chat.i1-Q4_0.gguf b/KviGPT-7b-Chat.i1-Q4_0.gguf new file mode 100644 index 0000000..7fd0f35 --- /dev/null +++ b/KviGPT-7b-Chat.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb143b25cc8630b4492153f0ffef34ccfd72cb2de6558c2ef82aeadc85e88748 +size 1744321792 diff --git a/KviGPT-7b-Chat.i1-Q4_0_4_4.gguf b/KviGPT-7b-Chat.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..5d1a10b --- /dev/null +++ b/KviGPT-7b-Chat.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da43b872ec37c3f02dfc3c412a7eef165afd8ddb52177fe381534924358b50f9 +size 1739603200 diff --git a/KviGPT-7b-Chat.i1-Q4_0_4_8.gguf b/KviGPT-7b-Chat.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..2748828 --- /dev/null +++ b/KviGPT-7b-Chat.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85d0a99d0d5994a371e1e71fd3e144fe8d897cc7c60ff6a5974786d1bb885672 +size 1739603200 diff --git a/KviGPT-7b-Chat.i1-Q4_0_8_8.gguf b/KviGPT-7b-Chat.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..bc1940e --- /dev/null +++ b/KviGPT-7b-Chat.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45fc490c447ea4c8e0b22bd1077e7df0aa6d176234f765d2159366e7a08fb776 +size 1739603200 diff --git a/KviGPT-7b-Chat.i1-Q4_K_M.gguf b/KviGPT-7b-Chat.i1-Q4_K_M.gguf new file mode 100644 index 0000000..a58ec83 --- /dev/null +++ b/KviGPT-7b-Chat.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:060b21d7557072d71f7fe07a1df995aafae6f1ef5608521412ee88becac27834 +size 1846656256 diff --git a/KviGPT-7b-Chat.i1-Q4_K_S.gguf b/KviGPT-7b-Chat.i1-Q4_K_S.gguf new file mode 100644 index 0000000..1422743 --- /dev/null +++ b/KviGPT-7b-Chat.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a73a447e74b2ebb90976ed0b0a80941e82320efa5a5250e05797043af549c33d +size 1753758976 diff --git a/KviGPT-7b-Chat.i1-Q5_K_M.gguf b/KviGPT-7b-Chat.i1-Q5_K_M.gguf new file mode 100644 index 0000000..9503f21 --- /dev/null +++ b/KviGPT-7b-Chat.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c40a3f5b75fa7976dad9861ae0bcb5a324c964737368fce5bd63e26577bbf2d +size 2153389312 diff --git a/KviGPT-7b-Chat.i1-Q5_K_S.gguf b/KviGPT-7b-Chat.i1-Q5_K_S.gguf new file mode 100644 index 0000000..886c935 --- /dev/null +++ b/KviGPT-7b-Chat.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06514fabca1d72b1d0cfad9094710f30249ac5cf210f11d02b123bbcf4e53183 +size 2098240768 diff --git a/KviGPT-7b-Chat.i1-Q6_K.gguf b/KviGPT-7b-Chat.i1-Q6_K.gguf new file mode 100644 index 0000000..1c65b28 --- /dev/null +++ b/KviGPT-7b-Chat.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10de1efd64b98748bd81a9c1a9f25c9c44db427436c3c21e072cad984cba459b +size 2479293184 diff --git a/README.md b/README.md new file mode 100644 index 0000000..00eee26 --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: kviai/KviGPT-7b-Chat +language: +- en +- ru +library_name: transformers +license: cc-by-sa-4.0 +quantized_by: mradermacher +tags: +- LLM +- Chat +- KVIGPT +- Llama +- Lora +- KVIAI +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/kviai/KviGPT-7b-Chat + + +static quants are available at https://huggingface.co/mradermacher/KviGPT-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/KviGPT-7b-Chat-i1-GGUF/resolve/main/KviGPT-7b-Chat.i1-IQ1_S.gguf) | i1-IQ1_S | 0.8 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/KviGPT-7b-Chat-i1-GGUF/resolve/main/KviGPT-7b-Chat.i1-IQ1_M.gguf) | i1-IQ1_M | 0.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/KviGPT-7b-Chat-i1-GGUF/resolve/main/KviGPT-7b-Chat.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/KviGPT-7b-Chat-i1-GGUF/resolve/main/KviGPT-7b-Chat.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/KviGPT-7b-Chat-i1-GGUF/resolve/main/KviGPT-7b-Chat.i1-IQ2_S.gguf) | i1-IQ2_S | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/KviGPT-7b-Chat-i1-GGUF/resolve/main/KviGPT-7b-Chat.i1-IQ2_M.gguf) | i1-IQ2_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/KviGPT-7b-Chat-i1-GGUF/resolve/main/KviGPT-7b-Chat.i1-Q2_K.gguf) | i1-Q2_K | 1.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/KviGPT-7b-Chat-i1-GGUF/resolve/main/KviGPT-7b-Chat.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KviGPT-7b-Chat-i1-GGUF/resolve/main/KviGPT-7b-Chat.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/KviGPT-7b-Chat-i1-GGUF/resolve/main/KviGPT-7b-Chat.i1-IQ3_S.gguf) | i1-IQ3_S | 1.5 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/KviGPT-7b-Chat-i1-GGUF/resolve/main/KviGPT-7b-Chat.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.5 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/KviGPT-7b-Chat-i1-GGUF/resolve/main/KviGPT-7b-Chat.i1-IQ3_M.gguf) | i1-IQ3_M | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/KviGPT-7b-Chat-i1-GGUF/resolve/main/KviGPT-7b-Chat.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.6 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/KviGPT-7b-Chat-i1-GGUF/resolve/main/KviGPT-7b-Chat.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/KviGPT-7b-Chat-i1-GGUF/resolve/main/KviGPT-7b-Chat.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/KviGPT-7b-Chat-i1-GGUF/resolve/main/KviGPT-7b-Chat.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 1.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/KviGPT-7b-Chat-i1-GGUF/resolve/main/KviGPT-7b-Chat.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 1.8 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/KviGPT-7b-Chat-i1-GGUF/resolve/main/KviGPT-7b-Chat.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 1.8 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/KviGPT-7b-Chat-i1-GGUF/resolve/main/KviGPT-7b-Chat.i1-Q4_0.gguf) | i1-Q4_0 | 1.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/KviGPT-7b-Chat-i1-GGUF/resolve/main/KviGPT-7b-Chat.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/KviGPT-7b-Chat-i1-GGUF/resolve/main/KviGPT-7b-Chat.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KviGPT-7b-Chat-i1-GGUF/resolve/main/KviGPT-7b-Chat.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/KviGPT-7b-Chat-i1-GGUF/resolve/main/KviGPT-7b-Chat.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/KviGPT-7b-Chat-i1-GGUF/resolve/main/KviGPT-7b-Chat.i1-Q6_K.gguf) | i1-Q6_K | 2.6 | 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..d4cf588 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7409fcd1ddf791419966eb48d335a68ffb9da3155e26ce3d092f821c8a86391 +size 2561461