commit de3872b8084ea60644de501d0478fd3db5807da7 Author: ModelHub XC Date: Thu May 14 00:57:26 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/KavithaSaaram-9b-it-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1a5719c --- /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 +KavithaSaaram-9b-it.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KavithaSaaram-9b-it.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +KavithaSaaram-9b-it.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KavithaSaaram-9b-it.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +KavithaSaaram-9b-it.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KavithaSaaram-9b-it.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +KavithaSaaram-9b-it.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KavithaSaaram-9b-it.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +KavithaSaaram-9b-it.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +KavithaSaaram-9b-it.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +KavithaSaaram-9b-it.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KavithaSaaram-9b-it.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +KavithaSaaram-9b-it.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KavithaSaaram-9b-it.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +KavithaSaaram-9b-it.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KavithaSaaram-9b-it.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +KavithaSaaram-9b-it.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KavithaSaaram-9b-it.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +KavithaSaaram-9b-it.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +KavithaSaaram-9b-it.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +KavithaSaaram-9b-it.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KavithaSaaram-9b-it.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +KavithaSaaram-9b-it.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +KavithaSaaram-9b-it.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KavithaSaaram-9b-it.i1-IQ1_M.gguf b/KavithaSaaram-9b-it.i1-IQ1_M.gguf new file mode 100644 index 0000000..8de1db7 --- /dev/null +++ b/KavithaSaaram-9b-it.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65388bd4303d9952a075443db117aaf508f50102fa2cc653c750055399d15b4e +size 2545952960 diff --git a/KavithaSaaram-9b-it.i1-IQ1_S.gguf b/KavithaSaaram-9b-it.i1-IQ1_S.gguf new file mode 100644 index 0000000..3c3bf55 --- /dev/null +++ b/KavithaSaaram-9b-it.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c8cf74cdfc09232a6a6b6a5d6a034b2e017b3e9ef3ed7627d43248a14c200e6 +size 2378565824 diff --git a/KavithaSaaram-9b-it.i1-IQ2_M.gguf b/KavithaSaaram-9b-it.i1-IQ2_M.gguf new file mode 100644 index 0000000..f535350 --- /dev/null +++ b/KavithaSaaram-9b-it.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1922ad7f965a7fe805a4e5239361a20ee1293eafc594b5fbf7544aa2bfc532d3 +size 3434670272 diff --git a/KavithaSaaram-9b-it.i1-IQ2_S.gguf b/KavithaSaaram-9b-it.i1-IQ2_S.gguf new file mode 100644 index 0000000..457993e --- /dev/null +++ b/KavithaSaaram-9b-it.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed547844ee02b6aedd509045157c983611c7d5c3c27f12555558004bddacdcd1 +size 3211487424 diff --git a/KavithaSaaram-9b-it.i1-IQ2_XS.gguf b/KavithaSaaram-9b-it.i1-IQ2_XS.gguf new file mode 100644 index 0000000..67ab6a5 --- /dev/null +++ b/KavithaSaaram-9b-it.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36bedb840e3039466ba9e3f5f3656db0bd93dc09bec381815b384da84a404c8d +size 3067381952 diff --git a/KavithaSaaram-9b-it.i1-IQ2_XXS.gguf b/KavithaSaaram-9b-it.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..5bb15f6 --- /dev/null +++ b/KavithaSaaram-9b-it.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f9927c0760eafce2d8d10b8827309ad382f4dc64c951b68030492f4e87d3c33 +size 2824931520 diff --git a/KavithaSaaram-9b-it.i1-IQ3_M.gguf b/KavithaSaaram-9b-it.i1-IQ3_M.gguf new file mode 100644 index 0000000..e9ec526 --- /dev/null +++ b/KavithaSaaram-9b-it.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9acc48f4721537a9b975d6820aab50ead707b66be22b89ec633069915d901f4e +size 4494616768 diff --git a/KavithaSaaram-9b-it.i1-IQ3_S.gguf b/KavithaSaaram-9b-it.i1-IQ3_S.gguf new file mode 100644 index 0000000..b133cc4 --- /dev/null +++ b/KavithaSaaram-9b-it.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:023c79f6b9b1d606681cc0be145ed54e14be5854e2e8625faef392d7ce015050 +size 4337666240 diff --git a/KavithaSaaram-9b-it.i1-IQ3_XS.gguf b/KavithaSaaram-9b-it.i1-IQ3_XS.gguf new file mode 100644 index 0000000..89e3f16 --- /dev/null +++ b/KavithaSaaram-9b-it.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:282ad84d56322a4a863fb37f896991e28c3c7e96623e52e28e9c8a8815baa4cc +size 4144990400 diff --git a/KavithaSaaram-9b-it.i1-IQ3_XXS.gguf b/KavithaSaaram-9b-it.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..f90830b --- /dev/null +++ b/KavithaSaaram-9b-it.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfe2a324b3f761e653ea61fe681c84fc675a4a71c89514673412688f0db63d52 +size 3796740288 diff --git a/KavithaSaaram-9b-it.i1-IQ4_NL.gguf b/KavithaSaaram-9b-it.i1-IQ4_NL.gguf new file mode 100644 index 0000000..bbf2624 --- /dev/null +++ b/KavithaSaaram-9b-it.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6e6157328410f22f0669d0ab20fd65fd490defcd9b6cb799b1bb9832e28c9c2 +size 5443143872 diff --git a/KavithaSaaram-9b-it.i1-IQ4_XS.gguf b/KavithaSaaram-9b-it.i1-IQ4_XS.gguf new file mode 100644 index 0000000..aa4731b --- /dev/null +++ b/KavithaSaaram-9b-it.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e644a328afe2e0fd054a5107d7de8a8abaaee400a5413f50809b3ac0197bd683 +size 5183031488 diff --git a/KavithaSaaram-9b-it.i1-Q2_K.gguf b/KavithaSaaram-9b-it.i1-Q2_K.gguf new file mode 100644 index 0000000..8f83319 --- /dev/null +++ b/KavithaSaaram-9b-it.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e67b09b1462b3d040e23e5a4a2e2337bcb134f6fddcefae56712251e09f53e0 +size 3805399232 diff --git a/KavithaSaaram-9b-it.i1-Q2_K_S.gguf b/KavithaSaaram-9b-it.i1-Q2_K_S.gguf new file mode 100644 index 0000000..5747c6d --- /dev/null +++ b/KavithaSaaram-9b-it.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e902b59f38e73bb4d0b03415a6c7adaf3da0f1a02cdd6334c8d2446ddd2330a1 +size 3552512192 diff --git a/KavithaSaaram-9b-it.i1-Q3_K_L.gguf b/KavithaSaaram-9b-it.i1-Q3_K_L.gguf new file mode 100644 index 0000000..8bae417 --- /dev/null +++ b/KavithaSaaram-9b-it.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae7e560c75aaf420bce95468175f9e26a1ad81bc22e94153535d9d0468ed14ad +size 5132454080 diff --git a/KavithaSaaram-9b-it.i1-Q3_K_M.gguf b/KavithaSaaram-9b-it.i1-Q3_K_M.gguf new file mode 100644 index 0000000..f8ebf52 --- /dev/null +++ b/KavithaSaaram-9b-it.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a17654799714f424607856307973d0eed4cbe5602bb3b084230d20250c9fb480 +size 4761782464 diff --git a/KavithaSaaram-9b-it.i1-Q3_K_S.gguf b/KavithaSaaram-9b-it.i1-Q3_K_S.gguf new file mode 100644 index 0000000..3aa7fb8 --- /dev/null +++ b/KavithaSaaram-9b-it.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71a17f86ae062f640f36937b56b4331032def6e7f8cf6a6413f0abc8fbcc1b61 +size 4337666240 diff --git a/KavithaSaaram-9b-it.i1-Q4_0.gguf b/KavithaSaaram-9b-it.i1-Q4_0.gguf new file mode 100644 index 0000000..3185432 --- /dev/null +++ b/KavithaSaaram-9b-it.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:306516991271754ce760ebf1edfa5f0f1961ae1f986f60fd1ff0d9ea8d50ddf7 +size 5459200192 diff --git a/KavithaSaaram-9b-it.i1-Q4_1.gguf b/KavithaSaaram-9b-it.i1-Q4_1.gguf new file mode 100644 index 0000000..8072c31 --- /dev/null +++ b/KavithaSaaram-9b-it.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6bcda48bb3478cce83a982e2bd3fba611aab32098df46b435028f3109aa7fed +size 5963368640 diff --git a/KavithaSaaram-9b-it.i1-Q4_K_M.gguf b/KavithaSaaram-9b-it.i1-Q4_K_M.gguf new file mode 100644 index 0000000..b47ab26 --- /dev/null +++ b/KavithaSaaram-9b-it.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c22ab0368574b5a68339d23795671edcd664aadb9b8ed99b2b2554c088276db8 +size 5761059008 diff --git a/KavithaSaaram-9b-it.i1-Q4_K_S.gguf b/KavithaSaaram-9b-it.i1-Q4_K_S.gguf new file mode 100644 index 0000000..778a2be --- /dev/null +++ b/KavithaSaaram-9b-it.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a91434cde3f767d2a7ac36cfad72ef16bd404f228d2429f2558a5fd9e08e0e82 +size 5478926528 diff --git a/KavithaSaaram-9b-it.i1-Q5_K_M.gguf b/KavithaSaaram-9b-it.i1-Q5_K_M.gguf new file mode 100644 index 0000000..a27df05 --- /dev/null +++ b/KavithaSaaram-9b-it.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4b970ae3f360bc1864f72942e951d0d3384cb8468968279cb6b24e40cc4c0e6 +size 6647367872 diff --git a/KavithaSaaram-9b-it.i1-Q5_K_S.gguf b/KavithaSaaram-9b-it.i1-Q5_K_S.gguf new file mode 100644 index 0000000..8934b83 --- /dev/null +++ b/KavithaSaaram-9b-it.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a611311297ee1837ed165109f725afbb117a5d78b0009b1e8c06a7cdfea7956d +size 6483593408 diff --git a/KavithaSaaram-9b-it.i1-Q6_K.gguf b/KavithaSaaram-9b-it.i1-Q6_K.gguf new file mode 100644 index 0000000..4617642 --- /dev/null +++ b/KavithaSaaram-9b-it.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:305f9db9752c7831e3ca8a5595646ba055dd163a3e5469cd3e3a69ee25185ded +size 7589071040 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6d1f9e4 --- /dev/null +++ b/README.md @@ -0,0 +1,89 @@ +--- +base_model: akdiwahar/KavithaSaaram-9b-it +datasets: +- akdiwahar/PaaPeyarchi +language: +- ta +library_name: transformers +license: gemma +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- tamil +- intralingual +- Thamizh +- Translation +- tamil poetry +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/akdiwahar/KavithaSaaram-9b-it + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#KavithaSaaram-9b-it-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/KavithaSaaram-9b-it-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/KavithaSaaram-9b-it-i1-GGUF/resolve/main/KavithaSaaram-9b-it.i1-IQ1_S.gguf) | i1-IQ1_S | 2.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/KavithaSaaram-9b-it-i1-GGUF/resolve/main/KavithaSaaram-9b-it.i1-IQ1_M.gguf) | i1-IQ1_M | 2.6 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/KavithaSaaram-9b-it-i1-GGUF/resolve/main/KavithaSaaram-9b-it.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/KavithaSaaram-9b-it-i1-GGUF/resolve/main/KavithaSaaram-9b-it.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/KavithaSaaram-9b-it-i1-GGUF/resolve/main/KavithaSaaram-9b-it.i1-IQ2_S.gguf) | i1-IQ2_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/KavithaSaaram-9b-it-i1-GGUF/resolve/main/KavithaSaaram-9b-it.i1-IQ2_M.gguf) | i1-IQ2_M | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/KavithaSaaram-9b-it-i1-GGUF/resolve/main/KavithaSaaram-9b-it.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/KavithaSaaram-9b-it-i1-GGUF/resolve/main/KavithaSaaram-9b-it.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KavithaSaaram-9b-it-i1-GGUF/resolve/main/KavithaSaaram-9b-it.i1-Q2_K.gguf) | i1-Q2_K | 3.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/KavithaSaaram-9b-it-i1-GGUF/resolve/main/KavithaSaaram-9b-it.i1-IQ3_XS.gguf) | i1-IQ3_XS | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/KavithaSaaram-9b-it-i1-GGUF/resolve/main/KavithaSaaram-9b-it.i1-IQ3_S.gguf) | i1-IQ3_S | 4.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/KavithaSaaram-9b-it-i1-GGUF/resolve/main/KavithaSaaram-9b-it.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/KavithaSaaram-9b-it-i1-GGUF/resolve/main/KavithaSaaram-9b-it.i1-IQ3_M.gguf) | i1-IQ3_M | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/KavithaSaaram-9b-it-i1-GGUF/resolve/main/KavithaSaaram-9b-it.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/KavithaSaaram-9b-it-i1-GGUF/resolve/main/KavithaSaaram-9b-it.i1-Q3_K_L.gguf) | i1-Q3_K_L | 5.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/KavithaSaaram-9b-it-i1-GGUF/resolve/main/KavithaSaaram-9b-it.i1-IQ4_XS.gguf) | i1-IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/KavithaSaaram-9b-it-i1-GGUF/resolve/main/KavithaSaaram-9b-it.i1-IQ4_NL.gguf) | i1-IQ4_NL | 5.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/KavithaSaaram-9b-it-i1-GGUF/resolve/main/KavithaSaaram-9b-it.i1-Q4_0.gguf) | i1-Q4_0 | 5.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/KavithaSaaram-9b-it-i1-GGUF/resolve/main/KavithaSaaram-9b-it.i1-Q4_K_S.gguf) | i1-Q4_K_S | 5.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/KavithaSaaram-9b-it-i1-GGUF/resolve/main/KavithaSaaram-9b-it.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KavithaSaaram-9b-it-i1-GGUF/resolve/main/KavithaSaaram-9b-it.i1-Q4_1.gguf) | i1-Q4_1 | 6.1 | | +| [GGUF](https://huggingface.co/mradermacher/KavithaSaaram-9b-it-i1-GGUF/resolve/main/KavithaSaaram-9b-it.i1-Q5_K_S.gguf) | i1-Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/KavithaSaaram-9b-it-i1-GGUF/resolve/main/KavithaSaaram-9b-it.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/KavithaSaaram-9b-it-i1-GGUF/resolve/main/KavithaSaaram-9b-it.i1-Q6_K.gguf) | i1-Q6_K | 7.7 | 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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..c7a88f2 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f3fd356c39ea5136a5907c3dff1434eac8ed51d224610d6ad6dcec2adeae10e +size 6116887