commit 58c7c7849a878d7ec15c272d02a59ae2566afabb Author: ModelHub XC Date: Wed May 20 03:23:48 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Clara-24B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..997e150 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.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 +Clara-24B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Clara-24B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Clara-24B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Clara-24B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Clara-24B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Clara-24B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Clara-24B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Clara-24B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Clara-24B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Clara-24B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Clara-24B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Clara-24B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Clara-24B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Clara-24B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Clara-24B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Clara-24B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Clara-24B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Clara-24B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Clara-24B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Clara-24B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Clara-24B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Clara-24B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Clara-24B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Clara-24B.i1-IQ1_M.gguf b/Clara-24B.i1-IQ1_M.gguf new file mode 100644 index 0000000..f0804ca --- /dev/null +++ b/Clara-24B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efeea12adabcbdf42c90ddd9f62409a81c88122b932cd1a8189f6f90719fbfc0 +size 5750497088 diff --git a/Clara-24B.i1-IQ1_S.gguf b/Clara-24B.i1-IQ1_S.gguf new file mode 100644 index 0000000..969f77a --- /dev/null +++ b/Clara-24B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce11f4e48bf2fea31bf7498a62a64c1d768ed31544a9d338afcb1e024c002544 +size 5273722688 diff --git a/Clara-24B.i1-IQ2_M.gguf b/Clara-24B.i1-IQ2_M.gguf new file mode 100644 index 0000000..5ef93d1 --- /dev/null +++ b/Clara-24B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe7809d38761cc8560bfeda49aca404daca4bdc29638c480cb0b09c4e78124df +size 8114052928 diff --git a/Clara-24B.i1-IQ2_S.gguf b/Clara-24B.i1-IQ2_S.gguf new file mode 100644 index 0000000..816225d --- /dev/null +++ b/Clara-24B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b50f3112541a952261a04038c2b82334276514383056d30d11928c619b79ea69 +size 7478353728 diff --git a/Clara-24B.i1-IQ2_XS.gguf b/Clara-24B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..17cc779 --- /dev/null +++ b/Clara-24B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a7ec21d64df4228c013d285b22983385d3bf99b5f3de53d32c4d1c998642bb2 +size 7207034688 diff --git a/Clara-24B.i1-IQ2_XXS.gguf b/Clara-24B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..76c532a --- /dev/null +++ b/Clara-24B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4849dc93a7cc91237e1851c1be167e4ef029dd3717fa40ec3bd212240b6200fd +size 6545121088 diff --git a/Clara-24B.i1-IQ3_M.gguf b/Clara-24B.i1-IQ3_M.gguf new file mode 100644 index 0000000..4863dd2 --- /dev/null +++ b/Clara-24B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20b9ed95426e0db5336de587af98940e52ba1c3991d801605f7bd0602d5a1fca +size 10650951488 diff --git a/Clara-24B.i1-IQ3_S.gguf b/Clara-24B.i1-IQ3_S.gguf new file mode 100644 index 0000000..aab46f1 --- /dev/null +++ b/Clara-24B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03d16fe3c27b8c7e1327f06bd237ebcf63117c4b2f80c2e1e0e377b63969e797 +size 10428129088 diff --git a/Clara-24B.i1-IQ3_XS.gguf b/Clara-24B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..02f7580 --- /dev/null +++ b/Clara-24B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46e00a6d04d7f70f057a6abcb4b369158ed4b8926c869fec00b6062a013361a7 +size 9907117888 diff --git a/Clara-24B.i1-IQ3_XXS.gguf b/Clara-24B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..dc5f914 --- /dev/null +++ b/Clara-24B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a246a52cd3f5ae2fa190ed0281e5d353d7bce41ea4fb80a256ccb0b6c97a0b3c +size 9280593728 diff --git a/Clara-24B.i1-IQ4_XS.gguf b/Clara-24B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..84a14e0 --- /dev/null +++ b/Clara-24B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c58a9b6ab05398235b3346fe8986fd01c5ca904a615472fcbf191ed805b0df3e +size 12758916928 diff --git a/Clara-24B.i1-Q2_K.gguf b/Clara-24B.i1-Q2_K.gguf new file mode 100644 index 0000000..be43ad5 --- /dev/null +++ b/Clara-24B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:935c13b9060ed38471c4a1537d0ad95baaacc8be89a625f717fbea5e84128e47 +size 8890326848 diff --git a/Clara-24B.i1-Q2_K_S.gguf b/Clara-24B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..bb3d050 --- /dev/null +++ b/Clara-24B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bd898bdcf7a058d2468443bab72d2f82e4ab97797012de7f68c47c9ccb2909d +size 8320163648 diff --git a/Clara-24B.i1-Q3_K_L.gguf b/Clara-24B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..41dff49 --- /dev/null +++ b/Clara-24B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d13a9f7eea63cea5ee48b395c91d27ca83e51dc30a6886146165cf49695536e +size 12400762688 diff --git a/Clara-24B.i1-Q3_K_M.gguf b/Clara-24B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..43ab015 --- /dev/null +++ b/Clara-24B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:babcad00e4893f3e4cd7d327aca1455aeac3a4d8ae571dcdfaf3f7ac6762d4ee +size 11474083648 diff --git a/Clara-24B.i1-Q3_K_S.gguf b/Clara-24B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..72875db --- /dev/null +++ b/Clara-24B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22c67e178b3c0dfb828760ec1b1b7bd70e899e18ff4b7972a3c839ae40239c4f +size 10400276288 diff --git a/Clara-24B.i1-Q4_0.gguf b/Clara-24B.i1-Q4_0.gguf new file mode 100644 index 0000000..f40a109 --- /dev/null +++ b/Clara-24B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:139ad14f77862dccd639f3238d669d754283dff50c5002408a6f845f95d76784 +size 13494230848 diff --git a/Clara-24B.i1-Q4_1.gguf b/Clara-24B.i1-Q4_1.gguf new file mode 100644 index 0000000..7d12ca7 --- /dev/null +++ b/Clara-24B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bb96faa50a5812e067241d105af4975aa0d244a651e7578e9302795bc7f4f4c +size 14873108288 diff --git a/Clara-24B.i1-Q4_K_M.gguf b/Clara-24B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..f49cdf7 --- /dev/null +++ b/Clara-24B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb660319f803223a64785d7a395c3ae567cfd67c9665874bad668bd8e3d517be +size 14333910848 diff --git a/Clara-24B.i1-Q4_K_S.gguf b/Clara-24B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..58811cd --- /dev/null +++ b/Clara-24B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1785c3f126c7959769a124c43d909a4aef07c843f33ff5b68c2d4f93ad365f4a +size 13549281088 diff --git a/Clara-24B.i1-Q5_K_M.gguf b/Clara-24B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..a2d9961 --- /dev/null +++ b/Clara-24B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e232b5a042598528345d8fa43bed1ce7dec86bc048d8fbcb681b7b0232104ca +size 16763985728 diff --git a/Clara-24B.i1-Q5_K_S.gguf b/Clara-24B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..efa4c87 --- /dev/null +++ b/Clara-24B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58e5a430534f9d5151377ac07c122b835008dcea0be0fc224709aec0a492943d +size 16304414528 diff --git a/Clara-24B.i1-Q6_K.gguf b/Clara-24B.i1-Q6_K.gguf new file mode 100644 index 0000000..a1554bb --- /dev/null +++ b/Clara-24B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f7fa2c7f9d83bd0a0f5a4387169f845534726d45a7ed31abc2a5eb603ac5363 +size 19345940288 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8ade5a3 --- /dev/null +++ b/README.md @@ -0,0 +1,91 @@ +--- +base_model: ayan4m1/Clara-24B +datasets: +- mlfoundations-dev/oh-dcft-v3.1-claude-3-5-sonnet-20241022 +- Gryphe/Sonnet3.5-SlimOrcaDedupCleaned +- nothingiisreal/Claude-3-Opus-Instruct-15K +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- mistral3 +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/ayan4m1/Clara-24B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Clara-24B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Clara-24B-GGUF + +**This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/Clara-24B-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/Clara-24B-i1-GGUF/resolve/main/Clara-24B.i1-IQ1_S.gguf) | i1-IQ1_S | 5.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Clara-24B-i1-GGUF/resolve/main/Clara-24B.i1-IQ1_M.gguf) | i1-IQ1_M | 5.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Clara-24B-i1-GGUF/resolve/main/Clara-24B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/Clara-24B-i1-GGUF/resolve/main/Clara-24B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 7.3 | | +| [GGUF](https://huggingface.co/mradermacher/Clara-24B-i1-GGUF/resolve/main/Clara-24B.i1-IQ2_S.gguf) | i1-IQ2_S | 7.6 | | +| [GGUF](https://huggingface.co/mradermacher/Clara-24B-i1-GGUF/resolve/main/Clara-24B.i1-IQ2_M.gguf) | i1-IQ2_M | 8.2 | | +| [GGUF](https://huggingface.co/mradermacher/Clara-24B-i1-GGUF/resolve/main/Clara-24B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 8.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Clara-24B-i1-GGUF/resolve/main/Clara-24B.i1-Q2_K.gguf) | i1-Q2_K | 9.0 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Clara-24B-i1-GGUF/resolve/main/Clara-24B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 9.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Clara-24B-i1-GGUF/resolve/main/Clara-24B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 10.0 | | +| [GGUF](https://huggingface.co/mradermacher/Clara-24B-i1-GGUF/resolve/main/Clara-24B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 10.5 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Clara-24B-i1-GGUF/resolve/main/Clara-24B.i1-IQ3_S.gguf) | i1-IQ3_S | 10.5 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Clara-24B-i1-GGUF/resolve/main/Clara-24B.i1-IQ3_M.gguf) | i1-IQ3_M | 10.8 | | +| [GGUF](https://huggingface.co/mradermacher/Clara-24B-i1-GGUF/resolve/main/Clara-24B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 11.6 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Clara-24B-i1-GGUF/resolve/main/Clara-24B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 12.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Clara-24B-i1-GGUF/resolve/main/Clara-24B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.9 | | +| [GGUF](https://huggingface.co/mradermacher/Clara-24B-i1-GGUF/resolve/main/Clara-24B.i1-Q4_0.gguf) | i1-Q4_0 | 13.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Clara-24B-i1-GGUF/resolve/main/Clara-24B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 13.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Clara-24B-i1-GGUF/resolve/main/Clara-24B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 14.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Clara-24B-i1-GGUF/resolve/main/Clara-24B.i1-Q4_1.gguf) | i1-Q4_1 | 15.0 | | +| [GGUF](https://huggingface.co/mradermacher/Clara-24B-i1-GGUF/resolve/main/Clara-24B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 16.4 | | +| [GGUF](https://huggingface.co/mradermacher/Clara-24B-i1-GGUF/resolve/main/Clara-24B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 16.9 | | +| [GGUF](https://huggingface.co/mradermacher/Clara-24B-i1-GGUF/resolve/main/Clara-24B.i1-Q6_K.gguf) | i1-Q6_K | 19.4 | 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..8ac0424 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0015be89337268adf669a7464bd5f9d28069b97b254e1cd9a19cedaba882dfed +size 10003525