commit 89a37e51dae7479bec4cb1edb912d971ad0331d3 Author: ModelHub XC Date: Mon May 4 17:09:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Ava-1.5-12B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..88ec4db --- /dev/null +++ b/.gitattributes @@ -0,0 +1,58 @@ +*.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 +Ava-1.5-12B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Ava-1.5-12B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Ava-1.5-12B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ava-1.5-12B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Ava-1.5-12B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ava-1.5-12B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ava-1.5-12B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Ava-1.5-12B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Ava-1.5-12B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Ava-1.5-12B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ava-1.5-12B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Ava-1.5-12B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ava-1.5-12B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Ava-1.5-12B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Ava-1.5-12B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Ava-1.5-12B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ava-1.5-12B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Ava-1.5-12B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Ava-1.5-12B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ava-1.5-12B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Ava-1.5-12B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Ava-1.5-12B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Ava-1.5-12B.i1-IQ1_M.gguf b/Ava-1.5-12B.i1-IQ1_M.gguf new file mode 100644 index 0000000..11f9daf --- /dev/null +++ b/Ava-1.5-12B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:721175ddea233ecaf0ad856fdb16ee63ac25a22536d97da5cffd0726626a17b5 +size 3221624384 diff --git a/Ava-1.5-12B.i1-IQ1_S.gguf b/Ava-1.5-12B.i1-IQ1_S.gguf new file mode 100644 index 0000000..b946de4 --- /dev/null +++ b/Ava-1.5-12B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5795e07aa3a584f745abdbf0a1ca420d3e1a8ae724f86823f8b84ad49845dec +size 2999211584 diff --git a/Ava-1.5-12B.i1-IQ2_M.gguf b/Ava-1.5-12B.i1-IQ2_M.gguf new file mode 100644 index 0000000..5864109 --- /dev/null +++ b/Ava-1.5-12B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa4887dc58568e43bfa738d804f165880b48d1ab2fd98d4a8df55a7f5177272d +size 4435023424 diff --git a/Ava-1.5-12B.i1-IQ2_S.gguf b/Ava-1.5-12B.i1-IQ2_S.gguf new file mode 100644 index 0000000..b991904 --- /dev/null +++ b/Ava-1.5-12B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a7c855c76ab0969ad862b772fe5acbc9c9787fc311506eb9224f5f9dca2e64e +size 4138473024 diff --git a/Ava-1.5-12B.i1-IQ2_XS.gguf b/Ava-1.5-12B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..56e48a2 --- /dev/null +++ b/Ava-1.5-12B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebddc1363c913e436304c9751de8f4afb958ed0bc1d063d33e503c7c07399810 +size 3915077184 diff --git a/Ava-1.5-12B.i1-IQ2_XXS.gguf b/Ava-1.5-12B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..6f51d69 --- /dev/null +++ b/Ava-1.5-12B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd83b6abeb38b7fb4e6562cee9dc1c334b62865e053220afe6e0d14728b37703 +size 3592312384 diff --git a/Ava-1.5-12B.i1-IQ3_M.gguf b/Ava-1.5-12B.i1-IQ3_M.gguf new file mode 100644 index 0000000..776deee --- /dev/null +++ b/Ava-1.5-12B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54a2af79a1899ae02edc96814219071406ca5e4715614ba3fe747b96eef9eb6d +size 5722232384 diff --git a/Ava-1.5-12B.i1-IQ3_S.gguf b/Ava-1.5-12B.i1-IQ3_S.gguf new file mode 100644 index 0000000..505e9b4 --- /dev/null +++ b/Ava-1.5-12B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56d2ed0f685c805c752339c83c96f886d46ce07c52063c7d8597186c8d6a6832 +size 5562078784 diff --git a/Ava-1.5-12B.i1-IQ3_XS.gguf b/Ava-1.5-12B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..718d7e8 --- /dev/null +++ b/Ava-1.5-12B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db8bac258829f9a2cfea2d6eaba817458838afb51370abe8ecc80751aec028a0 +size 5306488384 diff --git a/Ava-1.5-12B.i1-IQ3_XXS.gguf b/Ava-1.5-12B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..9320350 --- /dev/null +++ b/Ava-1.5-12B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:511a1cf1002cb49ef1e7e419af7c4d7b4c405dccd4258bbb6ab2d6a26eae7443 +size 4945385024 diff --git a/Ava-1.5-12B.i1-IQ4_XS.gguf b/Ava-1.5-12B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..fb326c2 --- /dev/null +++ b/Ava-1.5-12B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d655b34dd3f512ab48e9d77ff14be66e2700b58b6f7e6d0da14ceb15eb691d4 +size 6742709824 diff --git a/Ava-1.5-12B.i1-Q2_K.gguf b/Ava-1.5-12B.i1-Q2_K.gguf new file mode 100644 index 0000000..86b074f --- /dev/null +++ b/Ava-1.5-12B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23126624759a046cd882a23154cbee119467784bedd90cb8fb148940aba64abc +size 4791047744 diff --git a/Ava-1.5-12B.i1-Q2_K_S.gguf b/Ava-1.5-12B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..d29df6c --- /dev/null +++ b/Ava-1.5-12B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:715dea10cb2ab37d0a9b400bfcfa24ef1a276ef6432f641768c7dff5f5bbea4f +size 4493678144 diff --git a/Ava-1.5-12B.i1-Q3_K_L.gguf b/Ava-1.5-12B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..35014b8 --- /dev/null +++ b/Ava-1.5-12B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67886ee3154c1bba290c5d03a5b801b4e3cefdcc839da383b64e5e6e63e4dbe9 +size 6561502784 diff --git a/Ava-1.5-12B.i1-Q3_K_M.gguf b/Ava-1.5-12B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..21dbbfd --- /dev/null +++ b/Ava-1.5-12B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e57a0c02433f6ea5a26a1537fa0d4fac66cfeb00396975a688ce209c9011f26c +size 6083089984 diff --git a/Ava-1.5-12B.i1-Q3_K_S.gguf b/Ava-1.5-12B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..584f68f --- /dev/null +++ b/Ava-1.5-12B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48653a83ec0eb8df01dea74114f4cc561f6173a0a5aad96a031fb4a977c4f57f +size 5534225984 diff --git a/Ava-1.5-12B.i1-Q4_0.gguf b/Ava-1.5-12B.i1-Q4_0.gguf new file mode 100644 index 0000000..79cde54 --- /dev/null +++ b/Ava-1.5-12B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6171f13bffe78cb704e29e19b6e324224bb7d7ea869fce0e02d99637efe11e48 +size 7094638144 diff --git a/Ava-1.5-12B.i1-Q4_K_M.gguf b/Ava-1.5-12B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..8868168 --- /dev/null +++ b/Ava-1.5-12B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b40ef38dda90ecde793610045a2356697d8abd95fdc54c88bacae3d7d64831ce +size 7477204544 diff --git a/Ava-1.5-12B.i1-Q4_K_S.gguf b/Ava-1.5-12B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..dd37e35 --- /dev/null +++ b/Ava-1.5-12B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2e62355f4d1449092fd6feef02bfb32b5f190fdcb7f41cf2fc1db8578795ace +size 7120197184 diff --git a/Ava-1.5-12B.i1-Q5_K_M.gguf b/Ava-1.5-12B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..ed5f357 --- /dev/null +++ b/Ava-1.5-12B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b936ec1da273d2d787603bab66d40392c8c5072a94375549eb0f9972b042133 +size 8727631424 diff --git a/Ava-1.5-12B.i1-Q5_K_S.gguf b/Ava-1.5-12B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..e830ece --- /dev/null +++ b/Ava-1.5-12B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:173e93ae12acf88cb5441e2e04d2c503b98918fb2d34519fab74ef3efd60ba83 +size 8518735424 diff --git a/Ava-1.5-12B.i1-Q6_K.gguf b/Ava-1.5-12B.i1-Q6_K.gguf new file mode 100644 index 0000000..c9bb76b --- /dev/null +++ b/Ava-1.5-12B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc39c4253f99ef3b8effca55d0e5f67fc5f2929865476b303ad05a997d849cc8 +size 10056209984 diff --git a/README.md b/README.md new file mode 100644 index 0000000..88327fa --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: Spestly/Ava-1.5-12B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- mistral +- trl +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Spestly/Ava-1.5-12B + + +static quants are available at https://huggingface.co/mradermacher/Ava-1.5-12B-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/Ava-1.5-12B-i1-GGUF/resolve/main/Ava-1.5-12B.i1-IQ1_S.gguf) | i1-IQ1_S | 3.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Ava-1.5-12B-i1-GGUF/resolve/main/Ava-1.5-12B.i1-IQ1_M.gguf) | i1-IQ1_M | 3.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Ava-1.5-12B-i1-GGUF/resolve/main/Ava-1.5-12B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Ava-1.5-12B-i1-GGUF/resolve/main/Ava-1.5-12B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Ava-1.5-12B-i1-GGUF/resolve/main/Ava-1.5-12B.i1-IQ2_S.gguf) | i1-IQ2_S | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Ava-1.5-12B-i1-GGUF/resolve/main/Ava-1.5-12B.i1-IQ2_M.gguf) | i1-IQ2_M | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Ava-1.5-12B-i1-GGUF/resolve/main/Ava-1.5-12B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 4.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Ava-1.5-12B-i1-GGUF/resolve/main/Ava-1.5-12B.i1-Q2_K.gguf) | i1-Q2_K | 4.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Ava-1.5-12B-i1-GGUF/resolve/main/Ava-1.5-12B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Ava-1.5-12B-i1-GGUF/resolve/main/Ava-1.5-12B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Ava-1.5-12B-i1-GGUF/resolve/main/Ava-1.5-12B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Ava-1.5-12B-i1-GGUF/resolve/main/Ava-1.5-12B.i1-IQ3_S.gguf) | i1-IQ3_S | 5.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Ava-1.5-12B-i1-GGUF/resolve/main/Ava-1.5-12B.i1-IQ3_M.gguf) | i1-IQ3_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Ava-1.5-12B-i1-GGUF/resolve/main/Ava-1.5-12B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Ava-1.5-12B-i1-GGUF/resolve/main/Ava-1.5-12B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Ava-1.5-12B-i1-GGUF/resolve/main/Ava-1.5-12B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.8 | | +| [GGUF](https://huggingface.co/mradermacher/Ava-1.5-12B-i1-GGUF/resolve/main/Ava-1.5-12B.i1-Q4_0.gguf) | i1-Q4_0 | 7.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Ava-1.5-12B-i1-GGUF/resolve/main/Ava-1.5-12B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Ava-1.5-12B-i1-GGUF/resolve/main/Ava-1.5-12B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Ava-1.5-12B-i1-GGUF/resolve/main/Ava-1.5-12B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 8.6 | | +| [GGUF](https://huggingface.co/mradermacher/Ava-1.5-12B-i1-GGUF/resolve/main/Ava-1.5-12B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/Ava-1.5-12B-i1-GGUF/resolve/main/Ava-1.5-12B.i1-Q6_K.gguf) | i1-Q6_K | 10.2 | 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..0cc3d77 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22395f0dbfd1b4847122e53f53ca539569a1db7d56f7c618268bc6d31ed5c1f3 +size 7054405