commit d9b440344b138900c0b7fb8e28e8065374514d7f Author: ModelHub XC Date: Tue Jul 7 21:07:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TAMA-vB-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c2a0b1b --- /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 +TAMA-vB.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +TAMA-vB.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TAMA-vB.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +TAMA-vB.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +TAMA-vB.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TAMA-vB.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +TAMA-vB.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TAMA-vB.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +TAMA-vB.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TAMA-vB.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TAMA-vB.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TAMA-vB.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +TAMA-vB.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TAMA-vB.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +TAMA-vB.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +TAMA-vB.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TAMA-vB.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TAMA-vB.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +TAMA-vB.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TAMA-vB.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +TAMA-vB.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +TAMA-vB.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +TAMA-vB.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TAMA-vB.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +TAMA-vB.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..398ffc9 --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: MichiganNLP/TAMA-vB +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- table +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/MichiganNLP/TAMA-vB + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#TAMA-vB-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/TAMA-vB-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/TAMA-vB-i1-GGUF/resolve/main/TAMA-vB.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/TAMA-vB-i1-GGUF/resolve/main/TAMA-vB.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/TAMA-vB-i1-GGUF/resolve/main/TAMA-vB.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/TAMA-vB-i1-GGUF/resolve/main/TAMA-vB.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/TAMA-vB-i1-GGUF/resolve/main/TAMA-vB.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/TAMA-vB-i1-GGUF/resolve/main/TAMA-vB.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/TAMA-vB-i1-GGUF/resolve/main/TAMA-vB.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/TAMA-vB-i1-GGUF/resolve/main/TAMA-vB.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/TAMA-vB-i1-GGUF/resolve/main/TAMA-vB.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/TAMA-vB-i1-GGUF/resolve/main/TAMA-vB.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TAMA-vB-i1-GGUF/resolve/main/TAMA-vB.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/TAMA-vB-i1-GGUF/resolve/main/TAMA-vB.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/TAMA-vB-i1-GGUF/resolve/main/TAMA-vB.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/TAMA-vB-i1-GGUF/resolve/main/TAMA-vB.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/TAMA-vB-i1-GGUF/resolve/main/TAMA-vB.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/TAMA-vB-i1-GGUF/resolve/main/TAMA-vB.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/TAMA-vB-i1-GGUF/resolve/main/TAMA-vB.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/TAMA-vB-i1-GGUF/resolve/main/TAMA-vB.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/TAMA-vB-i1-GGUF/resolve/main/TAMA-vB.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/TAMA-vB-i1-GGUF/resolve/main/TAMA-vB.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/TAMA-vB-i1-GGUF/resolve/main/TAMA-vB.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TAMA-vB-i1-GGUF/resolve/main/TAMA-vB.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/TAMA-vB-i1-GGUF/resolve/main/TAMA-vB.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/TAMA-vB-i1-GGUF/resolve/main/TAMA-vB.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/TAMA-vB-i1-GGUF/resolve/main/TAMA-vB.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | 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/TAMA-vB.i1-IQ1_M.gguf b/TAMA-vB.i1-IQ1_M.gguf new file mode 100644 index 0000000..cb47352 --- /dev/null +++ b/TAMA-vB.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0376a084adbda7ca3d6bf996df93e6c0a976bf9bf37da0ca189be49a1de3f54c +size 2161973568 diff --git a/TAMA-vB.i1-IQ1_S.gguf b/TAMA-vB.i1-IQ1_S.gguf new file mode 100644 index 0000000..588bd13 --- /dev/null +++ b/TAMA-vB.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d99a77d972de33a72f250309032ce065a2d5623ffda049da619b63ae7a9564ce +size 2019629376 diff --git a/TAMA-vB.i1-IQ2_M.gguf b/TAMA-vB.i1-IQ2_M.gguf new file mode 100644 index 0000000..6c0baf4 --- /dev/null +++ b/TAMA-vB.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a4885e9b00975e77a73dff8282d5d7a58408edede73d4aa081a0185628dadb5 +size 2948282688 diff --git a/TAMA-vB.i1-IQ2_S.gguf b/TAMA-vB.i1-IQ2_S.gguf new file mode 100644 index 0000000..3bc413f --- /dev/null +++ b/TAMA-vB.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10d4805e4b23a37677089adf7031f79c639898e6b4edd7d98555f4c9ae6783ab +size 2758490432 diff --git a/TAMA-vB.i1-IQ2_XS.gguf b/TAMA-vB.i1-IQ2_XS.gguf new file mode 100644 index 0000000..46bfb0a --- /dev/null +++ b/TAMA-vB.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1ac79e83bf64c15e57a94c37210b7e64eeafe94aa53ecefdf73e02951091c20 +size 2605783360 diff --git a/TAMA-vB.i1-IQ2_XXS.gguf b/TAMA-vB.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..85c83a3 --- /dev/null +++ b/TAMA-vB.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a21038a937c0b081fbc3d7a6b87ef4d7f4e6092bca5a59b86d308b6a96500d4 +size 2399213888 diff --git a/TAMA-vB.i1-IQ3_M.gguf b/TAMA-vB.i1-IQ3_M.gguf new file mode 100644 index 0000000..8b614ab --- /dev/null +++ b/TAMA-vB.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:440a63319b92e127630ce83eccae88671087a56d609c5ed9145e5edecbb3680c +size 3784825152 diff --git a/TAMA-vB.i1-IQ3_S.gguf b/TAMA-vB.i1-IQ3_S.gguf new file mode 100644 index 0000000..7366c22 --- /dev/null +++ b/TAMA-vB.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a08eb61e6afee57e855c20bdb79f57508189e862117b01cde3e865d27d8a02c3 +size 3682326848 diff --git a/TAMA-vB.i1-IQ3_XS.gguf b/TAMA-vB.i1-IQ3_XS.gguf new file mode 100644 index 0000000..8663c5d --- /dev/null +++ b/TAMA-vB.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f48037281107eb5d12cbea025cf8e30c04118977e0c82d92fd5f09ce08dac14f +size 3518748992 diff --git a/TAMA-vB.i1-IQ3_XXS.gguf b/TAMA-vB.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..bdd17c6 --- /dev/null +++ b/TAMA-vB.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58cb238b4a8f73ead1bbd0dff38bd1dc3b6dfefde26d045f95360cf1a90313df +size 3274914112 diff --git a/TAMA-vB.i1-IQ4_NL.gguf b/TAMA-vB.i1-IQ4_NL.gguf new file mode 100644 index 0000000..03e9f07 --- /dev/null +++ b/TAMA-vB.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:790d9358911d2b09bc052fe93c46820fe05f73d9c757faa46f757bd6b9968263 +size 4677990720 diff --git a/TAMA-vB.i1-IQ4_XS.gguf b/TAMA-vB.i1-IQ4_XS.gguf new file mode 100644 index 0000000..6349c10 --- /dev/null +++ b/TAMA-vB.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f81de8b57b93e2842a184facb5d1414845900eec633efb2b6899fd08cb3a594a +size 4447664448 diff --git a/TAMA-vB.i1-Q2_K.gguf b/TAMA-vB.i1-Q2_K.gguf new file mode 100644 index 0000000..452aa61 --- /dev/null +++ b/TAMA-vB.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07a688441be4fc3e1e07c81035c9f336bcd60c42ffad4ba45e07b69ece5f695b +size 3179133248 diff --git a/TAMA-vB.i1-Q2_K_S.gguf b/TAMA-vB.i1-Q2_K_S.gguf new file mode 100644 index 0000000..5b6ed33 --- /dev/null +++ b/TAMA-vB.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac615af59dfd92523e745db5ec9492ff52d252ea67e30f8aa9f512de0beaae1b +size 2988816704 diff --git a/TAMA-vB.i1-Q3_K_L.gguf b/TAMA-vB.i1-Q3_K_L.gguf new file mode 100644 index 0000000..bf4c9ff --- /dev/null +++ b/TAMA-vB.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1519309ef9921b77bf223be8283a909a40fe5ec590b0e05d210bd2fa7cb1a922 +size 4321958208 diff --git a/TAMA-vB.i1-Q3_K_M.gguf b/TAMA-vB.i1-Q3_K_M.gguf new file mode 100644 index 0000000..e67c037 --- /dev/null +++ b/TAMA-vB.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dc08df71c46469a8524ddf21f70bc40585a9a07a27b160356645002f909266b +size 4018919744 diff --git a/TAMA-vB.i1-Q3_K_S.gguf b/TAMA-vB.i1-Q3_K_S.gguf new file mode 100644 index 0000000..2d0025b --- /dev/null +++ b/TAMA-vB.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f8a0b8d9d784ccc0aeaf514b15921337b9a43014437f00b3aa96fe50eb5a36c +size 3664501056 diff --git a/TAMA-vB.i1-Q4_0.gguf b/TAMA-vB.i1-Q4_0.gguf new file mode 100644 index 0000000..dd2ad03 --- /dev/null +++ b/TAMA-vB.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d99a9b16039457ae17542c329fd7906a39f4238c5a3ee1e9ff842c0370eab7ad +size 4675893568 diff --git a/TAMA-vB.i1-Q4_1.gguf b/TAMA-vB.i1-Q4_1.gguf new file mode 100644 index 0000000..54806d1 --- /dev/null +++ b/TAMA-vB.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c006878ef20eaf932fd35171d065037ecd7b447766e0fb40544097161cdbeb9 +size 5130254656 diff --git a/TAMA-vB.i1-Q4_K_M.gguf b/TAMA-vB.i1-Q4_K_M.gguf new file mode 100644 index 0000000..f27f7ef --- /dev/null +++ b/TAMA-vB.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf78cd58303938440f189a7ff9bcc4044d2f5c3a6933b6cab14ea95bd41edf32 +size 4920736064 diff --git a/TAMA-vB.i1-Q4_K_S.gguf b/TAMA-vB.i1-Q4_K_S.gguf new file mode 100644 index 0000000..2f1e9a5 --- /dev/null +++ b/TAMA-vB.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce4d2b3125b957264cdf60a64f9d868157f32f085a246915125048da06ec3397 +size 4692670784 diff --git a/TAMA-vB.i1-Q5_K_M.gguf b/TAMA-vB.i1-Q5_K_M.gguf new file mode 100644 index 0000000..f576241 --- /dev/null +++ b/TAMA-vB.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9b881e8c44a06136b50ffbc8912b18ff8c2ad1e1f9e642b80c7fb72a48242c5 +size 5732989248 diff --git a/TAMA-vB.i1-Q5_K_S.gguf b/TAMA-vB.i1-Q5_K_S.gguf new file mode 100644 index 0000000..0853516 --- /dev/null +++ b/TAMA-vB.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa5a90ac0563455ca3f0100ed33810e7f8f65dd0d59b8cecc7d778faf54580f9 +size 5599295808 diff --git a/TAMA-vB.i1-Q6_K.gguf b/TAMA-vB.i1-Q6_K.gguf new file mode 100644 index 0000000..8cb639d --- /dev/null +++ b/TAMA-vB.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa7c1b0ece09d310addf96b8b45891ed3bf4005fc3bf0be3f7457686f4b24536 +size 6596008256 diff --git a/TAMA-vB.imatrix.gguf b/TAMA-vB.imatrix.gguf new file mode 100644 index 0000000..01a5f4d --- /dev/null +++ b/TAMA-vB.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3f8a2866133d7083bd27c027bfb205837cadfbafc23d0ed20e923130d6d8c3c +size 5015200