commit ca461631f3d8377d6df4529459d1db1b94fdd488 Author: ModelHub XC Date: Mon Jul 20 00:30:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/arvi-20b-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d6749ac --- /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 +arvi-20b.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +arvi-20b.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +arvi-20b.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +arvi-20b.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +arvi-20b.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +arvi-20b.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +arvi-20b.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +arvi-20b.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +arvi-20b.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +arvi-20b.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +arvi-20b.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +arvi-20b.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +arvi-20b.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +arvi-20b.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +arvi-20b.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +arvi-20b.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +arvi-20b.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +arvi-20b.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +arvi-20b.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +arvi-20b.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +arvi-20b.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +arvi-20b.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +arvi-20b.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +arvi-20b.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..d85527d --- /dev/null +++ b/README.md @@ -0,0 +1,91 @@ +--- +base_model: metanthropic/arvi-20b +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- metanthropic +- reasoning +- moe +- arvi +- agentic +- vllm +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/metanthropic/arvi-20b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#arvi-20b-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/arvi-20b-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/arvi-20b-i1-GGUF/resolve/main/arvi-20b.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/arvi-20b-i1-GGUF/resolve/main/arvi-20b.i1-IQ1_M.gguf) | i1-IQ1_M | 12.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/arvi-20b-i1-GGUF/resolve/main/arvi-20b.i1-IQ1_S.gguf) | i1-IQ1_S | 12.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/arvi-20b-i1-GGUF/resolve/main/arvi-20b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 12.1 | | +| [GGUF](https://huggingface.co/mradermacher/arvi-20b-i1-GGUF/resolve/main/arvi-20b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 12.1 | | +| [GGUF](https://huggingface.co/mradermacher/arvi-20b-i1-GGUF/resolve/main/arvi-20b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 12.2 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/arvi-20b-i1-GGUF/resolve/main/arvi-20b.i1-IQ2_M.gguf) | i1-IQ2_M | 12.2 | | +| [GGUF](https://huggingface.co/mradermacher/arvi-20b-i1-GGUF/resolve/main/arvi-20b.i1-IQ2_S.gguf) | i1-IQ2_S | 12.2 | | +| [GGUF](https://huggingface.co/mradermacher/arvi-20b-i1-GGUF/resolve/main/arvi-20b.i1-IQ3_S.gguf) | i1-IQ3_S | 12.2 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/arvi-20b-i1-GGUF/resolve/main/arvi-20b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 12.2 | | +| [GGUF](https://huggingface.co/mradermacher/arvi-20b-i1-GGUF/resolve/main/arvi-20b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/arvi-20b-i1-GGUF/resolve/main/arvi-20b.i1-Q2_K.gguf) | i1-Q2_K | 12.2 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/arvi-20b-i1-GGUF/resolve/main/arvi-20b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.2 | | +| [GGUF](https://huggingface.co/mradermacher/arvi-20b-i1-GGUF/resolve/main/arvi-20b.i1-Q2_K_S.gguf) | i1-Q2_K_S | 12.2 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/arvi-20b-i1-GGUF/resolve/main/arvi-20b.i1-Q4_0.gguf) | i1-Q4_0 | 12.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/arvi-20b-i1-GGUF/resolve/main/arvi-20b.i1-IQ3_M.gguf) | i1-IQ3_M | 12.3 | | +| [GGUF](https://huggingface.co/mradermacher/arvi-20b-i1-GGUF/resolve/main/arvi-20b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 13.0 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/arvi-20b-i1-GGUF/resolve/main/arvi-20b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 13.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/arvi-20b-i1-GGUF/resolve/main/arvi-20b.i1-Q4_1.gguf) | i1-Q4_1 | 13.5 | | +| [GGUF](https://huggingface.co/mradermacher/arvi-20b-i1-GGUF/resolve/main/arvi-20b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 14.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/arvi-20b-i1-GGUF/resolve/main/arvi-20b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 15.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/arvi-20b-i1-GGUF/resolve/main/arvi-20b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 16.0 | | +| [GGUF](https://huggingface.co/mradermacher/arvi-20b-i1-GGUF/resolve/main/arvi-20b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 17.0 | | +| [GGUF](https://huggingface.co/mradermacher/arvi-20b-i1-GGUF/resolve/main/arvi-20b.i1-Q6_K.gguf) | i1-Q6_K | 22.3 | 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/arvi-20b.i1-IQ1_M.gguf b/arvi-20b.i1-IQ1_M.gguf new file mode 100644 index 0000000..a6d204c --- /dev/null +++ b/arvi-20b.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f22658c2ede5603696467374ac157ab114f61f235ebdbcd85045c16b5f8cc25 +size 12016854432 diff --git a/arvi-20b.i1-IQ1_S.gguf b/arvi-20b.i1-IQ1_S.gguf new file mode 100644 index 0000000..46dd381 --- /dev/null +++ b/arvi-20b.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d6032a2a0e84e2712631e648c3c6d4dcd389b87c1ec8d8f2efef92d24ed7984 +size 12016854432 diff --git a/arvi-20b.i1-IQ2_M.gguf b/arvi-20b.i1-IQ2_M.gguf new file mode 100644 index 0000000..5c13f32 --- /dev/null +++ b/arvi-20b.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54e0bcff13905c436ebed21da6da2c3b8f5b6b058ca1de829dfaab9d7b5145a5 +size 12065514912 diff --git a/arvi-20b.i1-IQ2_S.gguf b/arvi-20b.i1-IQ2_S.gguf new file mode 100644 index 0000000..fa7cfb4 --- /dev/null +++ b/arvi-20b.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea22e26cf0745858948a1508e9d8ce4e5dfbeb2a3e64a7c237f7fecf2a9e488c +size 12065514912 diff --git a/arvi-20b.i1-IQ2_XS.gguf b/arvi-20b.i1-IQ2_XS.gguf new file mode 100644 index 0000000..67de157 --- /dev/null +++ b/arvi-20b.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:163bb4fd59eaade9f26a94d4abb4ae98cf75d6daf12e8345c61700bcc8e0ed3e +size 12025701792 diff --git a/arvi-20b.i1-IQ2_XXS.gguf b/arvi-20b.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..e74e8b0 --- /dev/null +++ b/arvi-20b.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad1cdbdecc5e59b6ab644465493834865d26a53f93e5e9df7de37c54017452ba +size 12016854432 diff --git a/arvi-20b.i1-IQ3_M.gguf b/arvi-20b.i1-IQ3_M.gguf new file mode 100644 index 0000000..e23e161 --- /dev/null +++ b/arvi-20b.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1fdc0dbb676c542d8dae3b6eaa410782fcb2e09c80c734086c6cf495ad03ff5 +size 12202648992 diff --git a/arvi-20b.i1-IQ3_S.gguf b/arvi-20b.i1-IQ3_S.gguf new file mode 100644 index 0000000..4096268 --- /dev/null +++ b/arvi-20b.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbeb17bb7996ed5a4685fddce91695536f3964caa48beb79be9398be3d7a75c3 +size 12065514912 diff --git a/arvi-20b.i1-IQ3_XS.gguf b/arvi-20b.i1-IQ3_XS.gguf new file mode 100644 index 0000000..106a174 --- /dev/null +++ b/arvi-20b.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2093772bda214c8e3f0f703c9c0f34da6a62be22f7274eeaac5b5f264778d274 +size 12065514912 diff --git a/arvi-20b.i1-IQ3_XXS.gguf b/arvi-20b.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..2241555 --- /dev/null +++ b/arvi-20b.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ffea1c7495771e4f8630d74914ec4edfbce16b8137251a24c2f1c84dc014072 +size 12065514912 diff --git a/arvi-20b.i1-IQ4_XS.gguf b/arvi-20b.i1-IQ4_XS.gguf new file mode 100644 index 0000000..07564e8 --- /dev/null +++ b/arvi-20b.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac626202d39e9e6aff0a40e69f9cbd893ae8bb41cc2541751bd65c2fd18a2223 +size 12096480672 diff --git a/arvi-20b.i1-Q2_K.gguf b/arvi-20b.i1-Q2_K.gguf new file mode 100644 index 0000000..4edf242 --- /dev/null +++ b/arvi-20b.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1047b668962f316a0ebe525e845ec6e1fc31d3f3f5c4977e6d2cd415d062159b +size 12065514912 diff --git a/arvi-20b.i1-Q2_K_S.gguf b/arvi-20b.i1-Q2_K_S.gguf new file mode 100644 index 0000000..97e9538 --- /dev/null +++ b/arvi-20b.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0f9e95f69c5e7aaf72247d424e7913cdf432c021b0d93111ab66087c15784c5 +size 12136293792 diff --git a/arvi-20b.i1-Q3_K_L.gguf b/arvi-20b.i1-Q3_K_L.gguf new file mode 100644 index 0000000..942db13 --- /dev/null +++ b/arvi-20b.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7206bf2456e0623178e65bca6a016dd3f38fc2c0bb076014220a4b2ed8f4caf4 +size 13335111072 diff --git a/arvi-20b.i1-Q3_K_M.gguf b/arvi-20b.i1-Q3_K_M.gguf new file mode 100644 index 0000000..26c9a48 --- /dev/null +++ b/arvi-20b.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc639b7e977fc7caba2144d1731437cd5e7703b4a9f6721bf361432083c3f58a +size 12916151712 diff --git a/arvi-20b.i1-Q3_K_S.gguf b/arvi-20b.i1-Q3_K_S.gguf new file mode 100644 index 0000000..d26a2e7 --- /dev/null +++ b/arvi-20b.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5db95a353d3477ca0257071fd11dbc51e2eac3a76bfaff70be34ca3750bbd346 +size 12061091232 diff --git a/arvi-20b.i1-Q4_0.gguf b/arvi-20b.i1-Q4_0.gguf new file mode 100644 index 0000000..736e6f1 --- /dev/null +++ b/arvi-20b.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20a6ee2226567d8062e2c702ae8ed68891e6c605e00578c1bcd86a813a942b0f +size 12148458912 diff --git a/arvi-20b.i1-Q4_1.gguf b/arvi-20b.i1-Q4_1.gguf new file mode 100644 index 0000000..3bae2ba --- /dev/null +++ b/arvi-20b.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8eacfaaf4b043bdb78a55e41cd5b568fb1e73817694baa50fbee31df5f0a54e9 +size 13369095072 diff --git a/arvi-20b.i1-Q4_K_M.gguf b/arvi-20b.i1-Q4_K_M.gguf new file mode 100644 index 0000000..5381590 --- /dev/null +++ b/arvi-20b.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4c1a23e2478dcd90603b15b90edb70d83e35274525ca268d0e5eb21a5e4b823 +size 15805137312 diff --git a/arvi-20b.i1-Q4_K_S.gguf b/arvi-20b.i1-Q4_K_S.gguf new file mode 100644 index 0000000..39cf27b --- /dev/null +++ b/arvi-20b.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f36cf4be27b1ae6c5de133281d4d663e2b1db5a1437dfade52106222a6d7369 +size 14654243232 diff --git a/arvi-20b.i1-Q5_K_M.gguf b/arvi-20b.i1-Q5_K_M.gguf new file mode 100644 index 0000000..7dd5fc8 --- /dev/null +++ b/arvi-20b.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07fe16d9a838e60f37e372745082ea47ee5bd185124bd136d5d05ac69aaa3e05 +size 16893063072 diff --git a/arvi-20b.i1-Q5_K_S.gguf b/arvi-20b.i1-Q5_K_S.gguf new file mode 100644 index 0000000..dc3a407 --- /dev/null +++ b/arvi-20b.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6abd82d33607f6c3c3d4c93448017d7f71a41ebb67e62fc08886c24464a6be5b +size 15892205472 diff --git a/arvi-20b.i1-Q6_K.gguf b/arvi-20b.i1-Q6_K.gguf new file mode 100644 index 0000000..f47b96c --- /dev/null +++ b/arvi-20b.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3d2fe9e371f188d0f9ccc84cb36c5dc84e8b06fb1936ebd613758144ba2f0e1 +size 22193345952 diff --git a/arvi-20b.imatrix.gguf b/arvi-20b.imatrix.gguf new file mode 100644 index 0000000..a43ea44 --- /dev/null +++ b/arvi-20b.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecf34d7ca55d83fbf14435f88954e94e7cc7bceceea8f81ea0c31fb837863cef +size 28079776