commit 94de05c4fddd2a8b84caae383591b8d0328467a8 Author: ModelHub XC Date: Thu Apr 30 20:32:23 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Athena-70B-L3-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0e13350 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,64 @@ +*.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 +Athena-70B-L3.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Athena-70B-L3.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Athena-70B-L3.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Athena-70B-L3.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Athena-70B-L3.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Athena-70B-L3.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Athena-70B-L3.i1-Q6_K.gguf.part1of2 filter=lfs diff=lfs merge=lfs -text +Athena-70B-L3.i1-Q6_K.gguf.part2of2 filter=lfs diff=lfs merge=lfs -text +Athena-70B-L3.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Athena-70B-L3.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Athena-70B-L3.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Athena-70B-L3.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Athena-70B-L3.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Athena-70B-L3.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Athena-70B-L3.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Athena-70B-L3.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Athena-70B-L3.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Athena-70B-L3.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Athena-70B-L3.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Athena-70B-L3.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Athena-70B-L3.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Athena-70B-L3.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Athena-70B-L3.i1-IQ1_M.gguf b/Athena-70B-L3.i1-IQ1_M.gguf new file mode 100644 index 0000000..4d5caa7 --- /dev/null +++ b/Athena-70B-L3.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:160bb8e9fdeaa2c63af95c6e0b6a5608e040cbf97f086e1d1a38e52f07fb8325 +size 16751196256 diff --git a/Athena-70B-L3.i1-IQ1_S.gguf b/Athena-70B-L3.i1-IQ1_S.gguf new file mode 100644 index 0000000..b5b5621 --- /dev/null +++ b/Athena-70B-L3.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ff0cc544c59b21061c298ceeaeba817ddca7d20303aca0eed89944a1e584abf +size 15343482976 diff --git a/Athena-70B-L3.i1-IQ2_M.gguf b/Athena-70B-L3.i1-IQ2_M.gguf new file mode 100644 index 0000000..d8cde9c --- /dev/null +++ b/Athena-70B-L3.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cd81e92b800f987d3adc09e257f14ea6c1031e25033042396d3c78d9131bfe5 +size 24119294048 diff --git a/Athena-70B-L3.i1-IQ2_S.gguf b/Athena-70B-L3.i1-IQ2_S.gguf new file mode 100644 index 0000000..838c221 --- /dev/null +++ b/Athena-70B-L3.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:626d0d8db3edb91559ab61801ff05333f32725519a0c6fead62f001e132672c6 +size 22242343008 diff --git a/Athena-70B-L3.i1-IQ2_XS.gguf b/Athena-70B-L3.i1-IQ2_XS.gguf new file mode 100644 index 0000000..aa45600 --- /dev/null +++ b/Athena-70B-L3.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:109ee53b7e38f8d72a6cd912cbf9d6c671d79dc27f4cb92182dc50526fba376e +size 21142108256 diff --git a/Athena-70B-L3.i1-IQ2_XXS.gguf b/Athena-70B-L3.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..cb4ed1a --- /dev/null +++ b/Athena-70B-L3.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff2770b0a352554df37eed8983e0b8c828550b4396fdd8118257105671c6eb16 +size 19097385056 diff --git a/Athena-70B-L3.i1-IQ3_M.gguf b/Athena-70B-L3.i1-IQ3_M.gguf new file mode 100644 index 0000000..5524b41 --- /dev/null +++ b/Athena-70B-L3.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac3cbe726432a6294dd6beb54b21a7047da2e3b16f291eabcbbec6aff9fb834b +size 31937034336 diff --git a/Athena-70B-L3.i1-IQ3_S.gguf b/Athena-70B-L3.i1-IQ3_S.gguf new file mode 100644 index 0000000..c71c51d --- /dev/null +++ b/Athena-70B-L3.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7714a2a3c23fb3a4f13101c3d41a24acbf380d2b12b21601b22eac91f0fd0d58 +size 30912051296 diff --git a/Athena-70B-L3.i1-IQ3_XS.gguf b/Athena-70B-L3.i1-IQ3_XS.gguf new file mode 100644 index 0000000..a0f064e --- /dev/null +++ b/Athena-70B-L3.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74bf7dd9dc00c8ae2fccc2d88bf094ede8933ecdad31277781ccd409df197064 +size 29307730016 diff --git a/Athena-70B-L3.i1-IQ3_XXS.gguf b/Athena-70B-L3.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..1f829b0 --- /dev/null +++ b/Athena-70B-L3.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5420ce9b72fc53a927cdba1b19898a82ef6ad2056f72c65fa398684b6eea07ec +size 27469494368 diff --git a/Athena-70B-L3.i1-IQ4_XS.gguf b/Athena-70B-L3.i1-IQ4_XS.gguf new file mode 100644 index 0000000..3a692cb --- /dev/null +++ b/Athena-70B-L3.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5b887d96be3ffd208d4ebe4d06e714dd22e4c5bf7dfc2eaa9cce5400da11267 +size 37902661728 diff --git a/Athena-70B-L3.i1-Q2_K.gguf b/Athena-70B-L3.i1-Q2_K.gguf new file mode 100644 index 0000000..702dd00 --- /dev/null +++ b/Athena-70B-L3.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc3a26b575d0dad76b90f38a25dc58347ae538739951c436fb75c966cc452a9a +size 26375108704 diff --git a/Athena-70B-L3.i1-Q3_K_L.gguf b/Athena-70B-L3.i1-Q3_K_L.gguf new file mode 100644 index 0000000..ccbf991 --- /dev/null +++ b/Athena-70B-L3.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e464829cc177871a9399b624864f8e243bf0c55ff311be0ee7f4a9f99421b13 +size 37140592736 diff --git a/Athena-70B-L3.i1-Q3_K_M.gguf b/Athena-70B-L3.i1-Q3_K_M.gguf new file mode 100644 index 0000000..66a4b3f --- /dev/null +++ b/Athena-70B-L3.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:230abdab33b393088f7fd8a5c5714b1117275288343c78229c71ff1df4fe1a2d +size 34267494496 diff --git a/Athena-70B-L3.i1-Q3_K_S.gguf b/Athena-70B-L3.i1-Q3_K_S.gguf new file mode 100644 index 0000000..cade12e --- /dev/null +++ b/Athena-70B-L3.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ff2eb94512e92a9763d232eb377f88792ebe4f35b21d9434406790747ea393e +size 30912051296 diff --git a/Athena-70B-L3.i1-Q4_0.gguf b/Athena-70B-L3.i1-Q4_0.gguf new file mode 100644 index 0000000..7f459dd --- /dev/null +++ b/Athena-70B-L3.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e4d5decd389a4d7b1fba2acb767a3534c77817cc2223851032475e30160c6e8 +size 40116533344 diff --git a/Athena-70B-L3.i1-Q4_K_M.gguf b/Athena-70B-L3.i1-Q4_K_M.gguf new file mode 100644 index 0000000..ad9aa42 --- /dev/null +++ b/Athena-70B-L3.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49ee0085808d41c86089dfadb7a9c678c8be9ff63521d8c564010138a067232d +size 42520393824 diff --git a/Athena-70B-L3.i1-Q4_K_S.gguf b/Athena-70B-L3.i1-Q4_K_S.gguf new file mode 100644 index 0000000..8d35ad5 --- /dev/null +++ b/Athena-70B-L3.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76159b86d33214e85efcfb2d69bfadf140e5334c02491008f294219191f84f24 +size 40347220064 diff --git a/Athena-70B-L3.i1-Q5_K_M.gguf b/Athena-70B-L3.i1-Q5_K_M.gguf new file mode 100644 index 0000000..139261a --- /dev/null +++ b/Athena-70B-L3.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d78818a2518a816dafa5bc4c2d062befc9f6ce7b5815a6cf5082506459b9325 +size 49949816928 diff --git a/Athena-70B-L3.i1-Q5_K_S.gguf b/Athena-70B-L3.i1-Q5_K_S.gguf new file mode 100644 index 0000000..0782630 --- /dev/null +++ b/Athena-70B-L3.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1afeb9ffb77ea1b9c3d977a7fabb221d494ff1104a509b225c77e2029aba683a +size 48657447008 diff --git a/Athena-70B-L3.i1-Q6_K.gguf.part1of2 b/Athena-70B-L3.i1-Q6_K.gguf.part1of2 new file mode 100644 index 0000000..a5408a3 --- /dev/null +++ b/Athena-70B-L3.i1-Q6_K.gguf.part1of2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab3bfb4cd2bc855c2a1f490d16f19798f9ff0c83f742a5da1d80fbc0fed4bd82 +size 28991029248 diff --git a/Athena-70B-L3.i1-Q6_K.gguf.part2of2 b/Athena-70B-L3.i1-Q6_K.gguf.part2of2 new file mode 100644 index 0000000..14aa118 --- /dev/null +++ b/Athena-70B-L3.i1-Q6_K.gguf.part2of2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc07e09b71e25a6e4001281238b6faea4617d0e37fb46e0fa031f2a371fea380 +size 28897114208 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8441697 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: AiMavenAi/Athena-70B-L3 +language: +- en +library_name: transformers +license: cc-by-nc-nd-4.0 +quantized_by: mradermacher +tags: +- autotrain +- text-generation-inference +- text-generation +- peft +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/AiMavenAi/Athena-70B-L3 + + +static quants are available at https://huggingface.co/mradermacher/Athena-70B-L3-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/Athena-70B-L3-i1-GGUF/resolve/main/Athena-70B-L3.i1-IQ1_S.gguf) | i1-IQ1_S | 15.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Athena-70B-L3-i1-GGUF/resolve/main/Athena-70B-L3.i1-IQ1_M.gguf) | i1-IQ1_M | 16.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Athena-70B-L3-i1-GGUF/resolve/main/Athena-70B-L3.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 19.2 | | +| [GGUF](https://huggingface.co/mradermacher/Athena-70B-L3-i1-GGUF/resolve/main/Athena-70B-L3.i1-IQ2_XS.gguf) | i1-IQ2_XS | 21.2 | | +| [GGUF](https://huggingface.co/mradermacher/Athena-70B-L3-i1-GGUF/resolve/main/Athena-70B-L3.i1-IQ2_S.gguf) | i1-IQ2_S | 22.3 | | +| [GGUF](https://huggingface.co/mradermacher/Athena-70B-L3-i1-GGUF/resolve/main/Athena-70B-L3.i1-IQ2_M.gguf) | i1-IQ2_M | 24.2 | | +| [GGUF](https://huggingface.co/mradermacher/Athena-70B-L3-i1-GGUF/resolve/main/Athena-70B-L3.i1-Q2_K.gguf) | i1-Q2_K | 26.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Athena-70B-L3-i1-GGUF/resolve/main/Athena-70B-L3.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Athena-70B-L3-i1-GGUF/resolve/main/Athena-70B-L3.i1-IQ3_XS.gguf) | i1-IQ3_XS | 29.4 | | +| [GGUF](https://huggingface.co/mradermacher/Athena-70B-L3-i1-GGUF/resolve/main/Athena-70B-L3.i1-IQ3_S.gguf) | i1-IQ3_S | 31.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Athena-70B-L3-i1-GGUF/resolve/main/Athena-70B-L3.i1-Q3_K_S.gguf) | i1-Q3_K_S | 31.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Athena-70B-L3-i1-GGUF/resolve/main/Athena-70B-L3.i1-IQ3_M.gguf) | i1-IQ3_M | 32.0 | | +| [GGUF](https://huggingface.co/mradermacher/Athena-70B-L3-i1-GGUF/resolve/main/Athena-70B-L3.i1-Q3_K_M.gguf) | i1-Q3_K_M | 34.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Athena-70B-L3-i1-GGUF/resolve/main/Athena-70B-L3.i1-Q3_K_L.gguf) | i1-Q3_K_L | 37.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Athena-70B-L3-i1-GGUF/resolve/main/Athena-70B-L3.i1-IQ4_XS.gguf) | i1-IQ4_XS | 38.0 | | +| [GGUF](https://huggingface.co/mradermacher/Athena-70B-L3-i1-GGUF/resolve/main/Athena-70B-L3.i1-Q4_0.gguf) | i1-Q4_0 | 40.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Athena-70B-L3-i1-GGUF/resolve/main/Athena-70B-L3.i1-Q4_K_S.gguf) | i1-Q4_K_S | 40.4 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Athena-70B-L3-i1-GGUF/resolve/main/Athena-70B-L3.i1-Q4_K_M.gguf) | i1-Q4_K_M | 42.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Athena-70B-L3-i1-GGUF/resolve/main/Athena-70B-L3.i1-Q5_K_S.gguf) | i1-Q5_K_S | 48.8 | | +| [GGUF](https://huggingface.co/mradermacher/Athena-70B-L3-i1-GGUF/resolve/main/Athena-70B-L3.i1-Q5_K_M.gguf) | i1-Q5_K_M | 50.0 | | +| [PART 1](https://huggingface.co/mradermacher/Athena-70B-L3-i1-GGUF/resolve/main/Athena-70B-L3.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Athena-70B-L3-i1-GGUF/resolve/main/Athena-70B-L3.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 58.0 | 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..4dad59b --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a6393d16db460cb18a605c088599ce4af106741e828fafee6343013daaa2d95 +size 24922289