commit 232ee56440a21b68ff1e0407baa9010dee2b8ce2 Author: ModelHub XC Date: Thu Jul 23 21:57:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Apollo-1.8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cefbbd4 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +Apollo-1.8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Apollo-1.8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Apollo-1.8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Apollo-1.8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Apollo-1.8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Apollo-1.8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Apollo-1.8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Apollo-1.8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Apollo-1.8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Apollo-1.8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Apollo-1.8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Apollo-1.8B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Apollo-1.8B.IQ4_XS.gguf b/Apollo-1.8B.IQ4_XS.gguf new file mode 100644 index 0000000..01ae48a --- /dev/null +++ b/Apollo-1.8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10da52cd26ae7d01586676b972613630f960bd830eea97128d01aeb1aaa7bc56 +size 1087356352 diff --git a/Apollo-1.8B.Q2_K.gguf b/Apollo-1.8B.Q2_K.gguf new file mode 100644 index 0000000..0b63709 --- /dev/null +++ b/Apollo-1.8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bf94bdad11a3b6e79bea090400bc95a23a5c20b95075dc6dc6e2bd57a9f229b +size 836341184 diff --git a/Apollo-1.8B.Q3_K_L.gguf b/Apollo-1.8B.Q3_K_L.gguf new file mode 100644 index 0000000..fe94eb6 --- /dev/null +++ b/Apollo-1.8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31c414c2aa056819658f039c43fbfbb14dd32e270e0616a9af3cd31cc293c141 +size 1070351808 diff --git a/Apollo-1.8B.Q3_K_M.gguf b/Apollo-1.8B.Q3_K_M.gguf new file mode 100644 index 0000000..d54f9e6 --- /dev/null +++ b/Apollo-1.8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acae08e90db0124defc0366e46a19c39e6a385b93b489dbe76e81433aed2112a +size 1041565120 diff --git a/Apollo-1.8B.Q3_K_S.gguf b/Apollo-1.8B.Q3_K_S.gguf new file mode 100644 index 0000000..56d0ed0 --- /dev/null +++ b/Apollo-1.8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:713cb8db487ca6dc02a60b247d8e83bff929c7dcff637371da4a7d4bcbea2749 +size 953566656 diff --git a/Apollo-1.8B.Q4_K_M.gguf b/Apollo-1.8B.Q4_K_M.gguf new file mode 100644 index 0000000..b2cdf04 --- /dev/null +++ b/Apollo-1.8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:729d630768377605d765377d2f5c94486cb86fcc8c5a46e28effa60694dea83a +size 1242521024 diff --git a/Apollo-1.8B.Q4_K_S.gguf b/Apollo-1.8B.Q4_K_S.gguf new file mode 100644 index 0000000..f176ea5 --- /dev/null +++ b/Apollo-1.8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51b4b405cf80b507ee1cf4094589507003ae8a92c75fd4c2bb1f25f0f4372112 +size 1156160960 diff --git a/Apollo-1.8B.Q5_K_M.gguf b/Apollo-1.8B.Q5_K_M.gguf new file mode 100644 index 0000000..52b72af --- /dev/null +++ b/Apollo-1.8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:345091546d53e2708c50b1fb82c3db4f7cc655946868c0fdd3f96cb822c5837c +size 1410194880 diff --git a/Apollo-1.8B.Q5_K_S.gguf b/Apollo-1.8B.Q5_K_S.gguf new file mode 100644 index 0000000..8571abc --- /dev/null +++ b/Apollo-1.8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d661bc38d8e94c451845958571c87c26edfd7022744244319c5b6ecda6173d3d +size 1327816128 diff --git a/Apollo-1.8B.Q6_K.gguf b/Apollo-1.8B.Q6_K.gguf new file mode 100644 index 0000000..cb43a98 --- /dev/null +++ b/Apollo-1.8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dbf86f39c26e6cb4670bcbb1b9cb22911905de864fa86c1cd332f5d4e9691f1 +size 1579021760 diff --git a/Apollo-1.8B.Q8_0.gguf b/Apollo-1.8B.Q8_0.gguf new file mode 100644 index 0000000..5cd5fee --- /dev/null +++ b/Apollo-1.8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06d0e493eeab6c62450c16abcdf321681f6f20d045d3e6f10ea15d1c272e5f4f +size 1958299072 diff --git a/Apollo-1.8B.f16.gguf b/Apollo-1.8B.f16.gguf new file mode 100644 index 0000000..4db0d01 --- /dev/null +++ b/Apollo-1.8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f04c551b19952a30752479b3e1840145ba68064c8a6de7e29a8aa25e5413a51 +size 3680093632 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fa5aa6b --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: FreedomIntelligence/Apollo-1.8B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/FreedomIntelligence/Apollo-1.8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Apollo-1.8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Apollo-1.8B-i1-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/Apollo-1.8B-GGUF/resolve/main/Apollo-1.8B.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Apollo-1.8B-GGUF/resolve/main/Apollo-1.8B.Q3_K_S.gguf) | Q3_K_S | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Apollo-1.8B-GGUF/resolve/main/Apollo-1.8B.Q3_K_M.gguf) | Q3_K_M | 1.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Apollo-1.8B-GGUF/resolve/main/Apollo-1.8B.Q3_K_L.gguf) | Q3_K_L | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Apollo-1.8B-GGUF/resolve/main/Apollo-1.8B.IQ4_XS.gguf) | IQ4_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Apollo-1.8B-GGUF/resolve/main/Apollo-1.8B.Q4_K_S.gguf) | Q4_K_S | 1.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Apollo-1.8B-GGUF/resolve/main/Apollo-1.8B.Q4_K_M.gguf) | Q4_K_M | 1.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Apollo-1.8B-GGUF/resolve/main/Apollo-1.8B.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Apollo-1.8B-GGUF/resolve/main/Apollo-1.8B.Q5_K_M.gguf) | Q5_K_M | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Apollo-1.8B-GGUF/resolve/main/Apollo-1.8B.Q6_K.gguf) | Q6_K | 1.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Apollo-1.8B-GGUF/resolve/main/Apollo-1.8B.Q8_0.gguf) | Q8_0 | 2.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Apollo-1.8B-GGUF/resolve/main/Apollo-1.8B.f16.gguf) | f16 | 3.8 | 16 bpw, overkill | + +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. + +