commit 479a92143ae5cfcb0d03d474e86a7c416480d3da Author: ModelHub XC Date: Wed May 6 01:40:41 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Apollo2-0.5B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a7988fd --- /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 +Apollo2-0.5B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Apollo2-0.5B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Apollo2-0.5B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Apollo2-0.5B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Apollo2-0.5B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Apollo2-0.5B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Apollo2-0.5B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Apollo2-0.5B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Apollo2-0.5B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Apollo2-0.5B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Apollo2-0.5B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Apollo2-0.5B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Apollo2-0.5B.IQ4_XS.gguf b/Apollo2-0.5B.IQ4_XS.gguf new file mode 100644 index 0000000..63fba7f --- /dev/null +++ b/Apollo2-0.5B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd45a707a1dc0870476a7437aa31e86accbcd8ebcc459e1981d4a0d7713a6fa9 +size 428019808 diff --git a/Apollo2-0.5B.Q2_K.gguf b/Apollo2-0.5B.Q2_K.gguf new file mode 100644 index 0000000..9628672 --- /dev/null +++ b/Apollo2-0.5B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48ad8e157a80069ec3ae8c04762513482a874a7db485e82fe1a5d9a38c61baae +size 415181920 diff --git a/Apollo2-0.5B.Q3_K_L.gguf b/Apollo2-0.5B.Q3_K_L.gguf new file mode 100644 index 0000000..66dbac1 --- /dev/null +++ b/Apollo2-0.5B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dedd99a9b43d49a3e96cd4f18b73eb9b41af60be45708a450e7e4938de607d9c +size 445932640 diff --git a/Apollo2-0.5B.Q3_K_M.gguf b/Apollo2-0.5B.Q3_K_M.gguf new file mode 100644 index 0000000..f3cee32 --- /dev/null +++ b/Apollo2-0.5B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13d1650a55b57e898da975697049afabaad1f8a5fb0e32edae873c5119f33202 +size 432041056 diff --git a/Apollo2-0.5B.Q3_K_S.gguf b/Apollo2-0.5B.Q3_K_S.gguf new file mode 100644 index 0000000..5d28198 --- /dev/null +++ b/Apollo2-0.5B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e19c0a3ad9b7fb7ff1d9f6a9a42e929bbb089a15fdf3dfb327164d2926c9902f +size 414837856 diff --git a/Apollo2-0.5B.Q4_K_M.gguf b/Apollo2-0.5B.Q4_K_M.gguf new file mode 100644 index 0000000..28a7204 --- /dev/null +++ b/Apollo2-0.5B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f638be93ac6d15240f49bbac35caf7f6ee076a0d5424b54bf542c0ef085b3ac +size 491399264 diff --git a/Apollo2-0.5B.Q4_K_S.gguf b/Apollo2-0.5B.Q4_K_S.gguf new file mode 100644 index 0000000..a811143 --- /dev/null +++ b/Apollo2-0.5B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c617ce0fab60cfc8d1b3cb1fb38658da68e9b53a53251f43fa48f39459b17b81 +size 479063136 diff --git a/Apollo2-0.5B.Q5_K_M.gguf b/Apollo2-0.5B.Q5_K_M.gguf new file mode 100644 index 0000000..6d0ca9d --- /dev/null +++ b/Apollo2-0.5B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ada12468288ceb5c13baf8ea60886083185521292319be60d1a55d32168b3c0 +size 522185824 diff --git a/Apollo2-0.5B.Q5_K_S.gguf b/Apollo2-0.5B.Q5_K_S.gguf new file mode 100644 index 0000000..7fc2458 --- /dev/null +++ b/Apollo2-0.5B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a35cdb90550ffe9adc3f5ba0da8d9cd6f19a470f62ea7b247289ca2f40014fdb +size 514809952 diff --git a/Apollo2-0.5B.Q6_K.gguf b/Apollo2-0.5B.Q6_K.gguf new file mode 100644 index 0000000..d34ed7b --- /dev/null +++ b/Apollo2-0.5B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59221cd3178d949eaf8f80e82556e600244d55f7066dda7861b8a6080fda8afc +size 650378336 diff --git a/Apollo2-0.5B.Q8_0.gguf b/Apollo2-0.5B.Q8_0.gguf new file mode 100644 index 0000000..452e594 --- /dev/null +++ b/Apollo2-0.5B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaf9c1b7610b3db59c26677dd72c01d360452bf14b02ab918ae55e43e48d398d +size 675710048 diff --git a/Apollo2-0.5B.f16.gguf b/Apollo2-0.5B.f16.gguf new file mode 100644 index 0000000..05fd42d --- /dev/null +++ b/Apollo2-0.5B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:935cfc6d7682112b16544c66a3b99f2b9202d6f752c0de5a42954d76f9643f03 +size 1266424928 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c60a778 --- /dev/null +++ b/README.md @@ -0,0 +1,111 @@ +--- +base_model: FreedomIntelligence/Apollo2-0.5B +datasets: +- FreedomIntelligence/ApolloMoEDataset +language: +- ar +- en +- zh +- ko +- ja +- mn +- th +- vi +- lo +- mg +- de +- pt +- es +- fr +- ru +- it +- hr +- gl +- cs +- co +- la +- uk +- bs +- bg +- eo +- sq +- da +- sa +- gn +- sr +- sk +- gd +- lb +- hi +- ku +- mt +- he +- ln +- bm +- sw +- ig +- rw +- ha +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- biology +- medical +--- +## About + + + + + + +static quants of https://huggingface.co/FreedomIntelligence/Apollo2-0.5B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Apollo2-0.5B-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/Apollo2-0.5B-GGUF/resolve/main/Apollo2-0.5B.Q3_K_S.gguf) | Q3_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Apollo2-0.5B-GGUF/resolve/main/Apollo2-0.5B.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Apollo2-0.5B-GGUF/resolve/main/Apollo2-0.5B.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Apollo2-0.5B-GGUF/resolve/main/Apollo2-0.5B.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Apollo2-0.5B-GGUF/resolve/main/Apollo2-0.5B.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Apollo2-0.5B-GGUF/resolve/main/Apollo2-0.5B.Q4_K_S.gguf) | Q4_K_S | 0.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Apollo2-0.5B-GGUF/resolve/main/Apollo2-0.5B.Q4_K_M.gguf) | Q4_K_M | 0.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Apollo2-0.5B-GGUF/resolve/main/Apollo2-0.5B.Q5_K_S.gguf) | Q5_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Apollo2-0.5B-GGUF/resolve/main/Apollo2-0.5B.Q5_K_M.gguf) | Q5_K_M | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Apollo2-0.5B-GGUF/resolve/main/Apollo2-0.5B.Q6_K.gguf) | Q6_K | 0.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Apollo2-0.5B-GGUF/resolve/main/Apollo2-0.5B.Q8_0.gguf) | Q8_0 | 0.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Apollo2-0.5B-GGUF/resolve/main/Apollo2-0.5B.f16.gguf) | f16 | 1.4 | 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. + +