commit 8eef3c138b4c367668111d53b328af2bb0fa80e7 Author: ModelHub XC Date: Sun May 24 15:55:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Apollo2-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ee82a98 --- /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 +Apollo2-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Apollo2-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Apollo2-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Apollo2-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Apollo2-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Apollo2-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Apollo2-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Apollo2-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Apollo2-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Apollo2-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Apollo2-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Apollo2-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Apollo2-7B.IQ4_XS.gguf b/Apollo2-7B.IQ4_XS.gguf new file mode 100644 index 0000000..8b9ec27 --- /dev/null +++ b/Apollo2-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31b9df1e4f22cd34a9048f60ce7da076b488863c9a5f3b00daf03edcd333ba6d +size 4250297504 diff --git a/Apollo2-7B.Q2_K.gguf b/Apollo2-7B.Q2_K.gguf new file mode 100644 index 0000000..e8049cd --- /dev/null +++ b/Apollo2-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:291ea02f3e60ceaa762e64a7830a793b7ff2abf6226542d65f3073dfc2c30db0 +size 3015939232 diff --git a/Apollo2-7B.Q3_K_L.gguf b/Apollo2-7B.Q3_K_L.gguf new file mode 100644 index 0000000..a962fdd --- /dev/null +++ b/Apollo2-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:387741a8ae3cbbb600c1a0635a9c29633e12ccde08b7888de6fbeae8d5eea9cb +size 4088458400 diff --git a/Apollo2-7B.Q3_K_M.gguf b/Apollo2-7B.Q3_K_M.gguf new file mode 100644 index 0000000..346638e --- /dev/null +++ b/Apollo2-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9af0483fb73c4443ff8091a37696e794b71039cfbe4b536279057ca72b534142 +size 3808390304 diff --git a/Apollo2-7B.Q3_K_S.gguf b/Apollo2-7B.Q3_K_S.gguf new file mode 100644 index 0000000..53ae17a --- /dev/null +++ b/Apollo2-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75c1e8fcec5e52f74f015c20b3124a882fbe8d0d7d378f9a71b194743a31d324 +size 3492367520 diff --git a/Apollo2-7B.Q4_K_M.gguf b/Apollo2-7B.Q4_K_M.gguf new file mode 100644 index 0000000..e257280 --- /dev/null +++ b/Apollo2-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af77d000d5848aced823a2c1273b91f2bc0222686cb3ac9d5bcb89d2a806dd1f +size 4683072672 diff --git a/Apollo2-7B.Q4_K_S.gguf b/Apollo2-7B.Q4_K_S.gguf new file mode 100644 index 0000000..4e6eef3 --- /dev/null +++ b/Apollo2-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c96f5f63580f98c80c1a2e9a736bef0ebce5e64b5ea0316c5d512d65157ff9e +size 4457768096 diff --git a/Apollo2-7B.Q5_K_M.gguf b/Apollo2-7B.Q5_K_M.gguf new file mode 100644 index 0000000..a57a840 --- /dev/null +++ b/Apollo2-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3843b83f8343aa59767bd3fb3f877bb675469d73e41447a4c3414ef82b5458f2 +size 5444830368 diff --git a/Apollo2-7B.Q5_K_S.gguf b/Apollo2-7B.Q5_K_S.gguf new file mode 100644 index 0000000..69d3947 --- /dev/null +++ b/Apollo2-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fef5dea14b06a5eef10036bba2d95e36b32e67e25fa2ccc4864a42d00bbe971 +size 5315175584 diff --git a/Apollo2-7B.Q6_K.gguf b/Apollo2-7B.Q6_K.gguf new file mode 100644 index 0000000..ad7448b --- /dev/null +++ b/Apollo2-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:543b3c7f57f6c18f02f6a02cfec27649b803ff4058498596be4addf29d55e302 +size 6254197920 diff --git a/Apollo2-7B.Q8_0.gguf b/Apollo2-7B.Q8_0.gguf new file mode 100644 index 0000000..0498a71 --- /dev/null +++ b/Apollo2-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2ff34d46e4d2394c4b8977fa97b65d21851c975d40ec25ac951706f56998f41 +size 8098524320 diff --git a/Apollo2-7B.f16.gguf b/Apollo2-7B.f16.gguf new file mode 100644 index 0000000..1786f21 --- /dev/null +++ b/Apollo2-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:486d9272d80dcc554e1d3a8f360285227dd1c1f9a6d7fce571931234885c66c7 +size 15237852320 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a860e0c --- /dev/null +++ b/README.md @@ -0,0 +1,116 @@ +--- +base_model: FreedomIntelligence/Apollo2-7B +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 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- biology +- medical +--- +## About + + + + + + +static quants of https://huggingface.co/FreedomIntelligence/Apollo2-7B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Apollo2-7B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Apollo2-7B-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/Apollo2-7B-GGUF/resolve/main/Apollo2-7B.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Apollo2-7B-GGUF/resolve/main/Apollo2-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Apollo2-7B-GGUF/resolve/main/Apollo2-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Apollo2-7B-GGUF/resolve/main/Apollo2-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Apollo2-7B-GGUF/resolve/main/Apollo2-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Apollo2-7B-GGUF/resolve/main/Apollo2-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Apollo2-7B-GGUF/resolve/main/Apollo2-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Apollo2-7B-GGUF/resolve/main/Apollo2-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Apollo2-7B-GGUF/resolve/main/Apollo2-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Apollo2-7B-GGUF/resolve/main/Apollo2-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Apollo2-7B-GGUF/resolve/main/Apollo2-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Apollo2-7B-GGUF/resolve/main/Apollo2-7B.f16.gguf) | f16 | 15.3 | 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. + +