commit fc9ce9db44719ff2a8157df4eb4a10193f4bca8f Author: ModelHub XC Date: Mon Sep 21 18:31:25 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MAmmoTH2-8B-Plus-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fc896f8 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +MAmmoTH2-8B-Plus.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MAmmoTH2-8B-Plus.f16.gguf filter=lfs diff=lfs merge=lfs -text +MAmmoTH2-8B-Plus.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +MAmmoTH2-8B-Plus.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MAmmoTH2-8B-Plus.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +MAmmoTH2-8B-Plus.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MAmmoTH2-8B-Plus.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MAmmoTH2-8B-Plus.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MAmmoTH2-8B-Plus.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MAmmoTH2-8B-Plus.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MAmmoTH2-8B-Plus.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MAmmoTH2-8B-Plus.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MAmmoTH2-8B-Plus.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MAmmoTH2-8B-Plus.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +MAmmoTH2-8B-Plus.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MAmmoTH2-8B-Plus.IQ3_M.gguf b/MAmmoTH2-8B-Plus.IQ3_M.gguf new file mode 100644 index 0000000..7df2819 --- /dev/null +++ b/MAmmoTH2-8B-Plus.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faca771dfa259947b65f4b167a3b3b257cf1ede86159c0841202615365969670 +size 3784823808 diff --git a/MAmmoTH2-8B-Plus.IQ3_S.gguf b/MAmmoTH2-8B-Plus.IQ3_S.gguf new file mode 100644 index 0000000..e482fe6 --- /dev/null +++ b/MAmmoTH2-8B-Plus.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc3c289236a3c7ac28130c4ece6773c3d7e7a581e3f25fc8f2ad8a9cd3faaaea +size 3682325504 diff --git a/MAmmoTH2-8B-Plus.IQ3_XS.gguf b/MAmmoTH2-8B-Plus.IQ3_XS.gguf new file mode 100644 index 0000000..1096242 --- /dev/null +++ b/MAmmoTH2-8B-Plus.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b21f2156f09e7196a8dee45e66422f8d954c9fe3a209a12c773794e4dd14aeb +size 3518747648 diff --git a/MAmmoTH2-8B-Plus.IQ4_XS.gguf b/MAmmoTH2-8B-Plus.IQ4_XS.gguf new file mode 100644 index 0000000..0b1d771 --- /dev/null +++ b/MAmmoTH2-8B-Plus.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e84bd91d62af2f22a813cec9d3df22e7d12adda3217956143c93e423bbfdcda +size 4484363264 diff --git a/MAmmoTH2-8B-Plus.Q2_K.gguf b/MAmmoTH2-8B-Plus.Q2_K.gguf new file mode 100644 index 0000000..b767205 --- /dev/null +++ b/MAmmoTH2-8B-Plus.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fb6cf70655f759917134b09512ca391dba87406e9a08e001187754bb988ee2a +size 3179131904 diff --git a/MAmmoTH2-8B-Plus.Q3_K_L.gguf b/MAmmoTH2-8B-Plus.Q3_K_L.gguf new file mode 100644 index 0000000..604f61c --- /dev/null +++ b/MAmmoTH2-8B-Plus.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cce1470ad4c298b51e0e39abb9a7e10e46f281d93af2c4991442a7477293c89 +size 4321956864 diff --git a/MAmmoTH2-8B-Plus.Q3_K_M.gguf b/MAmmoTH2-8B-Plus.Q3_K_M.gguf new file mode 100644 index 0000000..0eccb1c --- /dev/null +++ b/MAmmoTH2-8B-Plus.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21d354ecf342fba30b04371b60778542e4214137e52aae57cc40acbb31c5223f +size 4018918400 diff --git a/MAmmoTH2-8B-Plus.Q3_K_S.gguf b/MAmmoTH2-8B-Plus.Q3_K_S.gguf new file mode 100644 index 0000000..71ce7b8 --- /dev/null +++ b/MAmmoTH2-8B-Plus.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46de5be927fe2dcadd4a8d9733abdb2d4c30a407609ab3441a9411e9b47bd290 +size 3664499712 diff --git a/MAmmoTH2-8B-Plus.Q4_K_M.gguf b/MAmmoTH2-8B-Plus.Q4_K_M.gguf new file mode 100644 index 0000000..b12fae5 --- /dev/null +++ b/MAmmoTH2-8B-Plus.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:759e4752a020a288c83a983b2cf44edfb48be99aa64618b8e7133a0dd641968d +size 4920734720 diff --git a/MAmmoTH2-8B-Plus.Q4_K_S.gguf b/MAmmoTH2-8B-Plus.Q4_K_S.gguf new file mode 100644 index 0000000..289612f --- /dev/null +++ b/MAmmoTH2-8B-Plus.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:854302fa1ecf1b553f2c62d3b10237bf88cde5dc51a88ca452429cd2f3ca4150 +size 4692669440 diff --git a/MAmmoTH2-8B-Plus.Q5_K_M.gguf b/MAmmoTH2-8B-Plus.Q5_K_M.gguf new file mode 100644 index 0000000..195d70b --- /dev/null +++ b/MAmmoTH2-8B-Plus.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9253e55618eeee0aa8dfeeef350e959369a2bca070917d969ca8545d4bf7689a +size 5732987904 diff --git a/MAmmoTH2-8B-Plus.Q5_K_S.gguf b/MAmmoTH2-8B-Plus.Q5_K_S.gguf new file mode 100644 index 0000000..1de7cfe --- /dev/null +++ b/MAmmoTH2-8B-Plus.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c9a89cffe7226b5c2bc2b23343934fc89ea2324ae209b4bb969a67e3419cd50 +size 5599294464 diff --git a/MAmmoTH2-8B-Plus.Q6_K.gguf b/MAmmoTH2-8B-Plus.Q6_K.gguf new file mode 100644 index 0000000..f890e9b --- /dev/null +++ b/MAmmoTH2-8B-Plus.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:589ec10206fb492a0f71b5f3eacad5251f71edee32b05e63c5444c8485ccde86 +size 6596006912 diff --git a/MAmmoTH2-8B-Plus.Q8_0.gguf b/MAmmoTH2-8B-Plus.Q8_0.gguf new file mode 100644 index 0000000..0ab3068 --- /dev/null +++ b/MAmmoTH2-8B-Plus.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be3237907f2fd777488e46eacd45a1e551bece2148db5083682a72c01c6556ae +size 8540771328 diff --git a/MAmmoTH2-8B-Plus.f16.gguf b/MAmmoTH2-8B-Plus.f16.gguf new file mode 100644 index 0000000..2dd0049 --- /dev/null +++ b/MAmmoTH2-8B-Plus.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1015960ed653b52c73b894ccfce267e1a9fb67a706f6b678a7e714b30b20a711 +size 16068891648 diff --git a/README.md b/README.md new file mode 100644 index 0000000..79716e2 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: TIGER-Lab/MAmmoTH2-8B-Plus +datasets: +- TIGER-Lab/WebInstructSub +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/TIGER-Lab/MAmmoTH2-8B-Plus + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/MAmmoTH2-8B-Plus-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/MAmmoTH2-8B-Plus-GGUF/resolve/main/MAmmoTH2-8B-Plus.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8B-Plus-GGUF/resolve/main/MAmmoTH2-8B-Plus.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8B-Plus-GGUF/resolve/main/MAmmoTH2-8B-Plus.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8B-Plus-GGUF/resolve/main/MAmmoTH2-8B-Plus.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8B-Plus-GGUF/resolve/main/MAmmoTH2-8B-Plus.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8B-Plus-GGUF/resolve/main/MAmmoTH2-8B-Plus.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8B-Plus-GGUF/resolve/main/MAmmoTH2-8B-Plus.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8B-Plus-GGUF/resolve/main/MAmmoTH2-8B-Plus.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8B-Plus-GGUF/resolve/main/MAmmoTH2-8B-Plus.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8B-Plus-GGUF/resolve/main/MAmmoTH2-8B-Plus.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8B-Plus-GGUF/resolve/main/MAmmoTH2-8B-Plus.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8B-Plus-GGUF/resolve/main/MAmmoTH2-8B-Plus.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8B-Plus-GGUF/resolve/main/MAmmoTH2-8B-Plus.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8B-Plus-GGUF/resolve/main/MAmmoTH2-8B-Plus.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8B-Plus-GGUF/resolve/main/MAmmoTH2-8B-Plus.f16.gguf) | f16 | 16.2 | 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. + +