commit 1b2dbb722b624be664283a24f6fef9814d61b949 Author: ModelHub XC Date: Sun Jun 14 23:50:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LEMMA-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8faa625 --- /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 +LEMMA-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LEMMA-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LEMMA-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +LEMMA-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LEMMA-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LEMMA-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LEMMA-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LEMMA-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LEMMA-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LEMMA-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LEMMA-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LEMMA-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LEMMA-7B.IQ4_XS.gguf b/LEMMA-7B.IQ4_XS.gguf new file mode 100644 index 0000000..6f15457 --- /dev/null +++ b/LEMMA-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a75f813a3bed7544473f9c0775d3a43fd1f0c8e1e658f0a9673ffc58d325533 +size 3647517280 diff --git a/LEMMA-7B.Q2_K.gguf b/LEMMA-7B.Q2_K.gguf new file mode 100644 index 0000000..0b4c1f2 --- /dev/null +++ b/LEMMA-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87d08b9825e4fe5bc67c9b5ad57190dceb585122364436b7111e30c04e2eb8b8 +size 2532864608 diff --git a/LEMMA-7B.Q3_K_L.gguf b/LEMMA-7B.Q3_K_L.gguf new file mode 100644 index 0000000..e58c0fb --- /dev/null +++ b/LEMMA-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff3a4d413a07eb8ecc65f410a93bedbf7344f39a6fc8f29bb51d46d9ddabc89a +size 3597111904 diff --git a/LEMMA-7B.Q3_K_M.gguf b/LEMMA-7B.Q3_K_M.gguf new file mode 100644 index 0000000..a4d6dbb --- /dev/null +++ b/LEMMA-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c3ce4dfc6065b934a444b52b4e8afc063b713d324b783118baf8af5757f9ec5 +size 3298005600 diff --git a/LEMMA-7B.Q3_K_S.gguf b/LEMMA-7B.Q3_K_S.gguf new file mode 100644 index 0000000..25e7f91 --- /dev/null +++ b/LEMMA-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cbf81b0bd7c9d6572d3ffa4cf31864a753d4daf9a61cca309cf19d026ff74df +size 2948305504 diff --git a/LEMMA-7B.Q4_K_M.gguf b/LEMMA-7B.Q4_K_M.gguf new file mode 100644 index 0000000..939315d --- /dev/null +++ b/LEMMA-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23c46f32fc17f235ce71cafd1eb12d82d1ddaf690de52bf7079f66172e9e3c6a +size 4081005152 diff --git a/LEMMA-7B.Q4_K_S.gguf b/LEMMA-7B.Q4_K_S.gguf new file mode 100644 index 0000000..a35f680 --- /dev/null +++ b/LEMMA-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:125ec5effbc6febf38ffff6bb75a539540649b104dfc5cced208a69c0710d96d +size 3856740960 diff --git a/LEMMA-7B.Q5_K_M.gguf b/LEMMA-7B.Q5_K_M.gguf new file mode 100644 index 0000000..45a1cc4 --- /dev/null +++ b/LEMMA-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ae81af75178aff36de28b70ee732d164a3b53661e5767fb91f0424358997917 +size 4783157856 diff --git a/LEMMA-7B.Q5_K_S.gguf b/LEMMA-7B.Q5_K_S.gguf new file mode 100644 index 0000000..41bad03 --- /dev/null +++ b/LEMMA-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9ba5c5d18b17cb33029e375e8be5318f47ae628147c2336f723706e2af03886 +size 4651692640 diff --git a/LEMMA-7B.Q6_K.gguf b/LEMMA-7B.Q6_K.gguf new file mode 100644 index 0000000..0e1216f --- /dev/null +++ b/LEMMA-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:217b156fdb7a0c37c0cad0fa6e6033efe4505ae6f3a4171d0f19469d9bd794a9 +size 5529195104 diff --git a/LEMMA-7B.Q8_0.gguf b/LEMMA-7B.Q8_0.gguf new file mode 100644 index 0000000..6c4a32b --- /dev/null +++ b/LEMMA-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc68c3f47a7a753eea836df2f7165e5ffafcba33e86094108981a10b6c67c119 +size 7161090656 diff --git a/LEMMA-7B.f16.gguf b/LEMMA-7B.f16.gguf new file mode 100644 index 0000000..e40559e --- /dev/null +++ b/LEMMA-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4480c33f26322b6ac217bcf2cb2f1097e930c6f1ea0bb68a01797691f4a3d45e +size 13478105696 diff --git a/README.md b/README.md new file mode 100644 index 0000000..56d2539 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: ZixuanANDJiaBao/LEMMA-7B +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/ZixuanANDJiaBao/LEMMA-7B + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/LEMMA-7B-GGUF/resolve/main/LEMMA-7B.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/LEMMA-7B-GGUF/resolve/main/LEMMA-7B.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/LEMMA-7B-GGUF/resolve/main/LEMMA-7B.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LEMMA-7B-GGUF/resolve/main/LEMMA-7B.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/LEMMA-7B-GGUF/resolve/main/LEMMA-7B.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/LEMMA-7B-GGUF/resolve/main/LEMMA-7B.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LEMMA-7B-GGUF/resolve/main/LEMMA-7B.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LEMMA-7B-GGUF/resolve/main/LEMMA-7B.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/LEMMA-7B-GGUF/resolve/main/LEMMA-7B.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/LEMMA-7B-GGUF/resolve/main/LEMMA-7B.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LEMMA-7B-GGUF/resolve/main/LEMMA-7B.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LEMMA-7B-GGUF/resolve/main/LEMMA-7B.f16.gguf) | f16 | 13.6 | 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. + +