commit f26b61da51fbe1db602f7a0f5022712b18754d94 Author: ModelHub XC Date: Thu Jul 23 15:58:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Bitnet-M7-resized-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..631df05 --- /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 +Bitnet-M7-resized.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Bitnet-M7-resized.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Bitnet-M7-resized.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Bitnet-M7-resized.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bitnet-M7-resized.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bitnet-M7-resized.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bitnet-M7-resized.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bitnet-M7-resized.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bitnet-M7-resized.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bitnet-M7-resized.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Bitnet-M7-resized.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Bitnet-M7-resized.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Bitnet-M7-resized.IQ4_XS.gguf b/Bitnet-M7-resized.IQ4_XS.gguf new file mode 100644 index 0000000..a87ebaa --- /dev/null +++ b/Bitnet-M7-resized.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93ebad210f9a444b3a586768bda63c8890c64d466efe5f75ded6e338232e611d +size 162936128 diff --git a/Bitnet-M7-resized.Q2_K.gguf b/Bitnet-M7-resized.Q2_K.gguf new file mode 100644 index 0000000..7cacdf1 --- /dev/null +++ b/Bitnet-M7-resized.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1dd85014aa857bcd9b419affe3c6dcc448cc32d62c7b69edf3224bc4879699c +size 127898944 diff --git a/Bitnet-M7-resized.Q3_K_L.gguf b/Bitnet-M7-resized.Q3_K_L.gguf new file mode 100644 index 0000000..1f8a529 --- /dev/null +++ b/Bitnet-M7-resized.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ebd3b85340338d6dc5abe621a70bbe04e955dec01339008bdc1150a44867fa8 +size 158442816 diff --git a/Bitnet-M7-resized.Q3_K_M.gguf b/Bitnet-M7-resized.Q3_K_M.gguf new file mode 100644 index 0000000..039a232 --- /dev/null +++ b/Bitnet-M7-resized.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e000b34e307bd6ef6675bbc20d331db50a6e7662ed064a53dc499d7ec8c00bbb +size 151627072 diff --git a/Bitnet-M7-resized.Q3_K_S.gguf b/Bitnet-M7-resized.Q3_K_S.gguf new file mode 100644 index 0000000..584a45f --- /dev/null +++ b/Bitnet-M7-resized.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d73a1c70207365ebd1163211465115b3863c25b2574baccc4cf2a3a541c24486 +size 142222656 diff --git a/Bitnet-M7-resized.Q4_K_M.gguf b/Bitnet-M7-resized.Q4_K_M.gguf new file mode 100644 index 0000000..3db7ca2 --- /dev/null +++ b/Bitnet-M7-resized.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e2392b40bff6f1da7ce0c9967f238364c3a4bb59011047e4274fd80624ed97f +size 172553536 diff --git a/Bitnet-M7-resized.Q4_K_S.gguf b/Bitnet-M7-resized.Q4_K_S.gguf new file mode 100644 index 0000000..5287332 --- /dev/null +++ b/Bitnet-M7-resized.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d873a44baf075ec56caac5f052d341551ab41dc8137da565cece86dd59393b2 +size 171406656 diff --git a/Bitnet-M7-resized.Q5_K_M.gguf b/Bitnet-M7-resized.Q5_K_M.gguf new file mode 100644 index 0000000..35e5fee --- /dev/null +++ b/Bitnet-M7-resized.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8afbb764b87e99f44330fc23023a58a82abdc16c434ee2d6921d08a0313308b1 +size 196474176 diff --git a/Bitnet-M7-resized.Q5_K_S.gguf b/Bitnet-M7-resized.Q5_K_S.gguf new file mode 100644 index 0000000..c50dc97 --- /dev/null +++ b/Bitnet-M7-resized.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0c4ea25766cef6a2524c3e4fd7f24c5098e88c7d299cab94a45868be41f00d0 +size 194803008 diff --git a/Bitnet-M7-resized.Q6_K.gguf b/Bitnet-M7-resized.Q6_K.gguf new file mode 100644 index 0000000..9bc8513 --- /dev/null +++ b/Bitnet-M7-resized.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c049dd21b021cb23055d5c6d344cd918a97329a25c1efc22fbc0dfb2bd5aad38 +size 221889856 diff --git a/Bitnet-M7-resized.Q8_0.gguf b/Bitnet-M7-resized.Q8_0.gguf new file mode 100644 index 0000000..063135c --- /dev/null +++ b/Bitnet-M7-resized.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:160a7129f2ad85fa6314b4803852f5dfc9d0800d696b2a986320ef67a71601a5 +size 287155520 diff --git a/Bitnet-M7-resized.f16.gguf b/Bitnet-M7-resized.f16.gguf new file mode 100644 index 0000000..4e82159 --- /dev/null +++ b/Bitnet-M7-resized.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58b478068775f1333b3125e508d3de2e448ca1bb47ab48f02b09bc332c6afa0b +size 539796800 diff --git a/README.md b/README.md new file mode 100644 index 0000000..23ad1dc --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: liminerity/Bitnet-M7-resized +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/liminerity/Bitnet-M7-resized + + +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/Bitnet-M7-resized-GGUF/resolve/main/Bitnet-M7-resized.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Bitnet-M7-resized-GGUF/resolve/main/Bitnet-M7-resized.Q3_K_S.gguf) | Q3_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Bitnet-M7-resized-GGUF/resolve/main/Bitnet-M7-resized.Q3_K_M.gguf) | Q3_K_M | 0.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Bitnet-M7-resized-GGUF/resolve/main/Bitnet-M7-resized.Q3_K_L.gguf) | Q3_K_L | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Bitnet-M7-resized-GGUF/resolve/main/Bitnet-M7-resized.IQ4_XS.gguf) | IQ4_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Bitnet-M7-resized-GGUF/resolve/main/Bitnet-M7-resized.Q4_K_S.gguf) | Q4_K_S | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Bitnet-M7-resized-GGUF/resolve/main/Bitnet-M7-resized.Q4_K_M.gguf) | Q4_K_M | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Bitnet-M7-resized-GGUF/resolve/main/Bitnet-M7-resized.Q5_K_S.gguf) | Q5_K_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Bitnet-M7-resized-GGUF/resolve/main/Bitnet-M7-resized.Q5_K_M.gguf) | Q5_K_M | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Bitnet-M7-resized-GGUF/resolve/main/Bitnet-M7-resized.Q6_K.gguf) | Q6_K | 0.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Bitnet-M7-resized-GGUF/resolve/main/Bitnet-M7-resized.Q8_0.gguf) | Q8_0 | 0.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Bitnet-M7-resized-GGUF/resolve/main/Bitnet-M7-resized.f16.gguf) | f16 | 0.6 | 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. + +