commit 515b9de8325caaab32a1fdf33d419982fbf78e66 Author: ModelHub XC Date: Sat Sep 26 23:49:23 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLama2-7B-Structural-Prune-1.5x-32-20kCalib-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..37ac200 --- /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 +LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-32-20kCalib.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-32-20kCalib.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-32-20kCalib.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-32-20kCalib.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-32-20kCalib.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.IQ3_M.gguf b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.IQ3_M.gguf new file mode 100644 index 0000000..a184373 --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54280fe8a4e9c58ff7761b8fe2574beed7aba7a1f2c340a71d61b7962a749488 +size 3114865088 diff --git a/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.IQ3_S.gguf b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.IQ3_S.gguf new file mode 100644 index 0000000..a20070e --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24fa52ae0d173f71eba16433f1664a6bc91473d15686ac11eef4045bcafae626 +size 2948305344 diff --git a/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.IQ3_XS.gguf b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.IQ3_XS.gguf new file mode 100644 index 0000000..c4044b4 --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e058f80417d5b2654dcbbf94a36f19eff3032c3253e621a084ce5a68279b174 +size 2796523968 diff --git a/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.IQ4_XS.gguf b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.IQ4_XS.gguf new file mode 100644 index 0000000..d18c75b --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e17755ba94c600858dcb3a6be1782b8405a330642fee7da465b60fdcd1f3f3e +size 3647517120 diff --git a/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q2_K.gguf b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q2_K.gguf new file mode 100644 index 0000000..96dfb52 --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2786b3a572612de9e45ef34fd3b7ab277e8aaaa3908a373af2e9d8c6d79c889e +size 2532864448 diff --git a/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q3_K_L.gguf b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q3_K_L.gguf new file mode 100644 index 0000000..db281a1 --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d56f479dfa1361b102b3c9f7c3a4b0e99f51e9ed65ac92f57ef884c2b6d78f0 +size 3597111744 diff --git a/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q3_K_M.gguf b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q3_K_M.gguf new file mode 100644 index 0000000..969b4be --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:904221b841c97b67ab1e9362680e340e3adee4cc7c2642538f8ff41a8d2cab8b +size 3298005440 diff --git a/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q3_K_S.gguf b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q3_K_S.gguf new file mode 100644 index 0000000..a150fdc --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f449ef291146b7bd11d269284e3212da030a70e0c5f1f9a0601b7f3cd46beabc +size 2948305344 diff --git a/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q4_K_M.gguf b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q4_K_M.gguf new file mode 100644 index 0000000..e7f4435 --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d3e411cc9295e1fac402cca31fca5f105933f261b39348e95196d4015a8a2e9 +size 4081004992 diff --git a/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q4_K_S.gguf b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q4_K_S.gguf new file mode 100644 index 0000000..9659e29 --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ae7be6b0adf8209d28f7579a94e3eabaf561b4388a57069c2e2859f722a31d5 +size 3856740800 diff --git a/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q5_K_M.gguf b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q5_K_M.gguf new file mode 100644 index 0000000..81b359c --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cab49b61afdf9ed5ba925640cb1db5e72ca6752fd8c99cae1ce0f157684c331 +size 4783157696 diff --git a/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q5_K_S.gguf b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q5_K_S.gguf new file mode 100644 index 0000000..0881312 --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf780c1b7efb55cdb452b45816be10f9283a34635b1b1df188cc9bfdb21b5ae4 +size 4651692480 diff --git a/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q6_K.gguf b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q6_K.gguf new file mode 100644 index 0000000..0cc1446 --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b2d0f02bc90044b135cb2571526faa62dc4e75402174a7201c726e0169b7f28 +size 5529194944 diff --git a/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q8_0.gguf b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q8_0.gguf new file mode 100644 index 0000000..1242897 --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:807e459f575dc33ea328811559ce39335e155a95bbdc132a76cb0db4999cd8fd +size 7161090496 diff --git a/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.f16.gguf b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.f16.gguf new file mode 100644 index 0000000..17abc2c --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05c452817f05c19a0b2ccf08223cc8161aafcb411b9571e2d185841b930c3325 +size 13478105536 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d386e86 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: Shengkun/LLama2-7B-Structural-Prune-1.5x-32-20kCalib +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Shengkun/LLama2-7B-Structural-Prune-1.5x-32-20kCalib + + +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/LLama2-7B-Structural-Prune-1.5x-32-20kCalib-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-32-20kCalib-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.IQ3_XS.gguf) | IQ3_XS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-32-20kCalib-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.IQ3_S.gguf) | IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-32-20kCalib-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-32-20kCalib-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.IQ3_M.gguf) | IQ3_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-32-20kCalib-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-32-20kCalib-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-32-20kCalib-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-32-20kCalib-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-32-20kCalib-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-32-20kCalib-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-32-20kCalib-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-32-20kCalib-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-32-20kCalib-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-32-20kCalib-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-32-20kCalib.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. + +