commit dbf558e7c34463a2c0638182a2d8ffc1529845df Author: ModelHub XC Date: Mon Sep 7 11:44:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLama2-7B-Structural-Prune-1.5x-128_size-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ef02078 --- /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-128_size.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-128_size.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-128_size.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-128_size.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-128_size.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-128_size.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-128_size.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-128_size.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-128_size.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-128_size.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-128_size.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-128_size.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-128_size.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-128_size.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +LLama2-7B-Structural-Prune-1.5x-128_size.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLama2-7B-Structural-Prune-1.5x-128_size.IQ3_M.gguf b/LLama2-7B-Structural-Prune-1.5x-128_size.IQ3_M.gguf new file mode 100644 index 0000000..2e60248 --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-128_size.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea226573774a8a2473fa1c54e6d7a9529d46ad2b94ee68c7de7ecd18a66c9b51 +size 3114865088 diff --git a/LLama2-7B-Structural-Prune-1.5x-128_size.IQ3_S.gguf b/LLama2-7B-Structural-Prune-1.5x-128_size.IQ3_S.gguf new file mode 100644 index 0000000..0ad5af6 --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-128_size.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5ea376fbc5b1d6e4ce1a256e9fb19b67966be546255c1e7fd4a2e37b9de46cc +size 2948305344 diff --git a/LLama2-7B-Structural-Prune-1.5x-128_size.IQ3_XS.gguf b/LLama2-7B-Structural-Prune-1.5x-128_size.IQ3_XS.gguf new file mode 100644 index 0000000..a9f55aa --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-128_size.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30f470554dd55d88d42931f29e9dd46229565b1ba46eb4c59eb1153e7465bbc3 +size 2796523968 diff --git a/LLama2-7B-Structural-Prune-1.5x-128_size.IQ4_XS.gguf b/LLama2-7B-Structural-Prune-1.5x-128_size.IQ4_XS.gguf new file mode 100644 index 0000000..b825ff9 --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-128_size.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9da207f8074096ebd866eb5c13a8e5b794095a3f4a8926aa5dc9b59d2fb895bb +size 3647517120 diff --git a/LLama2-7B-Structural-Prune-1.5x-128_size.Q2_K.gguf b/LLama2-7B-Structural-Prune-1.5x-128_size.Q2_K.gguf new file mode 100644 index 0000000..a2bb2ed --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-128_size.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a01f0f4b8c93df405a1fc1ba751c06247af1a68e799d3d3782a5490afe6eab9 +size 2532864448 diff --git a/LLama2-7B-Structural-Prune-1.5x-128_size.Q3_K_L.gguf b/LLama2-7B-Structural-Prune-1.5x-128_size.Q3_K_L.gguf new file mode 100644 index 0000000..2fddd93 --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-128_size.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4129b1805a7f2f0d961362c6e5c584b8f26547875f06ea61c414cfc714764a3 +size 3597111744 diff --git a/LLama2-7B-Structural-Prune-1.5x-128_size.Q3_K_M.gguf b/LLama2-7B-Structural-Prune-1.5x-128_size.Q3_K_M.gguf new file mode 100644 index 0000000..29c2748 --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-128_size.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:726fe874e7fe69c1e83b9a57cfde4d353c8a7236b7fb01ed2569c3470212fefb +size 3298005440 diff --git a/LLama2-7B-Structural-Prune-1.5x-128_size.Q3_K_S.gguf b/LLama2-7B-Structural-Prune-1.5x-128_size.Q3_K_S.gguf new file mode 100644 index 0000000..0d64659 --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-128_size.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a48b36c9e2afbdd2252bf9ec0da97f0f9ca5b8f7c63d659a9c6610f2c9085c96 +size 2948305344 diff --git a/LLama2-7B-Structural-Prune-1.5x-128_size.Q4_K_M.gguf b/LLama2-7B-Structural-Prune-1.5x-128_size.Q4_K_M.gguf new file mode 100644 index 0000000..b96f001 --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-128_size.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2292c26255a3a04d59183666c743af7595fc6977d84227ca337275136e3bdf23 +size 4081004992 diff --git a/LLama2-7B-Structural-Prune-1.5x-128_size.Q4_K_S.gguf b/LLama2-7B-Structural-Prune-1.5x-128_size.Q4_K_S.gguf new file mode 100644 index 0000000..94f920c --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-128_size.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46166bd9b54261080a6b416463025848277e87f8d66f76d3785d4d31d6e33841 +size 3856740800 diff --git a/LLama2-7B-Structural-Prune-1.5x-128_size.Q5_K_M.gguf b/LLama2-7B-Structural-Prune-1.5x-128_size.Q5_K_M.gguf new file mode 100644 index 0000000..c7e983a --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-128_size.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e88aae3cd78c1e3a2d19ff4a14e6d54753b367881c384a7a9ccb0b26eb6ed27e +size 4783157696 diff --git a/LLama2-7B-Structural-Prune-1.5x-128_size.Q5_K_S.gguf b/LLama2-7B-Structural-Prune-1.5x-128_size.Q5_K_S.gguf new file mode 100644 index 0000000..ef4d223 --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-128_size.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ef8a127ebb883862c0ffbdccc3b17a45075d81cee64ee0b87ad985cc59d7264 +size 4651692480 diff --git a/LLama2-7B-Structural-Prune-1.5x-128_size.Q6_K.gguf b/LLama2-7B-Structural-Prune-1.5x-128_size.Q6_K.gguf new file mode 100644 index 0000000..d2f14b8 --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-128_size.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4911a9988240c29ee23ed61ee671b3197f5c0837f0e324d1115c98e438460e5e +size 5529194944 diff --git a/LLama2-7B-Structural-Prune-1.5x-128_size.Q8_0.gguf b/LLama2-7B-Structural-Prune-1.5x-128_size.Q8_0.gguf new file mode 100644 index 0000000..721173a --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-128_size.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e51ea8fc39cac9f8e36af75137841d111b9bfb5ea0bb79c430a3354e670f46a +size 7161090496 diff --git a/LLama2-7B-Structural-Prune-1.5x-128_size.f16.gguf b/LLama2-7B-Structural-Prune-1.5x-128_size.f16.gguf new file mode 100644 index 0000000..822603b --- /dev/null +++ b/LLama2-7B-Structural-Prune-1.5x-128_size.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e3c6cf793e128b615784a44f46156e4d25a9bc195c8bff62eb375b35aaa2af6 +size 13478105536 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e642e59 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: Shengkun/LLama2-7B-Structural-Prune-1.5x-128_size +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-128_size + + +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-128_size-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-128_size.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-128_size-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-128_size.IQ3_XS.gguf) | IQ3_XS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-128_size-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-128_size.IQ3_S.gguf) | IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-128_size-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-128_size.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-128_size-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-128_size.IQ3_M.gguf) | IQ3_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-128_size-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-128_size.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-128_size-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-128_size.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-128_size-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-128_size.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-128_size-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-128_size.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-128_size-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-128_size.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-128_size-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-128_size.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-128_size-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-128_size.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-128_size-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-128_size.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-128_size-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-128_size.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLama2-7B-Structural-Prune-1.5x-128_size-GGUF/resolve/main/LLama2-7B-Structural-Prune-1.5x-128_size.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. + +