commit 6dd390f8e762b795840795e9ca30da5e2b3347d6 Author: ModelHub XC Date: Sat Sep 19 03:38:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-2-7b-nubidoc-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..01d6147 --- /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 +llama-2-7b-nubidoc.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-nubidoc.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-nubidoc.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-nubidoc.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-nubidoc.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-nubidoc.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-nubidoc.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-nubidoc.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-nubidoc.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-nubidoc.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-nubidoc.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-nubidoc.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-nubidoc.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-nubidoc.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-nubidoc.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..49d8fdc --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: Osru/llama-2-7b-nubidoc +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + +static quants of https://huggingface.co/Osru/llama-2-7b-nubidoc + + +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/llama-2-7b-nubidoc-GGUF/resolve/main/llama-2-7b-nubidoc.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-nubidoc-GGUF/resolve/main/llama-2-7b-nubidoc.IQ3_XS.gguf) | IQ3_XS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-nubidoc-GGUF/resolve/main/llama-2-7b-nubidoc.IQ3_S.gguf) | IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-nubidoc-GGUF/resolve/main/llama-2-7b-nubidoc.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-nubidoc-GGUF/resolve/main/llama-2-7b-nubidoc.IQ3_M.gguf) | IQ3_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-nubidoc-GGUF/resolve/main/llama-2-7b-nubidoc.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-nubidoc-GGUF/resolve/main/llama-2-7b-nubidoc.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-nubidoc-GGUF/resolve/main/llama-2-7b-nubidoc.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-nubidoc-GGUF/resolve/main/llama-2-7b-nubidoc.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-nubidoc-GGUF/resolve/main/llama-2-7b-nubidoc.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-nubidoc-GGUF/resolve/main/llama-2-7b-nubidoc.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-nubidoc-GGUF/resolve/main/llama-2-7b-nubidoc.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-nubidoc-GGUF/resolve/main/llama-2-7b-nubidoc.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-nubidoc-GGUF/resolve/main/llama-2-7b-nubidoc.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-nubidoc-GGUF/resolve/main/llama-2-7b-nubidoc.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. + + diff --git a/llama-2-7b-nubidoc.IQ3_M.gguf b/llama-2-7b-nubidoc.IQ3_M.gguf new file mode 100644 index 0000000..4a71c68 --- /dev/null +++ b/llama-2-7b-nubidoc.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b1ab9672e58d918decfd8e0069f80e3c728f7c7b1b4c68192d3cf9b6df2e141 +size 3114864832 diff --git a/llama-2-7b-nubidoc.IQ3_S.gguf b/llama-2-7b-nubidoc.IQ3_S.gguf new file mode 100644 index 0000000..5d4061a --- /dev/null +++ b/llama-2-7b-nubidoc.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06cc2177d8d1ef062890cbae522d766de5d2edb4a8661782c9e6edd5a665ef37 +size 2948305088 diff --git a/llama-2-7b-nubidoc.IQ3_XS.gguf b/llama-2-7b-nubidoc.IQ3_XS.gguf new file mode 100644 index 0000000..824e1ac --- /dev/null +++ b/llama-2-7b-nubidoc.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7bd0ad7a242206992dc49ae9e1090c8a0c023c17b6b7b62cb81d7b4111e20d7 +size 2796523712 diff --git a/llama-2-7b-nubidoc.IQ4_XS.gguf b/llama-2-7b-nubidoc.IQ4_XS.gguf new file mode 100644 index 0000000..6d86b44 --- /dev/null +++ b/llama-2-7b-nubidoc.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:811b39c4f3a0e6b4653d65a6297eee82869d81318e7b54c8d50e0a0f2727cec5 +size 3647516864 diff --git a/llama-2-7b-nubidoc.Q2_K.gguf b/llama-2-7b-nubidoc.Q2_K.gguf new file mode 100644 index 0000000..36f55e3 --- /dev/null +++ b/llama-2-7b-nubidoc.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:258171dc9e1ab050d072c5d2647cddab05da92310377c3176e7ed3cfecbf64b2 +size 2532864192 diff --git a/llama-2-7b-nubidoc.Q3_K_L.gguf b/llama-2-7b-nubidoc.Q3_K_L.gguf new file mode 100644 index 0000000..f3a1d64 --- /dev/null +++ b/llama-2-7b-nubidoc.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab2100ccc153b87437585fc280c4d2a4ae70a41691efb7fbea518065295ae2b3 +size 3597111488 diff --git a/llama-2-7b-nubidoc.Q3_K_M.gguf b/llama-2-7b-nubidoc.Q3_K_M.gguf new file mode 100644 index 0000000..731f5bc --- /dev/null +++ b/llama-2-7b-nubidoc.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:262122e2dada9ee02dd6f9865305961760f761fdfe92c2375e66fe009e3d5a6e +size 3298005184 diff --git a/llama-2-7b-nubidoc.Q3_K_S.gguf b/llama-2-7b-nubidoc.Q3_K_S.gguf new file mode 100644 index 0000000..3568496 --- /dev/null +++ b/llama-2-7b-nubidoc.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81f0be513dbeb58f55eaadfbd3a01d635a69ef9cf54e10665ba11c4c1e3a5d06 +size 2948305088 diff --git a/llama-2-7b-nubidoc.Q4_K_M.gguf b/llama-2-7b-nubidoc.Q4_K_M.gguf new file mode 100644 index 0000000..2164e7f --- /dev/null +++ b/llama-2-7b-nubidoc.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e60310213c875f8826171f239e32cbc4396c6362ae608b6b0fdac79adfe95d04 +size 4081004736 diff --git a/llama-2-7b-nubidoc.Q4_K_S.gguf b/llama-2-7b-nubidoc.Q4_K_S.gguf new file mode 100644 index 0000000..45dab06 --- /dev/null +++ b/llama-2-7b-nubidoc.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61cd463d24defbfd81c866f954764d754c80a30b0c0a7b2c9654f5442dcc134d +size 3856740544 diff --git a/llama-2-7b-nubidoc.Q5_K_M.gguf b/llama-2-7b-nubidoc.Q5_K_M.gguf new file mode 100644 index 0000000..3b15bf3 --- /dev/null +++ b/llama-2-7b-nubidoc.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:221203c7f8c922c3d3ece8d5deebe616b70bb1d8ce2f6771f8ee70adca1cb1cd +size 4783157440 diff --git a/llama-2-7b-nubidoc.Q5_K_S.gguf b/llama-2-7b-nubidoc.Q5_K_S.gguf new file mode 100644 index 0000000..bce458b --- /dev/null +++ b/llama-2-7b-nubidoc.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65588b591b5943edc87f0c0c464a11eb1ab28059d863575e7e7ded6741b47f31 +size 4651692224 diff --git a/llama-2-7b-nubidoc.Q6_K.gguf b/llama-2-7b-nubidoc.Q6_K.gguf new file mode 100644 index 0000000..e12e5b6 --- /dev/null +++ b/llama-2-7b-nubidoc.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c28afa9613fc0f61054bcf3b9aff87e3b4883b8e80ffee6cdb3bca3050cde3d6 +size 5529194688 diff --git a/llama-2-7b-nubidoc.Q8_0.gguf b/llama-2-7b-nubidoc.Q8_0.gguf new file mode 100644 index 0000000..5dadf2b --- /dev/null +++ b/llama-2-7b-nubidoc.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e77f7de0bfc4f62e5834e48e911a428bf9ff9c159393aa13820ed0d6e6201fb2 +size 7161090240 diff --git a/llama-2-7b-nubidoc.f16.gguf b/llama-2-7b-nubidoc.f16.gguf new file mode 100644 index 0000000..5beb7df --- /dev/null +++ b/llama-2-7b-nubidoc.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f17d00a2801a32a76bb9fdab51a1e83f6ab4e61c3f4bc4ff8d2804f8b6e2dab +size 13478105280