commit 87b090b8800be668880361e8524aec64e1493b43 Author: ModelHub XC Date: Tue Sep 1 03:50:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qra-7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3efc75c --- /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 +Qra-7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qra-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qra-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qra-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qra-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qra-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qra-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qra-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qra-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qra-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qra-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qra-7b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qra-7b.IQ4_XS.gguf b/Qra-7b.IQ4_XS.gguf new file mode 100644 index 0000000..8665da2 --- /dev/null +++ b/Qra-7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ee4f25446691c4d30669eb37be426b507be90259bb1cad1e4b166ccff97cad4 +size 3647517184 diff --git a/Qra-7b.Q2_K.gguf b/Qra-7b.Q2_K.gguf new file mode 100644 index 0000000..2f2b2e6 --- /dev/null +++ b/Qra-7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:798bb8fb417fb839395d7ad232eb1f951c68ac933daa15a61c625aa82cc822c6 +size 2532864512 diff --git a/Qra-7b.Q3_K_L.gguf b/Qra-7b.Q3_K_L.gguf new file mode 100644 index 0000000..578e5d8 --- /dev/null +++ b/Qra-7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0cf5db809e98b1abe66fe461b4cf1fbfd179d23479a813b58a5cc20b17a5ff4 +size 3597111808 diff --git a/Qra-7b.Q3_K_M.gguf b/Qra-7b.Q3_K_M.gguf new file mode 100644 index 0000000..c246fac --- /dev/null +++ b/Qra-7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dff1e4df3bc824617e3de31678750415f4872cdbcb88e8977744e1f4c0665106 +size 3298005504 diff --git a/Qra-7b.Q3_K_S.gguf b/Qra-7b.Q3_K_S.gguf new file mode 100644 index 0000000..c8bca8f --- /dev/null +++ b/Qra-7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c05d708a5d4662491f9fc0538c2a79b64780077dba05b306b96ae2a1ae66560d +size 2948305408 diff --git a/Qra-7b.Q4_K_M.gguf b/Qra-7b.Q4_K_M.gguf new file mode 100644 index 0000000..f25d273 --- /dev/null +++ b/Qra-7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf1490a1ce280e355fbcc1ad3e69e6ade85facbe30554246235c44ece40b8505 +size 4081005056 diff --git a/Qra-7b.Q4_K_S.gguf b/Qra-7b.Q4_K_S.gguf new file mode 100644 index 0000000..eb5acda --- /dev/null +++ b/Qra-7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77ec14b8d0f1b1bf2c3c37e4750d2cf76e542e1bf047ad447af448930fdb356e +size 3856740864 diff --git a/Qra-7b.Q5_K_M.gguf b/Qra-7b.Q5_K_M.gguf new file mode 100644 index 0000000..14f9c54 --- /dev/null +++ b/Qra-7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d43bfe9e16fb032b4e62454837cbfb2233fe09eb7171729d8505ce1cf297a35e +size 4783157760 diff --git a/Qra-7b.Q5_K_S.gguf b/Qra-7b.Q5_K_S.gguf new file mode 100644 index 0000000..7a487a9 --- /dev/null +++ b/Qra-7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5fb8ea2b907ef7e6775949f56d1c0c49d381d08cb2d43f3a7dd4d25f66568a1 +size 4651692544 diff --git a/Qra-7b.Q6_K.gguf b/Qra-7b.Q6_K.gguf new file mode 100644 index 0000000..c5c455e --- /dev/null +++ b/Qra-7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e47b2a5eb97fdbcad5702262cd6c65164d9d6cdc302c2b5ca27ec3da348e57dd +size 5529195008 diff --git a/Qra-7b.Q8_0.gguf b/Qra-7b.Q8_0.gguf new file mode 100644 index 0000000..e610d4a --- /dev/null +++ b/Qra-7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5210da22a52e53f4a41f9e5d2aa12363c07e01b82f8db548a27a99e982199a18 +size 7161090560 diff --git a/Qra-7b.f16.gguf b/Qra-7b.f16.gguf new file mode 100644 index 0000000..2342477 --- /dev/null +++ b/Qra-7b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af1c6c338a9ce51649e7d419692682499b7720bb09d771dee8b4fff6186bbb28 +size 13478105600 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a88cd19 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: OPI-PG/Qra-7b +language: +- en +library_name: transformers +license: llama2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/OPI-PG/Qra-7b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qra-7b-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qra-7b-i1-GGUF +## 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/Qra-7b-GGUF/resolve/main/Qra-7b.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qra-7b-GGUF/resolve/main/Qra-7b.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qra-7b-GGUF/resolve/main/Qra-7b.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qra-7b-GGUF/resolve/main/Qra-7b.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qra-7b-GGUF/resolve/main/Qra-7b.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qra-7b-GGUF/resolve/main/Qra-7b.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qra-7b-GGUF/resolve/main/Qra-7b.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qra-7b-GGUF/resolve/main/Qra-7b.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qra-7b-GGUF/resolve/main/Qra-7b.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qra-7b-GGUF/resolve/main/Qra-7b.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qra-7b-GGUF/resolve/main/Qra-7b.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qra-7b-GGUF/resolve/main/Qra-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. + +