commit e6cb0c9226fe753648c663afdb9ed77e901f0db0 Author: ModelHub XC Date: Thu Jul 2 14:06:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Patent-Instruct-7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8b2bcbb --- /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 +Patent-Instruct-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Patent-Instruct-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Patent-Instruct-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Patent-Instruct-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Patent-Instruct-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Patent-Instruct-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Patent-Instruct-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Patent-Instruct-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Patent-Instruct-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Patent-Instruct-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Patent-Instruct-7b.f16.gguf filter=lfs diff=lfs merge=lfs -text +Patent-Instruct-7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Patent-Instruct-7b.IQ4_XS.gguf b/Patent-Instruct-7b.IQ4_XS.gguf new file mode 100644 index 0000000..ef5d799 --- /dev/null +++ b/Patent-Instruct-7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23981a19850ba9df2408dc7e4d550f1f5ef808ffc11eaad51804c7bb61d7f94c +size 3647517184 diff --git a/Patent-Instruct-7b.Q2_K.gguf b/Patent-Instruct-7b.Q2_K.gguf new file mode 100644 index 0000000..032cb93 --- /dev/null +++ b/Patent-Instruct-7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:301f52b1b8faf452a58a33c693dc9fa6c702864a8610c4d2a584c5305fae1a2c +size 2532864512 diff --git a/Patent-Instruct-7b.Q3_K_L.gguf b/Patent-Instruct-7b.Q3_K_L.gguf new file mode 100644 index 0000000..c939d4a --- /dev/null +++ b/Patent-Instruct-7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:354ea6a928b138741f2e91418be9ebd35eb72afc50c3f170e3df4c69f7ecaf13 +size 3597111808 diff --git a/Patent-Instruct-7b.Q3_K_M.gguf b/Patent-Instruct-7b.Q3_K_M.gguf new file mode 100644 index 0000000..a9cb9c4 --- /dev/null +++ b/Patent-Instruct-7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:445637fe89567911674e9cdaab5b7532aedd91bd997f72ca8ac58a21c2231714 +size 3298005504 diff --git a/Patent-Instruct-7b.Q3_K_S.gguf b/Patent-Instruct-7b.Q3_K_S.gguf new file mode 100644 index 0000000..6183a9c --- /dev/null +++ b/Patent-Instruct-7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0afc68c058772229d927c0043d576c7f7c2758421b33090706ef2d80eb16ce59 +size 2948305408 diff --git a/Patent-Instruct-7b.Q4_K_M.gguf b/Patent-Instruct-7b.Q4_K_M.gguf new file mode 100644 index 0000000..d43d4ea --- /dev/null +++ b/Patent-Instruct-7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f480441c0446f35cb11ff104439e8b3bf0424a7260263638745a63f96323e26 +size 4081005056 diff --git a/Patent-Instruct-7b.Q4_K_S.gguf b/Patent-Instruct-7b.Q4_K_S.gguf new file mode 100644 index 0000000..0dadb62 --- /dev/null +++ b/Patent-Instruct-7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f2e611713f5281c3d4d0c5a1a67efb29415d05a19456d16b340d897b216c6f7 +size 3856740864 diff --git a/Patent-Instruct-7b.Q5_K_M.gguf b/Patent-Instruct-7b.Q5_K_M.gguf new file mode 100644 index 0000000..4394f9c --- /dev/null +++ b/Patent-Instruct-7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8d5e2fb28f08ae036748cbcf191e7c1e2606006d66d69087e36b12f3ddd0a49 +size 4783157760 diff --git a/Patent-Instruct-7b.Q5_K_S.gguf b/Patent-Instruct-7b.Q5_K_S.gguf new file mode 100644 index 0000000..87009d5 --- /dev/null +++ b/Patent-Instruct-7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87a6b4d33fbe29e3a9c813b9dc0499a9b1f6d3062adcf43515331a4e414c80a8 +size 4651692544 diff --git a/Patent-Instruct-7b.Q6_K.gguf b/Patent-Instruct-7b.Q6_K.gguf new file mode 100644 index 0000000..ed9f616 --- /dev/null +++ b/Patent-Instruct-7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1321f36b84d5e3f7dff1538b8411ae30713b4790c265c6f96a3fc0c908929836 +size 5529195008 diff --git a/Patent-Instruct-7b.Q8_0.gguf b/Patent-Instruct-7b.Q8_0.gguf new file mode 100644 index 0000000..c07f7dd --- /dev/null +++ b/Patent-Instruct-7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da253418a55c4c47cacd8d3a66f431da8e78892d83c3bbb59cbeb762d2e70cae +size 7161090560 diff --git a/Patent-Instruct-7b.f16.gguf b/Patent-Instruct-7b.f16.gguf new file mode 100644 index 0000000..74d2807 --- /dev/null +++ b/Patent-Instruct-7b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:202b3300ee1f7f1194f1713445b4527103150191f22a10c90b9c3cb128596a69 +size 13478105600 diff --git a/README.md b/README.md new file mode 100644 index 0000000..874576c --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: arcee-ai/Patent-Instruct-7b +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/arcee-ai/Patent-Instruct-7b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Patent-Instruct-7b-GGUF).*** + +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/Patent-Instruct-7b-GGUF/resolve/main/Patent-Instruct-7b.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Patent-Instruct-7b-GGUF/resolve/main/Patent-Instruct-7b.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Patent-Instruct-7b-GGUF/resolve/main/Patent-Instruct-7b.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Patent-Instruct-7b-GGUF/resolve/main/Patent-Instruct-7b.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Patent-Instruct-7b-GGUF/resolve/main/Patent-Instruct-7b.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Patent-Instruct-7b-GGUF/resolve/main/Patent-Instruct-7b.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Patent-Instruct-7b-GGUF/resolve/main/Patent-Instruct-7b.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Patent-Instruct-7b-GGUF/resolve/main/Patent-Instruct-7b.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Patent-Instruct-7b-GGUF/resolve/main/Patent-Instruct-7b.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Patent-Instruct-7b-GGUF/resolve/main/Patent-Instruct-7b.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Patent-Instruct-7b-GGUF/resolve/main/Patent-Instruct-7b.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Patent-Instruct-7b-GGUF/resolve/main/Patent-Instruct-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. + +