From 53608462661dc5ae46e8f802cadb103062ad9220 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sun, 4 Oct 2026 01:31:17 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/Patent-Llama-7B-Chat-Slerp-GGUF Source: Original Platform --- .gitattributes | 47 +++++++++++++++++ Patent-Llama-7B-Chat-Slerp.IQ4_XS.gguf | 3 ++ Patent-Llama-7B-Chat-Slerp.Q2_K.gguf | 3 ++ Patent-Llama-7B-Chat-Slerp.Q3_K_L.gguf | 3 ++ Patent-Llama-7B-Chat-Slerp.Q3_K_M.gguf | 3 ++ Patent-Llama-7B-Chat-Slerp.Q3_K_S.gguf | 3 ++ Patent-Llama-7B-Chat-Slerp.Q4_K_M.gguf | 3 ++ Patent-Llama-7B-Chat-Slerp.Q4_K_S.gguf | 3 ++ Patent-Llama-7B-Chat-Slerp.Q5_K_M.gguf | 3 ++ Patent-Llama-7B-Chat-Slerp.Q5_K_S.gguf | 3 ++ Patent-Llama-7B-Chat-Slerp.Q6_K.gguf | 3 ++ Patent-Llama-7B-Chat-Slerp.Q8_0.gguf | 3 ++ Patent-Llama-7B-Chat-Slerp.f16.gguf | 3 ++ README.md | 71 ++++++++++++++++++++++++++ 14 files changed, 154 insertions(+) create mode 100644 .gitattributes create mode 100644 Patent-Llama-7B-Chat-Slerp.IQ4_XS.gguf create mode 100644 Patent-Llama-7B-Chat-Slerp.Q2_K.gguf create mode 100644 Patent-Llama-7B-Chat-Slerp.Q3_K_L.gguf create mode 100644 Patent-Llama-7B-Chat-Slerp.Q3_K_M.gguf create mode 100644 Patent-Llama-7B-Chat-Slerp.Q3_K_S.gguf create mode 100644 Patent-Llama-7B-Chat-Slerp.Q4_K_M.gguf create mode 100644 Patent-Llama-7B-Chat-Slerp.Q4_K_S.gguf create mode 100644 Patent-Llama-7B-Chat-Slerp.Q5_K_M.gguf create mode 100644 Patent-Llama-7B-Chat-Slerp.Q5_K_S.gguf create mode 100644 Patent-Llama-7B-Chat-Slerp.Q6_K.gguf create mode 100644 Patent-Llama-7B-Chat-Slerp.Q8_0.gguf create mode 100644 Patent-Llama-7B-Chat-Slerp.f16.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..042d30c --- /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-Llama-7B-Chat-Slerp.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Patent-Llama-7B-Chat-Slerp.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Patent-Llama-7B-Chat-Slerp.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Patent-Llama-7B-Chat-Slerp.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Patent-Llama-7B-Chat-Slerp.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Patent-Llama-7B-Chat-Slerp.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Patent-Llama-7B-Chat-Slerp.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Patent-Llama-7B-Chat-Slerp.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Patent-Llama-7B-Chat-Slerp.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Patent-Llama-7B-Chat-Slerp.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Patent-Llama-7B-Chat-Slerp.f16.gguf filter=lfs diff=lfs merge=lfs -text +Patent-Llama-7B-Chat-Slerp.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Patent-Llama-7B-Chat-Slerp.IQ4_XS.gguf b/Patent-Llama-7B-Chat-Slerp.IQ4_XS.gguf new file mode 100644 index 0000000..beae7cf --- /dev/null +++ b/Patent-Llama-7B-Chat-Slerp.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34d51a477410b25ff882c696a57ff90db5715f845e73efa86daaaa2d1a2d1c6b +size 3647517824 diff --git a/Patent-Llama-7B-Chat-Slerp.Q2_K.gguf b/Patent-Llama-7B-Chat-Slerp.Q2_K.gguf new file mode 100644 index 0000000..1f3fd06 --- /dev/null +++ b/Patent-Llama-7B-Chat-Slerp.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ae7ab03b9af374f4d0c488603e3758e59da572978adaaf999bec86bab8b621b +size 2532865152 diff --git a/Patent-Llama-7B-Chat-Slerp.Q3_K_L.gguf b/Patent-Llama-7B-Chat-Slerp.Q3_K_L.gguf new file mode 100644 index 0000000..b0106ec --- /dev/null +++ b/Patent-Llama-7B-Chat-Slerp.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa1eb9950cbbaec28cbc46e610d73fff21b08870eac0e4526507daa02f132f5e +size 3597112448 diff --git a/Patent-Llama-7B-Chat-Slerp.Q3_K_M.gguf b/Patent-Llama-7B-Chat-Slerp.Q3_K_M.gguf new file mode 100644 index 0000000..b961bf2 --- /dev/null +++ b/Patent-Llama-7B-Chat-Slerp.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26629e005460ee97b8bab6a1631e8f537c5a24af472413dd0c03153efffe71dd +size 3298006144 diff --git a/Patent-Llama-7B-Chat-Slerp.Q3_K_S.gguf b/Patent-Llama-7B-Chat-Slerp.Q3_K_S.gguf new file mode 100644 index 0000000..633e7f6 --- /dev/null +++ b/Patent-Llama-7B-Chat-Slerp.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e23e2170a96a79d0454c1a11630d64fe2498babf777f7a03af56c24e4ff7a133 +size 2948306048 diff --git a/Patent-Llama-7B-Chat-Slerp.Q4_K_M.gguf b/Patent-Llama-7B-Chat-Slerp.Q4_K_M.gguf new file mode 100644 index 0000000..a65c89c --- /dev/null +++ b/Patent-Llama-7B-Chat-Slerp.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e65e2ff0871474c06faff4bb6046a24f807348c46aa21dc22e400fe57e80d7fb +size 4081005696 diff --git a/Patent-Llama-7B-Chat-Slerp.Q4_K_S.gguf b/Patent-Llama-7B-Chat-Slerp.Q4_K_S.gguf new file mode 100644 index 0000000..37ba813 --- /dev/null +++ b/Patent-Llama-7B-Chat-Slerp.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61c1a7f5c6b78156c8d848c2eb6fe931f1f19700d0ffcbf612184c4ed25b51d7 +size 3856741504 diff --git a/Patent-Llama-7B-Chat-Slerp.Q5_K_M.gguf b/Patent-Llama-7B-Chat-Slerp.Q5_K_M.gguf new file mode 100644 index 0000000..cf714a2 --- /dev/null +++ b/Patent-Llama-7B-Chat-Slerp.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d9335e5a251f9eb4c58a076bd4250e7f55187641a87959685900071f2d95abb +size 4783158400 diff --git a/Patent-Llama-7B-Chat-Slerp.Q5_K_S.gguf b/Patent-Llama-7B-Chat-Slerp.Q5_K_S.gguf new file mode 100644 index 0000000..f91b279 --- /dev/null +++ b/Patent-Llama-7B-Chat-Slerp.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a11d83d9765bb02bf243738caa7d2b44ec0b9097770f30ff1574adfb79abe4ee +size 4651693184 diff --git a/Patent-Llama-7B-Chat-Slerp.Q6_K.gguf b/Patent-Llama-7B-Chat-Slerp.Q6_K.gguf new file mode 100644 index 0000000..0a6a2c3 --- /dev/null +++ b/Patent-Llama-7B-Chat-Slerp.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d28b260dc09630b207dc5787b2c878fb0a78e1be40dc7cdb12f8aac0466f2b62 +size 5529195648 diff --git a/Patent-Llama-7B-Chat-Slerp.Q8_0.gguf b/Patent-Llama-7B-Chat-Slerp.Q8_0.gguf new file mode 100644 index 0000000..372decd --- /dev/null +++ b/Patent-Llama-7B-Chat-Slerp.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a50d8c67d2cec8389366f5946d8f83bdf8c119f4629cc7f800fef0590a06952 +size 7161091200 diff --git a/Patent-Llama-7B-Chat-Slerp.f16.gguf b/Patent-Llama-7B-Chat-Slerp.f16.gguf new file mode 100644 index 0000000..95d01b2 --- /dev/null +++ b/Patent-Llama-7B-Chat-Slerp.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2456a33627f2e43536bb9a8375aec9d67d3efb1653623dbe05dccef61d7a13ca +size 13478106240 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f0bdb1e --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: arcee-ai/Patent-Llama-7B-Chat-Slerp +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/arcee-ai/Patent-Llama-7B-Chat-Slerp + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Patent-Llama-7B-Chat-Slerp-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-Llama-7B-Chat-Slerp-GGUF/resolve/main/Patent-Llama-7B-Chat-Slerp.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Patent-Llama-7B-Chat-Slerp-GGUF/resolve/main/Patent-Llama-7B-Chat-Slerp.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Patent-Llama-7B-Chat-Slerp-GGUF/resolve/main/Patent-Llama-7B-Chat-Slerp.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Patent-Llama-7B-Chat-Slerp-GGUF/resolve/main/Patent-Llama-7B-Chat-Slerp.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Patent-Llama-7B-Chat-Slerp-GGUF/resolve/main/Patent-Llama-7B-Chat-Slerp.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Patent-Llama-7B-Chat-Slerp-GGUF/resolve/main/Patent-Llama-7B-Chat-Slerp.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Patent-Llama-7B-Chat-Slerp-GGUF/resolve/main/Patent-Llama-7B-Chat-Slerp.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Patent-Llama-7B-Chat-Slerp-GGUF/resolve/main/Patent-Llama-7B-Chat-Slerp.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Patent-Llama-7B-Chat-Slerp-GGUF/resolve/main/Patent-Llama-7B-Chat-Slerp.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Patent-Llama-7B-Chat-Slerp-GGUF/resolve/main/Patent-Llama-7B-Chat-Slerp.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Patent-Llama-7B-Chat-Slerp-GGUF/resolve/main/Patent-Llama-7B-Chat-Slerp.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Patent-Llama-7B-Chat-Slerp-GGUF/resolve/main/Patent-Llama-7B-Chat-Slerp.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. + +