From ae3a19588b07679800125be5ca8b2427f7b3e1fe Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Thu, 24 Sep 2026 16:51:16 +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/Llama-3.2-text2SQL-schemaReduzido-GGUF Source: Original Platform --- .gitattributes | 48 ++++++++++++++ Llama-3.2-text2SQL-schemaReduzido.IQ4_XS.gguf | 3 + Llama-3.2-text2SQL-schemaReduzido.Q2_K.gguf | 3 + Llama-3.2-text2SQL-schemaReduzido.Q3_K_L.gguf | 3 + Llama-3.2-text2SQL-schemaReduzido.Q3_K_M.gguf | 3 + Llama-3.2-text2SQL-schemaReduzido.Q3_K_S.gguf | 3 + ...-3.2-text2SQL-schemaReduzido.Q4_0_4_4.gguf | 3 + Llama-3.2-text2SQL-schemaReduzido.Q4_K_M.gguf | 3 + Llama-3.2-text2SQL-schemaReduzido.Q4_K_S.gguf | 3 + Llama-3.2-text2SQL-schemaReduzido.Q5_K_M.gguf | 3 + Llama-3.2-text2SQL-schemaReduzido.Q5_K_S.gguf | 3 + Llama-3.2-text2SQL-schemaReduzido.Q6_K.gguf | 3 + Llama-3.2-text2SQL-schemaReduzido.Q8_0.gguf | 3 + Llama-3.2-text2SQL-schemaReduzido.f16.gguf | 3 + README.md | 65 +++++++++++++++++++ 15 files changed, 152 insertions(+) create mode 100644 .gitattributes create mode 100644 Llama-3.2-text2SQL-schemaReduzido.IQ4_XS.gguf create mode 100644 Llama-3.2-text2SQL-schemaReduzido.Q2_K.gguf create mode 100644 Llama-3.2-text2SQL-schemaReduzido.Q3_K_L.gguf create mode 100644 Llama-3.2-text2SQL-schemaReduzido.Q3_K_M.gguf create mode 100644 Llama-3.2-text2SQL-schemaReduzido.Q3_K_S.gguf create mode 100644 Llama-3.2-text2SQL-schemaReduzido.Q4_0_4_4.gguf create mode 100644 Llama-3.2-text2SQL-schemaReduzido.Q4_K_M.gguf create mode 100644 Llama-3.2-text2SQL-schemaReduzido.Q4_K_S.gguf create mode 100644 Llama-3.2-text2SQL-schemaReduzido.Q5_K_M.gguf create mode 100644 Llama-3.2-text2SQL-schemaReduzido.Q5_K_S.gguf create mode 100644 Llama-3.2-text2SQL-schemaReduzido.Q6_K.gguf create mode 100644 Llama-3.2-text2SQL-schemaReduzido.Q8_0.gguf create mode 100644 Llama-3.2-text2SQL-schemaReduzido.f16.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7089b38 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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-3.2-text2SQL-schemaReduzido.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-text2SQL-schemaReduzido.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-text2SQL-schemaReduzido.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-text2SQL-schemaReduzido.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-text2SQL-schemaReduzido.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-text2SQL-schemaReduzido.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-text2SQL-schemaReduzido.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-text2SQL-schemaReduzido.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-text2SQL-schemaReduzido.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-text2SQL-schemaReduzido.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-text2SQL-schemaReduzido.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-text2SQL-schemaReduzido.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-text2SQL-schemaReduzido.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-text2SQL-schemaReduzido.IQ4_XS.gguf b/Llama-3.2-text2SQL-schemaReduzido.IQ4_XS.gguf new file mode 100644 index 0000000..971bd6d --- /dev/null +++ b/Llama-3.2-text2SQL-schemaReduzido.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ce63bd8785e4b7bd342d89103190775080d3956b09aec00a6ab0d491728f468 +size 748384384 diff --git a/Llama-3.2-text2SQL-schemaReduzido.Q2_K.gguf b/Llama-3.2-text2SQL-schemaReduzido.Q2_K.gguf new file mode 100644 index 0000000..2a5eb32 --- /dev/null +++ b/Llama-3.2-text2SQL-schemaReduzido.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47293d4ade0d126432421327358d467bffc466ff94c5023c8966da370f284f7a +size 580874368 diff --git a/Llama-3.2-text2SQL-schemaReduzido.Q3_K_L.gguf b/Llama-3.2-text2SQL-schemaReduzido.Q3_K_L.gguf new file mode 100644 index 0000000..cf2b2ab --- /dev/null +++ b/Llama-3.2-text2SQL-schemaReduzido.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20972763b7110008fe62bd8f85d63d6e1b62526487f22692f9d15dc82a3c5ec8 +size 732524672 diff --git a/Llama-3.2-text2SQL-schemaReduzido.Q3_K_M.gguf b/Llama-3.2-text2SQL-schemaReduzido.Q3_K_M.gguf new file mode 100644 index 0000000..d1251b8 --- /dev/null +++ b/Llama-3.2-text2SQL-schemaReduzido.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c6c64943412068cc9914a6cea443a9c6acba7f69de57e993cc74d5c07c04dbb +size 690843776 diff --git a/Llama-3.2-text2SQL-schemaReduzido.Q3_K_S.gguf b/Llama-3.2-text2SQL-schemaReduzido.Q3_K_S.gguf new file mode 100644 index 0000000..a87cb32 --- /dev/null +++ b/Llama-3.2-text2SQL-schemaReduzido.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d907a6af4b670d878ca98a10604bf8e2518d78d601406f472bce89f96199fa54 +size 641691776 diff --git a/Llama-3.2-text2SQL-schemaReduzido.Q4_0_4_4.gguf b/Llama-3.2-text2SQL-schemaReduzido.Q4_0_4_4.gguf new file mode 100644 index 0000000..941977e --- /dev/null +++ b/Llama-3.2-text2SQL-schemaReduzido.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b74fddded9e40a6c6fab6422b09233cf4114fab6a3ef26edd68404620886424 +size 770928768 diff --git a/Llama-3.2-text2SQL-schemaReduzido.Q4_K_M.gguf b/Llama-3.2-text2SQL-schemaReduzido.Q4_K_M.gguf new file mode 100644 index 0000000..d0d0fc2 --- /dev/null +++ b/Llama-3.2-text2SQL-schemaReduzido.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c497da642eadd22fb6a05722126027e9dd29cf25eb490b8b3e79ba533bc8b67 +size 807694464 diff --git a/Llama-3.2-text2SQL-schemaReduzido.Q4_K_S.gguf b/Llama-3.2-text2SQL-schemaReduzido.Q4_K_S.gguf new file mode 100644 index 0000000..aa1356a --- /dev/null +++ b/Llama-3.2-text2SQL-schemaReduzido.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a71ba798e3b643c22ad576ef4a460385aeacf5764df47e0711e2f8aa6a086cd0 +size 775647360 diff --git a/Llama-3.2-text2SQL-schemaReduzido.Q5_K_M.gguf b/Llama-3.2-text2SQL-schemaReduzido.Q5_K_M.gguf new file mode 100644 index 0000000..5d76b97 --- /dev/null +++ b/Llama-3.2-text2SQL-schemaReduzido.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb29a1ae090109e80c55fd4ee8243a06a20c719ad0b3a03cc13e958c3f906327 +size 911503488 diff --git a/Llama-3.2-text2SQL-schemaReduzido.Q5_K_S.gguf b/Llama-3.2-text2SQL-schemaReduzido.Q5_K_S.gguf new file mode 100644 index 0000000..df2a23e --- /dev/null +++ b/Llama-3.2-text2SQL-schemaReduzido.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f7680b55f3fbb053883d8af5d27839b70ecb5ecfe3ef1b8c6070e7af28e718a +size 892563584 diff --git a/Llama-3.2-text2SQL-schemaReduzido.Q6_K.gguf b/Llama-3.2-text2SQL-schemaReduzido.Q6_K.gguf new file mode 100644 index 0000000..184bbda --- /dev/null +++ b/Llama-3.2-text2SQL-schemaReduzido.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a3689037fb14100e890886e5cb05be0ac0af9f7a691ef66d7bad0ff16bb8212 +size 1021800576 diff --git a/Llama-3.2-text2SQL-schemaReduzido.Q8_0.gguf b/Llama-3.2-text2SQL-schemaReduzido.Q8_0.gguf new file mode 100644 index 0000000..c97ad02 --- /dev/null +++ b/Llama-3.2-text2SQL-schemaReduzido.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cff200713f10b845f934620805e816f1ae84483a62b1cd9e8712e0768d382cff +size 1321083008 diff --git a/Llama-3.2-text2SQL-schemaReduzido.f16.gguf b/Llama-3.2-text2SQL-schemaReduzido.f16.gguf new file mode 100644 index 0000000..8c4c729 --- /dev/null +++ b/Llama-3.2-text2SQL-schemaReduzido.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5c000cb0c3d8a60db49f728a9f1fc4c2abc546a7cfb806c4ba0d2afd4a104c9 +size 2479595648 diff --git a/README.md b/README.md new file mode 100644 index 0000000..54ad436 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: NESPED-GEN/Llama-3.2-text2SQL-schemaReduzido +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/NESPED-GEN/Llama-3.2-text2SQL-schemaReduzido + + +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-3.2-text2SQL-schemaReduzido-GGUF/resolve/main/Llama-3.2-text2SQL-schemaReduzido.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-text2SQL-schemaReduzido-GGUF/resolve/main/Llama-3.2-text2SQL-schemaReduzido.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-text2SQL-schemaReduzido-GGUF/resolve/main/Llama-3.2-text2SQL-schemaReduzido.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-text2SQL-schemaReduzido-GGUF/resolve/main/Llama-3.2-text2SQL-schemaReduzido.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-text2SQL-schemaReduzido-GGUF/resolve/main/Llama-3.2-text2SQL-schemaReduzido.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-text2SQL-schemaReduzido-GGUF/resolve/main/Llama-3.2-text2SQL-schemaReduzido.Q4_0_4_4.gguf) | Q4_0_4_4 | 0.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-text2SQL-schemaReduzido-GGUF/resolve/main/Llama-3.2-text2SQL-schemaReduzido.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-text2SQL-schemaReduzido-GGUF/resolve/main/Llama-3.2-text2SQL-schemaReduzido.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-text2SQL-schemaReduzido-GGUF/resolve/main/Llama-3.2-text2SQL-schemaReduzido.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-text2SQL-schemaReduzido-GGUF/resolve/main/Llama-3.2-text2SQL-schemaReduzido.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-text2SQL-schemaReduzido-GGUF/resolve/main/Llama-3.2-text2SQL-schemaReduzido.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-text2SQL-schemaReduzido-GGUF/resolve/main/Llama-3.2-text2SQL-schemaReduzido.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-text2SQL-schemaReduzido-GGUF/resolve/main/Llama-3.2-text2SQL-schemaReduzido.f16.gguf) | f16 | 2.6 | 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. + +