From d50a18e642359e2636512155c566262db3abc958 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Fri, 24 Apr 2026 16:19:03 +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/DeepSeek-R1-Distill-Llama-text-to-sql-GGUF Source: Original Platform --- .gitattributes | 47 ++++++++++++ ...k-R1-Distill-Llama-text-to-sql.IQ4_XS.gguf | 3 + ...eek-R1-Distill-Llama-text-to-sql.Q2_K.gguf | 3 + ...k-R1-Distill-Llama-text-to-sql.Q3_K_L.gguf | 3 + ...k-R1-Distill-Llama-text-to-sql.Q3_K_M.gguf | 3 + ...k-R1-Distill-Llama-text-to-sql.Q3_K_S.gguf | 3 + ...k-R1-Distill-Llama-text-to-sql.Q4_K_M.gguf | 3 + ...k-R1-Distill-Llama-text-to-sql.Q4_K_S.gguf | 3 + ...k-R1-Distill-Llama-text-to-sql.Q5_K_M.gguf | 3 + ...k-R1-Distill-Llama-text-to-sql.Q5_K_S.gguf | 3 + ...eek-R1-Distill-Llama-text-to-sql.Q6_K.gguf | 3 + ...eek-R1-Distill-Llama-text-to-sql.Q8_0.gguf | 3 + ...Seek-R1-Distill-Llama-text-to-sql.f16.gguf | 3 + README.md | 71 +++++++++++++++++++ 14 files changed, 154 insertions(+) create mode 100644 .gitattributes create mode 100644 DeepSeek-R1-Distill-Llama-text-to-sql.IQ4_XS.gguf create mode 100644 DeepSeek-R1-Distill-Llama-text-to-sql.Q2_K.gguf create mode 100644 DeepSeek-R1-Distill-Llama-text-to-sql.Q3_K_L.gguf create mode 100644 DeepSeek-R1-Distill-Llama-text-to-sql.Q3_K_M.gguf create mode 100644 DeepSeek-R1-Distill-Llama-text-to-sql.Q3_K_S.gguf create mode 100644 DeepSeek-R1-Distill-Llama-text-to-sql.Q4_K_M.gguf create mode 100644 DeepSeek-R1-Distill-Llama-text-to-sql.Q4_K_S.gguf create mode 100644 DeepSeek-R1-Distill-Llama-text-to-sql.Q5_K_M.gguf create mode 100644 DeepSeek-R1-Distill-Llama-text-to-sql.Q5_K_S.gguf create mode 100644 DeepSeek-R1-Distill-Llama-text-to-sql.Q6_K.gguf create mode 100644 DeepSeek-R1-Distill-Llama-text-to-sql.Q8_0.gguf create mode 100644 DeepSeek-R1-Distill-Llama-text-to-sql.f16.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..36c3be7 --- /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 +DeepSeek-R1-Distill-Llama-text-to-sql.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-text-to-sql.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-text-to-sql.f16.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-text-to-sql.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-text-to-sql.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-text-to-sql.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-text-to-sql.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-text-to-sql.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-text-to-sql.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-text-to-sql.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-text-to-sql.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-text-to-sql.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepSeek-R1-Distill-Llama-text-to-sql.IQ4_XS.gguf b/DeepSeek-R1-Distill-Llama-text-to-sql.IQ4_XS.gguf new file mode 100644 index 0000000..0095f62 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-text-to-sql.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f23b2286a941fe8d937302ce7d81dcd4f13602dcc13ae5d6046ae90aa937587c +size 4484366048 diff --git a/DeepSeek-R1-Distill-Llama-text-to-sql.Q2_K.gguf b/DeepSeek-R1-Distill-Llama-text-to-sql.Q2_K.gguf new file mode 100644 index 0000000..f7e5972 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-text-to-sql.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e78c24dc43788253c4188a8a2bbf57c9d33fe5f1ccccbe0d54497619224faf4 +size 3179134688 diff --git a/DeepSeek-R1-Distill-Llama-text-to-sql.Q3_K_L.gguf b/DeepSeek-R1-Distill-Llama-text-to-sql.Q3_K_L.gguf new file mode 100644 index 0000000..bfdf4a8 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-text-to-sql.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40c14d949d76b2bbdc363694d60c9008fa2b78182939ff24cc4817591a7607e2 +size 4321959648 diff --git a/DeepSeek-R1-Distill-Llama-text-to-sql.Q3_K_M.gguf b/DeepSeek-R1-Distill-Llama-text-to-sql.Q3_K_M.gguf new file mode 100644 index 0000000..53a5f8c --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-text-to-sql.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b1c80481e4329a5431118f0881e1dbedb0e598c882c87f1a878a74388b362de +size 4018921184 diff --git a/DeepSeek-R1-Distill-Llama-text-to-sql.Q3_K_S.gguf b/DeepSeek-R1-Distill-Llama-text-to-sql.Q3_K_S.gguf new file mode 100644 index 0000000..c0124da --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-text-to-sql.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56bdcd6dd24f20f0ee57d41f3470f7ade4749b5b511a53d0f4c55fb7b0fd4a5b +size 3664502496 diff --git a/DeepSeek-R1-Distill-Llama-text-to-sql.Q4_K_M.gguf b/DeepSeek-R1-Distill-Llama-text-to-sql.Q4_K_M.gguf new file mode 100644 index 0000000..14797c8 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-text-to-sql.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:871d7ab8c2b8f1858cd203fdc22699da6b79366b1f67daa10587b783e6d622e6 +size 4920737504 diff --git a/DeepSeek-R1-Distill-Llama-text-to-sql.Q4_K_S.gguf b/DeepSeek-R1-Distill-Llama-text-to-sql.Q4_K_S.gguf new file mode 100644 index 0000000..48f3726 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-text-to-sql.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62fa576f30db187b791faa627ecc47050f4ae3d7f4922d7f2127120262991450 +size 4692672224 diff --git a/DeepSeek-R1-Distill-Llama-text-to-sql.Q5_K_M.gguf b/DeepSeek-R1-Distill-Llama-text-to-sql.Q5_K_M.gguf new file mode 100644 index 0000000..989ea2c --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-text-to-sql.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6953193b5864e0a9f3ef04b19335df41bd33ddfb041bc9343d0fdac09f6d58bf +size 5732990688 diff --git a/DeepSeek-R1-Distill-Llama-text-to-sql.Q5_K_S.gguf b/DeepSeek-R1-Distill-Llama-text-to-sql.Q5_K_S.gguf new file mode 100644 index 0000000..519cd1a --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-text-to-sql.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:091acf9ee7f5879200a8aa5a21249d91c6e42bd1d0a65e36ec9d1a4d6267377f +size 5599297248 diff --git a/DeepSeek-R1-Distill-Llama-text-to-sql.Q6_K.gguf b/DeepSeek-R1-Distill-Llama-text-to-sql.Q6_K.gguf new file mode 100644 index 0000000..cb9efc7 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-text-to-sql.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75ae057c8f9198f3825f93c692f0b672398ec6e42bd1cc6600c974c5121dfa69 +size 6596009696 diff --git a/DeepSeek-R1-Distill-Llama-text-to-sql.Q8_0.gguf b/DeepSeek-R1-Distill-Llama-text-to-sql.Q8_0.gguf new file mode 100644 index 0000000..1911d7c --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-text-to-sql.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5014c16a18a425a6a09314482c6bf0e5e43b234bd7c0b7270f7d772e360bf58 +size 8540774112 diff --git a/DeepSeek-R1-Distill-Llama-text-to-sql.f16.gguf b/DeepSeek-R1-Distill-Llama-text-to-sql.f16.gguf new file mode 100644 index 0000000..41418f1 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-text-to-sql.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8f2ad11975ecda79f459d96a658e8bef699645f71291d7ac64f36e3a2993510 +size 16068894432 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0c4f70f --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: natthawadee/DeepSeek-R1-Distill-Llama-text-to-sql +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/natthawadee/DeepSeek-R1-Distill-Llama-text-to-sql + + +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/DeepSeek-R1-Distill-Llama-text-to-sql-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-text-to-sql.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-text-to-sql-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-text-to-sql.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-text-to-sql-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-text-to-sql.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-text-to-sql-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-text-to-sql.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-text-to-sql-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-text-to-sql.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-text-to-sql-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-text-to-sql.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-text-to-sql-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-text-to-sql.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-text-to-sql-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-text-to-sql.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-text-to-sql-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-text-to-sql.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-text-to-sql-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-text-to-sql.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-text-to-sql-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-text-to-sql.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-text-to-sql-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-text-to-sql.f16.gguf) | f16 | 16.2 | 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. + +