commit ab5a178e2f3a044e39dcab7013a9da5e8d92f778 Author: ModelHub XC Date: Wed Aug 5 16:47:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLama-Text2SQL-v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4caeb53 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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-Text2SQL-v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLama-Text2SQL-v1.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +LLama-Text2SQL-v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLama-Text2SQL-v1.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +LLama-Text2SQL-v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLama-Text2SQL-v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLama-Text2SQL-v1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLama-Text2SQL-v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLama-Text2SQL-v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLama-Text2SQL-v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLama-Text2SQL-v1.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLama-Text2SQL-v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLama-Text2SQL-v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLama-Text2SQL-v1.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +LLama-Text2SQL-v1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLama-Text2SQL-v1.IQ3_M.gguf b/LLama-Text2SQL-v1.IQ3_M.gguf new file mode 100644 index 0000000..898dd27 --- /dev/null +++ b/LLama-Text2SQL-v1.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f93f0fd419373a1dc5586c6317c7436c4febdea0d72548fcac9d476b1a5b16a +size 3115003936 diff --git a/LLama-Text2SQL-v1.IQ3_S.gguf b/LLama-Text2SQL-v1.IQ3_S.gguf new file mode 100644 index 0000000..0adb03b --- /dev/null +++ b/LLama-Text2SQL-v1.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79ca33ab3a73d61c97b4df95b8ec1080f40e3ef431ceb4c335fad96d9b1cd960 +size 2948444192 diff --git a/LLama-Text2SQL-v1.IQ3_XS.gguf b/LLama-Text2SQL-v1.IQ3_XS.gguf new file mode 100644 index 0000000..61b2c6c --- /dev/null +++ b/LLama-Text2SQL-v1.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39c106328ab18592bf9852770638577b687d39d015c554c92f793a1f02d4d7c6 +size 2796662816 diff --git a/LLama-Text2SQL-v1.IQ4_XS.gguf b/LLama-Text2SQL-v1.IQ4_XS.gguf new file mode 100644 index 0000000..fab6def --- /dev/null +++ b/LLama-Text2SQL-v1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2da61afff47d192c603cc278c74ea92cf82ff9b50f2466bc01ff01b501298b20 +size 3647667200 diff --git a/LLama-Text2SQL-v1.Q2_K.gguf b/LLama-Text2SQL-v1.Q2_K.gguf new file mode 100644 index 0000000..a05ade0 --- /dev/null +++ b/LLama-Text2SQL-v1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:745507e8835f10d06e5ccf4de3dd365622198132201ca3c19ba2f9373272923c +size 2532992064 diff --git a/LLama-Text2SQL-v1.Q3_K_L.gguf b/LLama-Text2SQL-v1.Q3_K_L.gguf new file mode 100644 index 0000000..dc9cf90 --- /dev/null +++ b/LLama-Text2SQL-v1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e4c942e0436a1b82e25922625b63509c5eed15ac7add99f1a4108c2030292bd +size 3597250592 diff --git a/LLama-Text2SQL-v1.Q3_K_M.gguf b/LLama-Text2SQL-v1.Q3_K_M.gguf new file mode 100644 index 0000000..0143c1e --- /dev/null +++ b/LLama-Text2SQL-v1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f91687318ea4abe0e870456c78f622c4cc3517879fb7a4e7b3aa1d7daa8f363e +size 3298144288 diff --git a/LLama-Text2SQL-v1.Q3_K_S.gguf b/LLama-Text2SQL-v1.Q3_K_S.gguf new file mode 100644 index 0000000..744f573 --- /dev/null +++ b/LLama-Text2SQL-v1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a06c4579232fa7d02b520f5d4e67b72eee46ab47486ef4bd0aab72e7659c78e7 +size 2948444192 diff --git a/LLama-Text2SQL-v1.Q4_K_M.gguf b/LLama-Text2SQL-v1.Q4_K_M.gguf new file mode 100644 index 0000000..245bd62 --- /dev/null +++ b/LLama-Text2SQL-v1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fbb23759d062f2259c8fe28181198ded696a3c34ca82973012cd267ea264a11 +size 4081158528 diff --git a/LLama-Text2SQL-v1.Q4_K_S.gguf b/LLama-Text2SQL-v1.Q4_K_S.gguf new file mode 100644 index 0000000..33bf1f3 --- /dev/null +++ b/LLama-Text2SQL-v1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4a7bbc1ed90f70f608f3237df1d5bf6e2262b00608f8485f1a7466587b954cf +size 3856894336 diff --git a/LLama-Text2SQL-v1.Q5_K_M.gguf b/LLama-Text2SQL-v1.Q5_K_M.gguf new file mode 100644 index 0000000..3f7a041 --- /dev/null +++ b/LLama-Text2SQL-v1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c82c7c3d75fd38d3769cf83489271c8fca5125ecff9e944030dd9e937148ecf8 +size 4783325056 diff --git a/LLama-Text2SQL-v1.Q5_K_S.gguf b/LLama-Text2SQL-v1.Q5_K_S.gguf new file mode 100644 index 0000000..d4692be --- /dev/null +++ b/LLama-Text2SQL-v1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:899684157378e3735fc95624bca166dd89d3ef800fc388d7adb3f1a8aeccf93b +size 4651859840 diff --git a/LLama-Text2SQL-v1.Q6_K.gguf b/LLama-Text2SQL-v1.Q6_K.gguf new file mode 100644 index 0000000..d4535db --- /dev/null +++ b/LLama-Text2SQL-v1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ecb7aae36eea01bafad8d60cec96509505850c9b8bf8fed022bfb8af9886f3a +size 5529376992 diff --git a/LLama-Text2SQL-v1.Q8_0.gguf b/LLama-Text2SQL-v1.Q8_0.gguf new file mode 100644 index 0000000..c692e5b --- /dev/null +++ b/LLama-Text2SQL-v1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a18041c9c1e157bbfff97882e21876d7064f4dc720f11366f8168328ec72b90 +size 7161326112 diff --git a/LLama-Text2SQL-v1.f16.gguf b/LLama-Text2SQL-v1.f16.gguf new file mode 100644 index 0000000..987cc88 --- /dev/null +++ b/LLama-Text2SQL-v1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0af7263adb0f55ad84a6a002e8878749eeda2aab91d9f3ad0ae1ea6016f8083a +size 13478548512 diff --git a/README.md b/README.md new file mode 100644 index 0000000..530d3c2 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: Jasaa/LLama-Text2SQL-v1 +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Jasaa/LLama-Text2SQL-v1 + + +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-Text2SQL-v1-GGUF/resolve/main/LLama-Text2SQL-v1.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLama-Text2SQL-v1-GGUF/resolve/main/LLama-Text2SQL-v1.IQ3_XS.gguf) | IQ3_XS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/LLama-Text2SQL-v1-GGUF/resolve/main/LLama-Text2SQL-v1.IQ3_S.gguf) | IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/LLama-Text2SQL-v1-GGUF/resolve/main/LLama-Text2SQL-v1.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/LLama-Text2SQL-v1-GGUF/resolve/main/LLama-Text2SQL-v1.IQ3_M.gguf) | IQ3_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/LLama-Text2SQL-v1-GGUF/resolve/main/LLama-Text2SQL-v1.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLama-Text2SQL-v1-GGUF/resolve/main/LLama-Text2SQL-v1.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLama-Text2SQL-v1-GGUF/resolve/main/LLama-Text2SQL-v1.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLama-Text2SQL-v1-GGUF/resolve/main/LLama-Text2SQL-v1.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLama-Text2SQL-v1-GGUF/resolve/main/LLama-Text2SQL-v1.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLama-Text2SQL-v1-GGUF/resolve/main/LLama-Text2SQL-v1.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLama-Text2SQL-v1-GGUF/resolve/main/LLama-Text2SQL-v1.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/LLama-Text2SQL-v1-GGUF/resolve/main/LLama-Text2SQL-v1.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLama-Text2SQL-v1-GGUF/resolve/main/LLama-Text2SQL-v1.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLama-Text2SQL-v1-GGUF/resolve/main/LLama-Text2SQL-v1.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. + +