commit 7d6efb0519070937e9305f9c17ecf03e55f435a1 Author: ModelHub XC Date: Mon Jul 6 11:07:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-text2SQL-indentacao-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..76bf179 --- /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-indentacao.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-text2SQL-indentacao.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-text2SQL-indentacao.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-text2SQL-indentacao.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-text2SQL-indentacao.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-text2SQL-indentacao.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-text2SQL-indentacao.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-text2SQL-indentacao.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-text2SQL-indentacao.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-text2SQL-indentacao.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-text2SQL-indentacao.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-text2SQL-indentacao.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-text2SQL-indentacao.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-text2SQL-indentacao.IQ4_XS.gguf b/Llama-3.2-text2SQL-indentacao.IQ4_XS.gguf new file mode 100644 index 0000000..7225fd2 --- /dev/null +++ b/Llama-3.2-text2SQL-indentacao.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a853a1f683f0b4c6527f63e3bec8145144807af0838e03b42b4a234a73470d2b +size 748384384 diff --git a/Llama-3.2-text2SQL-indentacao.Q2_K.gguf b/Llama-3.2-text2SQL-indentacao.Q2_K.gguf new file mode 100644 index 0000000..c644cbc --- /dev/null +++ b/Llama-3.2-text2SQL-indentacao.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f883224eccf1d5336ae8dd118e72788b5c80a5de9c9d80dd9b4b6b4b1c212a3 +size 580874368 diff --git a/Llama-3.2-text2SQL-indentacao.Q3_K_L.gguf b/Llama-3.2-text2SQL-indentacao.Q3_K_L.gguf new file mode 100644 index 0000000..a0bc74c --- /dev/null +++ b/Llama-3.2-text2SQL-indentacao.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eeef9ccf746c525863437d09711e2be73f9ecbffbbe5dc16b60276ad7d0654d +size 732524672 diff --git a/Llama-3.2-text2SQL-indentacao.Q3_K_M.gguf b/Llama-3.2-text2SQL-indentacao.Q3_K_M.gguf new file mode 100644 index 0000000..9cd1ada --- /dev/null +++ b/Llama-3.2-text2SQL-indentacao.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fb72adb370dbd268ac091d4fdf4979dec80290c2cc3204056341a2ad6916848 +size 690843776 diff --git a/Llama-3.2-text2SQL-indentacao.Q3_K_S.gguf b/Llama-3.2-text2SQL-indentacao.Q3_K_S.gguf new file mode 100644 index 0000000..687fa17 --- /dev/null +++ b/Llama-3.2-text2SQL-indentacao.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbdf597321c1540133071c7020802469483a792fe186ce18ea473865892263da +size 641691776 diff --git a/Llama-3.2-text2SQL-indentacao.Q4_0_4_4.gguf b/Llama-3.2-text2SQL-indentacao.Q4_0_4_4.gguf new file mode 100644 index 0000000..880e927 --- /dev/null +++ b/Llama-3.2-text2SQL-indentacao.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1b6efab3dd758a9d885d5d9cb014b19adeee95686507b0474eefd45213e7816 +size 770928768 diff --git a/Llama-3.2-text2SQL-indentacao.Q4_K_M.gguf b/Llama-3.2-text2SQL-indentacao.Q4_K_M.gguf new file mode 100644 index 0000000..9ec6ede --- /dev/null +++ b/Llama-3.2-text2SQL-indentacao.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:994df4f35bc391625d23309dc0fed078e3c7b91f63c360054ea33527095fba5a +size 807694464 diff --git a/Llama-3.2-text2SQL-indentacao.Q4_K_S.gguf b/Llama-3.2-text2SQL-indentacao.Q4_K_S.gguf new file mode 100644 index 0000000..16a30a3 --- /dev/null +++ b/Llama-3.2-text2SQL-indentacao.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf07d946569356d0b82e33f4fd92834ad738a088fbd6d0c64826bf0359808889 +size 775647360 diff --git a/Llama-3.2-text2SQL-indentacao.Q5_K_M.gguf b/Llama-3.2-text2SQL-indentacao.Q5_K_M.gguf new file mode 100644 index 0000000..65696fa --- /dev/null +++ b/Llama-3.2-text2SQL-indentacao.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4796e45890c9af928d7e5ae79868c05c3623887a36020c81a888d365d2c2382c +size 911503488 diff --git a/Llama-3.2-text2SQL-indentacao.Q5_K_S.gguf b/Llama-3.2-text2SQL-indentacao.Q5_K_S.gguf new file mode 100644 index 0000000..68f51f2 --- /dev/null +++ b/Llama-3.2-text2SQL-indentacao.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a204946db993c332f9fcfdbc8b20a0da61a69a29b6c0e31a83f29d473927dd17 +size 892563584 diff --git a/Llama-3.2-text2SQL-indentacao.Q6_K.gguf b/Llama-3.2-text2SQL-indentacao.Q6_K.gguf new file mode 100644 index 0000000..f825561 --- /dev/null +++ b/Llama-3.2-text2SQL-indentacao.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26adef392eaf7ca8490c608189063a3de1d4bacc4c8668279ab4c879619b75a1 +size 1021800576 diff --git a/Llama-3.2-text2SQL-indentacao.Q8_0.gguf b/Llama-3.2-text2SQL-indentacao.Q8_0.gguf new file mode 100644 index 0000000..d22c137 --- /dev/null +++ b/Llama-3.2-text2SQL-indentacao.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ea927de9bdc6b3bd761118e8ce4dbfc05d32baeb9d87e266cc5eee2c946f503 +size 1321083008 diff --git a/Llama-3.2-text2SQL-indentacao.f16.gguf b/Llama-3.2-text2SQL-indentacao.f16.gguf new file mode 100644 index 0000000..eaf0590 --- /dev/null +++ b/Llama-3.2-text2SQL-indentacao.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:630ee78fc2c1c0f3a44b84f1dc6ec642004bb48e582d75ac27d6e7ce003bd569 +size 2479595648 diff --git a/README.md b/README.md new file mode 100644 index 0000000..354a020 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: NESPED-GEN/Llama-3.2-text2SQL-indentacao +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/NESPED-GEN/Llama-3.2-text2SQL-indentacao + + +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-indentacao-GGUF/resolve/main/Llama-3.2-text2SQL-indentacao.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-text2SQL-indentacao-GGUF/resolve/main/Llama-3.2-text2SQL-indentacao.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-text2SQL-indentacao-GGUF/resolve/main/Llama-3.2-text2SQL-indentacao.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-text2SQL-indentacao-GGUF/resolve/main/Llama-3.2-text2SQL-indentacao.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-text2SQL-indentacao-GGUF/resolve/main/Llama-3.2-text2SQL-indentacao.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-text2SQL-indentacao-GGUF/resolve/main/Llama-3.2-text2SQL-indentacao.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-indentacao-GGUF/resolve/main/Llama-3.2-text2SQL-indentacao.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-text2SQL-indentacao-GGUF/resolve/main/Llama-3.2-text2SQL-indentacao.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-text2SQL-indentacao-GGUF/resolve/main/Llama-3.2-text2SQL-indentacao.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-text2SQL-indentacao-GGUF/resolve/main/Llama-3.2-text2SQL-indentacao.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-text2SQL-indentacao-GGUF/resolve/main/Llama-3.2-text2SQL-indentacao.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-text2SQL-indentacao-GGUF/resolve/main/Llama-3.2-text2SQL-indentacao.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-text2SQL-indentacao-GGUF/resolve/main/Llama-3.2-text2SQL-indentacao.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. + +