commit 18220e4c288d07e7e90289954f05368832395fc9 Author: ModelHub XC Date: Wed Apr 29 02:55:07 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3.1-8B-StructuredIE-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6e695bb --- /dev/null +++ b/.gitattributes @@ -0,0 +1,44 @@ +*.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-3.1-8B-StructuredIE-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8B-StructuredIE-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8B-StructuredIE-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8B-StructuredIE-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8B-StructuredIE-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8B-StructuredIE-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8B-StructuredIE-v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8B-StructuredIE-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8B-StructuredIE-v2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9233952 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: tu-ericngo/llama-3.1-8B-StructuredIE-v2 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +--- +## About + + + + + + + + + +static quants of https://huggingface.co/tu-ericngo/llama-3.1-8B-StructuredIE-v2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama-3.1-8B-StructuredIE-v2-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/llama-3.1-8B-StructuredIE-v2-GGUF/resolve/main/llama-3.1-8B-StructuredIE-v2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8B-StructuredIE-v2-GGUF/resolve/main/llama-3.1-8B-StructuredIE-v2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8B-StructuredIE-v2-GGUF/resolve/main/llama-3.1-8B-StructuredIE-v2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8B-StructuredIE-v2-GGUF/resolve/main/llama-3.1-8B-StructuredIE-v2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8B-StructuredIE-v2-GGUF/resolve/main/llama-3.1-8B-StructuredIE-v2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8B-StructuredIE-v2-GGUF/resolve/main/llama-3.1-8B-StructuredIE-v2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8B-StructuredIE-v2-GGUF/resolve/main/llama-3.1-8B-StructuredIE-v2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8B-StructuredIE-v2-GGUF/resolve/main/llama-3.1-8B-StructuredIE-v2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8B-StructuredIE-v2-GGUF/resolve/main/llama-3.1-8B-StructuredIE-v2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8B-StructuredIE-v2-GGUF/resolve/main/llama-3.1-8B-StructuredIE-v2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8B-StructuredIE-v2-GGUF/resolve/main/llama-3.1-8B-StructuredIE-v2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8B-StructuredIE-v2-GGUF/resolve/main/llama-3.1-8B-StructuredIE-v2.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. + + diff --git a/llama-3.1-8B-StructuredIE-v2.IQ4_XS.gguf b/llama-3.1-8B-StructuredIE-v2.IQ4_XS.gguf new file mode 100644 index 0000000..8fd7920 --- /dev/null +++ b/llama-3.1-8B-StructuredIE-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7c61d7ae36234bc44ec8b4f3792e6fb11bc97886568123b72530bf3fd03d7f0 +size 4484368416 diff --git a/llama-3.1-8B-StructuredIE-v2.Q2_K.gguf b/llama-3.1-8B-StructuredIE-v2.Q2_K.gguf new file mode 100644 index 0000000..3b80c28 --- /dev/null +++ b/llama-3.1-8B-StructuredIE-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6f3f05430561d1dc2ccdf7ee8605744ab14eb0d9eab808d85793960a5ead703 +size 3179137056 diff --git a/llama-3.1-8B-StructuredIE-v2.Q3_K_L.gguf b/llama-3.1-8B-StructuredIE-v2.Q3_K_L.gguf new file mode 100644 index 0000000..ba24bca --- /dev/null +++ b/llama-3.1-8B-StructuredIE-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55a8704b835606c4eb66092034616cb848849fb1cc1628e3a11e066ebc4e8a54 +size 4321962016 diff --git a/llama-3.1-8B-StructuredIE-v2.Q3_K_M.gguf b/llama-3.1-8B-StructuredIE-v2.Q3_K_M.gguf new file mode 100644 index 0000000..2df446c --- /dev/null +++ b/llama-3.1-8B-StructuredIE-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6c75a5814f43c29519ca3894615df1c1f2214fdee994b3dac8d2a5daa1a62b1 +size 4018923552 diff --git a/llama-3.1-8B-StructuredIE-v2.Q3_K_S.gguf b/llama-3.1-8B-StructuredIE-v2.Q3_K_S.gguf new file mode 100644 index 0000000..f6f00d3 --- /dev/null +++ b/llama-3.1-8B-StructuredIE-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6737a6c2f2856ce753b587b44223c5b78814d9b96845451df6fa704b53bd1f39 +size 3664504864 diff --git a/llama-3.1-8B-StructuredIE-v2.Q4_K_M.gguf b/llama-3.1-8B-StructuredIE-v2.Q4_K_M.gguf new file mode 100644 index 0000000..f6291a9 --- /dev/null +++ b/llama-3.1-8B-StructuredIE-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72e7d80783a4a6bccda104182ccca14a32a48f49f749a49c19a541c58a68e771 +size 4920739872 diff --git a/llama-3.1-8B-StructuredIE-v2.Q4_K_S.gguf b/llama-3.1-8B-StructuredIE-v2.Q4_K_S.gguf new file mode 100644 index 0000000..9db2d4b --- /dev/null +++ b/llama-3.1-8B-StructuredIE-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79509851cf0703ef3fe715b75ad9374da5a03fee9400c23ec8d134a42efbf19b +size 4692674592 diff --git a/llama-3.1-8B-StructuredIE-v2.Q5_K_M.gguf b/llama-3.1-8B-StructuredIE-v2.Q5_K_M.gguf new file mode 100644 index 0000000..ed3aa54 --- /dev/null +++ b/llama-3.1-8B-StructuredIE-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:356e033df5963b87e4833f57de770971a7cdcb1a41fef73c75f17c4a2660af35 +size 5732993056 diff --git a/llama-3.1-8B-StructuredIE-v2.Q5_K_S.gguf b/llama-3.1-8B-StructuredIE-v2.Q5_K_S.gguf new file mode 100644 index 0000000..98fb65b --- /dev/null +++ b/llama-3.1-8B-StructuredIE-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ddba1f1b413cf62d5cd3df1f0a9b1b35f0a42c49015aae60785fcdfe8477bee +size 5599299616 diff --git a/llama-3.1-8B-StructuredIE-v2.Q6_K.gguf b/llama-3.1-8B-StructuredIE-v2.Q6_K.gguf new file mode 100644 index 0000000..07a4433 --- /dev/null +++ b/llama-3.1-8B-StructuredIE-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c1d88e36ae623cb504e2ec8649a302d3993584005ef7548e864439a9c0014de +size 6596012064 diff --git a/llama-3.1-8B-StructuredIE-v2.Q8_0.gguf b/llama-3.1-8B-StructuredIE-v2.Q8_0.gguf new file mode 100644 index 0000000..8e1b2f3 --- /dev/null +++ b/llama-3.1-8B-StructuredIE-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:438a4b558f5f0baa3e54c72e156959b2b77b26151af8003ea168e97e013541a0 +size 8540776480 diff --git a/llama-3.1-8B-StructuredIE-v2.f16.gguf b/llama-3.1-8B-StructuredIE-v2.f16.gguf new file mode 100644 index 0000000..dfa3261 --- /dev/null +++ b/llama-3.1-8B-StructuredIE-v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91f3bf3ff8995e9921ead735e16918cc9d4a9931254a11095188e6ad9e3b3fc1 +size 16068896800