From 816456e8c4f7e32ca564c5a919cbfa144d06f640 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 6 Jun 2026 00:28:16 +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/intent-aware-lfqa-llama3-8b-intent-explicit-GGUF Source: Original Platform --- .gitattributes | 47 ++++++++++++ README.md | 71 +++++++++++++++++++ ...lfqa-llama3-8b-intent-explicit.IQ4_XS.gguf | 3 + ...e-lfqa-llama3-8b-intent-explicit.Q2_K.gguf | 3 + ...lfqa-llama3-8b-intent-explicit.Q3_K_L.gguf | 3 + ...lfqa-llama3-8b-intent-explicit.Q3_K_M.gguf | 3 + ...lfqa-llama3-8b-intent-explicit.Q3_K_S.gguf | 3 + ...lfqa-llama3-8b-intent-explicit.Q4_K_M.gguf | 3 + ...lfqa-llama3-8b-intent-explicit.Q4_K_S.gguf | 3 + ...lfqa-llama3-8b-intent-explicit.Q5_K_M.gguf | 3 + ...lfqa-llama3-8b-intent-explicit.Q5_K_S.gguf | 3 + ...e-lfqa-llama3-8b-intent-explicit.Q6_K.gguf | 3 + ...e-lfqa-llama3-8b-intent-explicit.Q8_0.gguf | 3 + ...re-lfqa-llama3-8b-intent-explicit.f16.gguf | 3 + 14 files changed, 154 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 intent-aware-lfqa-llama3-8b-intent-explicit.IQ4_XS.gguf create mode 100644 intent-aware-lfqa-llama3-8b-intent-explicit.Q2_K.gguf create mode 100644 intent-aware-lfqa-llama3-8b-intent-explicit.Q3_K_L.gguf create mode 100644 intent-aware-lfqa-llama3-8b-intent-explicit.Q3_K_M.gguf create mode 100644 intent-aware-lfqa-llama3-8b-intent-explicit.Q3_K_S.gguf create mode 100644 intent-aware-lfqa-llama3-8b-intent-explicit.Q4_K_M.gguf create mode 100644 intent-aware-lfqa-llama3-8b-intent-explicit.Q4_K_S.gguf create mode 100644 intent-aware-lfqa-llama3-8b-intent-explicit.Q5_K_M.gguf create mode 100644 intent-aware-lfqa-llama3-8b-intent-explicit.Q5_K_S.gguf create mode 100644 intent-aware-lfqa-llama3-8b-intent-explicit.Q6_K.gguf create mode 100644 intent-aware-lfqa-llama3-8b-intent-explicit.Q8_0.gguf create mode 100644 intent-aware-lfqa-llama3-8b-intent-explicit.f16.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..09c1a2c --- /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 +intent-aware-lfqa-llama3-8b-intent-explicit.f16.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-llama3-8b-intent-explicit.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-llama3-8b-intent-explicit.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-llama3-8b-intent-explicit.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-llama3-8b-intent-explicit.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-llama3-8b-intent-explicit.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-llama3-8b-intent-explicit.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-llama3-8b-intent-explicit.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-llama3-8b-intent-explicit.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-llama3-8b-intent-explicit.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-llama3-8b-intent-explicit.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-llama3-8b-intent-explicit.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f15bf76 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: allenai/intent-aware-lfqa-llama3-8b-intent-explicit +language: en +library_name: transformers +license: odc-by +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/allenai/intent-aware-lfqa-llama3-8b-intent-explicit + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#intent-aware-lfqa-llama3-8b-intent-explicit-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/intent-aware-lfqa-llama3-8b-intent-explicit-GGUF/resolve/main/intent-aware-lfqa-llama3-8b-intent-explicit.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-llama3-8b-intent-explicit-GGUF/resolve/main/intent-aware-lfqa-llama3-8b-intent-explicit.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-llama3-8b-intent-explicit-GGUF/resolve/main/intent-aware-lfqa-llama3-8b-intent-explicit.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-llama3-8b-intent-explicit-GGUF/resolve/main/intent-aware-lfqa-llama3-8b-intent-explicit.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-llama3-8b-intent-explicit-GGUF/resolve/main/intent-aware-lfqa-llama3-8b-intent-explicit.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-llama3-8b-intent-explicit-GGUF/resolve/main/intent-aware-lfqa-llama3-8b-intent-explicit.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-llama3-8b-intent-explicit-GGUF/resolve/main/intent-aware-lfqa-llama3-8b-intent-explicit.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-llama3-8b-intent-explicit-GGUF/resolve/main/intent-aware-lfqa-llama3-8b-intent-explicit.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-llama3-8b-intent-explicit-GGUF/resolve/main/intent-aware-lfqa-llama3-8b-intent-explicit.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-llama3-8b-intent-explicit-GGUF/resolve/main/intent-aware-lfqa-llama3-8b-intent-explicit.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-llama3-8b-intent-explicit-GGUF/resolve/main/intent-aware-lfqa-llama3-8b-intent-explicit.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-llama3-8b-intent-explicit-GGUF/resolve/main/intent-aware-lfqa-llama3-8b-intent-explicit.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/intent-aware-lfqa-llama3-8b-intent-explicit.IQ4_XS.gguf b/intent-aware-lfqa-llama3-8b-intent-explicit.IQ4_XS.gguf new file mode 100644 index 0000000..82733e9 --- /dev/null +++ b/intent-aware-lfqa-llama3-8b-intent-explicit.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35f7fdc201525c5de101b920757148e58a895b66db7d83cd0e7275cf95d22330 +size 4484408736 diff --git a/intent-aware-lfqa-llama3-8b-intent-explicit.Q2_K.gguf b/intent-aware-lfqa-llama3-8b-intent-explicit.Q2_K.gguf new file mode 100644 index 0000000..cefb04d --- /dev/null +++ b/intent-aware-lfqa-llama3-8b-intent-explicit.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f834f14b71b6367ef1761aee8a83f852f1919f350414c5b4d88a670a7efd4ce +size 3179170720 diff --git a/intent-aware-lfqa-llama3-8b-intent-explicit.Q3_K_L.gguf b/intent-aware-lfqa-llama3-8b-intent-explicit.Q3_K_L.gguf new file mode 100644 index 0000000..efbc9fd --- /dev/null +++ b/intent-aware-lfqa-llama3-8b-intent-explicit.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e76e53d7692df7986c76ccc0ad91351170ddeb6c871ac057eafed6eb3426990f +size 4321999008 diff --git a/intent-aware-lfqa-llama3-8b-intent-explicit.Q3_K_M.gguf b/intent-aware-lfqa-llama3-8b-intent-explicit.Q3_K_M.gguf new file mode 100644 index 0000000..3dc140e --- /dev/null +++ b/intent-aware-lfqa-llama3-8b-intent-explicit.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86dcb9cd9c2e12f40a7d5ce61adb5139a141b8d9ea015486a25fa62a3b29d4cb +size 4018960544 diff --git a/intent-aware-lfqa-llama3-8b-intent-explicit.Q3_K_S.gguf b/intent-aware-lfqa-llama3-8b-intent-explicit.Q3_K_S.gguf new file mode 100644 index 0000000..87f3bdc --- /dev/null +++ b/intent-aware-lfqa-llama3-8b-intent-explicit.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87bbc6b1c15bf9d0f99838dee716f9a36fa8fe77f2396ba866a1b217ea2eff5b +size 3664541856 diff --git a/intent-aware-lfqa-llama3-8b-intent-explicit.Q4_K_M.gguf b/intent-aware-lfqa-llama3-8b-intent-explicit.Q4_K_M.gguf new file mode 100644 index 0000000..bf9595b --- /dev/null +++ b/intent-aware-lfqa-llama3-8b-intent-explicit.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eed66f91fecd7c6b3ebab086c17dba2d80182bb3268df639feac32af734aac31 +size 4920781216 diff --git a/intent-aware-lfqa-llama3-8b-intent-explicit.Q4_K_S.gguf b/intent-aware-lfqa-llama3-8b-intent-explicit.Q4_K_S.gguf new file mode 100644 index 0000000..e1e1db7 --- /dev/null +++ b/intent-aware-lfqa-llama3-8b-intent-explicit.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ceb7ddf8fa01b658ba71da022e31f2e02f50484f53adc6b539b63c0b0397e8ca +size 4692715936 diff --git a/intent-aware-lfqa-llama3-8b-intent-explicit.Q5_K_M.gguf b/intent-aware-lfqa-llama3-8b-intent-explicit.Q5_K_M.gguf new file mode 100644 index 0000000..0fb8cd3 --- /dev/null +++ b/intent-aware-lfqa-llama3-8b-intent-explicit.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8085fafa3e5005121b6bbf034200e759764f40e881533c7146de67f297151d74 +size 5733038496 diff --git a/intent-aware-lfqa-llama3-8b-intent-explicit.Q5_K_S.gguf b/intent-aware-lfqa-llama3-8b-intent-explicit.Q5_K_S.gguf new file mode 100644 index 0000000..737c974 --- /dev/null +++ b/intent-aware-lfqa-llama3-8b-intent-explicit.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86f0d692bb5fcaa4e2ad25209fa79462558fae1eb0e32ef4b12584869328a402 +size 5599345056 diff --git a/intent-aware-lfqa-llama3-8b-intent-explicit.Q6_K.gguf b/intent-aware-lfqa-llama3-8b-intent-explicit.Q6_K.gguf new file mode 100644 index 0000000..7f0497f --- /dev/null +++ b/intent-aware-lfqa-llama3-8b-intent-explicit.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd1485898e3f7e09d8442e3c4a92f7e6c2e508df9df8882164b5b07391733774 +size 6596061856 diff --git a/intent-aware-lfqa-llama3-8b-intent-explicit.Q8_0.gguf b/intent-aware-lfqa-llama3-8b-intent-explicit.Q8_0.gguf new file mode 100644 index 0000000..a4c7936 --- /dev/null +++ b/intent-aware-lfqa-llama3-8b-intent-explicit.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2002a172e5f1a0bf480adc614ed7743da276256b1da0cb47ee68f5b9148268d2 +size 8540842144 diff --git a/intent-aware-lfqa-llama3-8b-intent-explicit.f16.gguf b/intent-aware-lfqa-llama3-8b-intent-explicit.f16.gguf new file mode 100644 index 0000000..917717b --- /dev/null +++ b/intent-aware-lfqa-llama3-8b-intent-explicit.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:269af6b18f4b231ec50ddd27d330f7f3cab7691f70c1528c9df27b3347e5d0de +size 16069023904