From d2955f623b9f2e4142bd6fc94981a4fee07909c2 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 19 Oct 2026 10:59:18 +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/Llama-3.1-8B-Instruct-AgenticLU-GGUF Source: Original Platform --- .gitattributes | 47 +++++++++++++++ Llama-3.1-8B-Instruct-AgenticLU.IQ4_XS.gguf | 3 + Llama-3.1-8B-Instruct-AgenticLU.Q2_K.gguf | 3 + Llama-3.1-8B-Instruct-AgenticLU.Q3_K_L.gguf | 3 + Llama-3.1-8B-Instruct-AgenticLU.Q3_K_M.gguf | 3 + Llama-3.1-8B-Instruct-AgenticLU.Q3_K_S.gguf | 3 + Llama-3.1-8B-Instruct-AgenticLU.Q4_K_M.gguf | 3 + Llama-3.1-8B-Instruct-AgenticLU.Q4_K_S.gguf | 3 + Llama-3.1-8B-Instruct-AgenticLU.Q5_K_M.gguf | 3 + Llama-3.1-8B-Instruct-AgenticLU.Q5_K_S.gguf | 3 + Llama-3.1-8B-Instruct-AgenticLU.Q6_K.gguf | 3 + Llama-3.1-8B-Instruct-AgenticLU.Q8_0.gguf | 3 + Llama-3.1-8B-Instruct-AgenticLU.f16.gguf | 3 + README.md | 66 +++++++++++++++++++++ 14 files changed, 149 insertions(+) create mode 100644 .gitattributes create mode 100644 Llama-3.1-8B-Instruct-AgenticLU.IQ4_XS.gguf create mode 100644 Llama-3.1-8B-Instruct-AgenticLU.Q2_K.gguf create mode 100644 Llama-3.1-8B-Instruct-AgenticLU.Q3_K_L.gguf create mode 100644 Llama-3.1-8B-Instruct-AgenticLU.Q3_K_M.gguf create mode 100644 Llama-3.1-8B-Instruct-AgenticLU.Q3_K_S.gguf create mode 100644 Llama-3.1-8B-Instruct-AgenticLU.Q4_K_M.gguf create mode 100644 Llama-3.1-8B-Instruct-AgenticLU.Q4_K_S.gguf create mode 100644 Llama-3.1-8B-Instruct-AgenticLU.Q5_K_M.gguf create mode 100644 Llama-3.1-8B-Instruct-AgenticLU.Q5_K_S.gguf create mode 100644 Llama-3.1-8B-Instruct-AgenticLU.Q6_K.gguf create mode 100644 Llama-3.1-8B-Instruct-AgenticLU.Q8_0.gguf create mode 100644 Llama-3.1-8B-Instruct-AgenticLU.f16.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..adaa03d --- /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 +Llama-3.1-8B-Instruct-AgenticLU.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-AgenticLU.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-AgenticLU.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-AgenticLU.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-AgenticLU.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-AgenticLU.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-AgenticLU.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-AgenticLU.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-AgenticLU.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-AgenticLU.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-AgenticLU.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-AgenticLU.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-Instruct-AgenticLU.IQ4_XS.gguf b/Llama-3.1-8B-Instruct-AgenticLU.IQ4_XS.gguf new file mode 100644 index 0000000..48c593c --- /dev/null +++ b/Llama-3.1-8B-Instruct-AgenticLU.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:377000c8c94119de39569c8815530a53f17bc65a48bfd861a412738b0e54ceac +size 4484367808 diff --git a/Llama-3.1-8B-Instruct-AgenticLU.Q2_K.gguf b/Llama-3.1-8B-Instruct-AgenticLU.Q2_K.gguf new file mode 100644 index 0000000..509228f --- /dev/null +++ b/Llama-3.1-8B-Instruct-AgenticLU.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7961bea161d02ed600d0775c43290bc597a2e6d10359936c5162485b9a6d9dc0 +size 3179136448 diff --git a/Llama-3.1-8B-Instruct-AgenticLU.Q3_K_L.gguf b/Llama-3.1-8B-Instruct-AgenticLU.Q3_K_L.gguf new file mode 100644 index 0000000..fa4c344 --- /dev/null +++ b/Llama-3.1-8B-Instruct-AgenticLU.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30d983eb21e65b93d29e94a75c8c1e4edfcbaddf4d4163c1f090b980e5786856 +size 4321961408 diff --git a/Llama-3.1-8B-Instruct-AgenticLU.Q3_K_M.gguf b/Llama-3.1-8B-Instruct-AgenticLU.Q3_K_M.gguf new file mode 100644 index 0000000..209741f --- /dev/null +++ b/Llama-3.1-8B-Instruct-AgenticLU.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:661cd172f32ce70e41b735895d39069cb1d2dcdf67645b43cb47e858bec133b9 +size 4018922944 diff --git a/Llama-3.1-8B-Instruct-AgenticLU.Q3_K_S.gguf b/Llama-3.1-8B-Instruct-AgenticLU.Q3_K_S.gguf new file mode 100644 index 0000000..ac49b2c --- /dev/null +++ b/Llama-3.1-8B-Instruct-AgenticLU.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77f9d568363542539730e62be5e6efd28e287933be009894a079839d43b585ed +size 3664504256 diff --git a/Llama-3.1-8B-Instruct-AgenticLU.Q4_K_M.gguf b/Llama-3.1-8B-Instruct-AgenticLU.Q4_K_M.gguf new file mode 100644 index 0000000..f8a1c0d --- /dev/null +++ b/Llama-3.1-8B-Instruct-AgenticLU.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33ee363ca7d24b364c41e0c2c277bfe54154e12d2d1fd76120cbd3a86d45196d +size 4920739264 diff --git a/Llama-3.1-8B-Instruct-AgenticLU.Q4_K_S.gguf b/Llama-3.1-8B-Instruct-AgenticLU.Q4_K_S.gguf new file mode 100644 index 0000000..6cd28ab --- /dev/null +++ b/Llama-3.1-8B-Instruct-AgenticLU.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a092e258c2a7fe8b1c82060dd578631ff4ede3ed4ae83031d8a15fb3dd410dbe +size 4692673984 diff --git a/Llama-3.1-8B-Instruct-AgenticLU.Q5_K_M.gguf b/Llama-3.1-8B-Instruct-AgenticLU.Q5_K_M.gguf new file mode 100644 index 0000000..bda88f2 --- /dev/null +++ b/Llama-3.1-8B-Instruct-AgenticLU.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4db333cecc2db148eb9ba6242ca69e1772f03317166141c1886d478c862bf0ae +size 5732992448 diff --git a/Llama-3.1-8B-Instruct-AgenticLU.Q5_K_S.gguf b/Llama-3.1-8B-Instruct-AgenticLU.Q5_K_S.gguf new file mode 100644 index 0000000..a1ca445 --- /dev/null +++ b/Llama-3.1-8B-Instruct-AgenticLU.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34bd27e65dbb0073af57b81ca4cbcb00f8b54422db869a0cbf29e8098c3d3864 +size 5599299008 diff --git a/Llama-3.1-8B-Instruct-AgenticLU.Q6_K.gguf b/Llama-3.1-8B-Instruct-AgenticLU.Q6_K.gguf new file mode 100644 index 0000000..b3fff47 --- /dev/null +++ b/Llama-3.1-8B-Instruct-AgenticLU.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41ba768c9a64729c5c16ec447726cd6a068fcfdc0206647dfd745579a9056cac +size 6596011456 diff --git a/Llama-3.1-8B-Instruct-AgenticLU.Q8_0.gguf b/Llama-3.1-8B-Instruct-AgenticLU.Q8_0.gguf new file mode 100644 index 0000000..299aa08 --- /dev/null +++ b/Llama-3.1-8B-Instruct-AgenticLU.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6fd62856bdfb3545ade2f6ee7b7d9f09fdf328985f97b8ec9d7cc6609bffceb +size 8540775872 diff --git a/Llama-3.1-8B-Instruct-AgenticLU.f16.gguf b/Llama-3.1-8B-Instruct-AgenticLU.f16.gguf new file mode 100644 index 0000000..509f060 --- /dev/null +++ b/Llama-3.1-8B-Instruct-AgenticLU.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7444d30a07bc9af381b16abbcc532095d9017d4560f8300d41d0c4c78ab80b15 +size 16068896192 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8ef617a --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: yzhuang/Llama-3.1-8B-Instruct-AgenticLU +datasets: +- yzhuang/Agentic-Long-Context-Understanding-QA +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/yzhuang/Llama-3.1-8B-Instruct-AgenticLU + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-AgenticLU-i1-GGUF +## 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-Instruct-AgenticLU-GGUF/resolve/main/Llama-3.1-8B-Instruct-AgenticLU.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-AgenticLU-GGUF/resolve/main/Llama-3.1-8B-Instruct-AgenticLU.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-AgenticLU-GGUF/resolve/main/Llama-3.1-8B-Instruct-AgenticLU.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-AgenticLU-GGUF/resolve/main/Llama-3.1-8B-Instruct-AgenticLU.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-AgenticLU-GGUF/resolve/main/Llama-3.1-8B-Instruct-AgenticLU.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-AgenticLU-GGUF/resolve/main/Llama-3.1-8B-Instruct-AgenticLU.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-AgenticLU-GGUF/resolve/main/Llama-3.1-8B-Instruct-AgenticLU.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-AgenticLU-GGUF/resolve/main/Llama-3.1-8B-Instruct-AgenticLU.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-AgenticLU-GGUF/resolve/main/Llama-3.1-8B-Instruct-AgenticLU.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-AgenticLU-GGUF/resolve/main/Llama-3.1-8B-Instruct-AgenticLU.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-AgenticLU-GGUF/resolve/main/Llama-3.1-8B-Instruct-AgenticLU.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-AgenticLU-GGUF/resolve/main/Llama-3.1-8B-Instruct-AgenticLU.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. + +