commit 78f3a1fc3840ef27b0c2a5dc4e2eaf8592664419 Author: ModelHub XC Date: Mon Sep 14 02:27:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GraphMind-LLAMA-3.1-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c45d413 --- /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 +GraphMind-LLAMA-3.1-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GraphMind-LLAMA-3.1-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +GraphMind-LLAMA-3.1-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GraphMind-LLAMA-3.1-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GraphMind-LLAMA-3.1-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GraphMind-LLAMA-3.1-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GraphMind-LLAMA-3.1-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GraphMind-LLAMA-3.1-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GraphMind-LLAMA-3.1-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GraphMind-LLAMA-3.1-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GraphMind-LLAMA-3.1-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GraphMind-LLAMA-3.1-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GraphMind-LLAMA-3.1-8B.IQ4_XS.gguf b/GraphMind-LLAMA-3.1-8B.IQ4_XS.gguf new file mode 100644 index 0000000..766467d --- /dev/null +++ b/GraphMind-LLAMA-3.1-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a8d058bad13bdc95487a8a82e3d53c268adfd1cbf44a292556049a0366a2abb +size 4484364256 diff --git a/GraphMind-LLAMA-3.1-8B.Q2_K.gguf b/GraphMind-LLAMA-3.1-8B.Q2_K.gguf new file mode 100644 index 0000000..30cb07d --- /dev/null +++ b/GraphMind-LLAMA-3.1-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd568257fc230e21d7735b33385f766ff6744cce00ee892bc27214103a873b89 +size 3179132896 diff --git a/GraphMind-LLAMA-3.1-8B.Q3_K_L.gguf b/GraphMind-LLAMA-3.1-8B.Q3_K_L.gguf new file mode 100644 index 0000000..0266e58 --- /dev/null +++ b/GraphMind-LLAMA-3.1-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61959ac70784a0245da2c01f3b91c44748d1342c5eb05e11d3649e0c852b6976 +size 4321957856 diff --git a/GraphMind-LLAMA-3.1-8B.Q3_K_M.gguf b/GraphMind-LLAMA-3.1-8B.Q3_K_M.gguf new file mode 100644 index 0000000..8f0c38c --- /dev/null +++ b/GraphMind-LLAMA-3.1-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee56396bec1a374e7e689886f65ba5a42806f54b28d1596e5a493735ff2c0f70 +size 4018919392 diff --git a/GraphMind-LLAMA-3.1-8B.Q3_K_S.gguf b/GraphMind-LLAMA-3.1-8B.Q3_K_S.gguf new file mode 100644 index 0000000..d475557 --- /dev/null +++ b/GraphMind-LLAMA-3.1-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5238eb3d73907f83e4ea0b6fe25b362373ae10e1b059ea43a7cadbfe9406adc +size 3664500704 diff --git a/GraphMind-LLAMA-3.1-8B.Q4_K_M.gguf b/GraphMind-LLAMA-3.1-8B.Q4_K_M.gguf new file mode 100644 index 0000000..c028800 --- /dev/null +++ b/GraphMind-LLAMA-3.1-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3789c251423bf12cfbcc39d4833b9dc5dc7769968db49855255f0889ddcb366 +size 4920735712 diff --git a/GraphMind-LLAMA-3.1-8B.Q4_K_S.gguf b/GraphMind-LLAMA-3.1-8B.Q4_K_S.gguf new file mode 100644 index 0000000..4c687e4 --- /dev/null +++ b/GraphMind-LLAMA-3.1-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81c26f025c307614f1068dd3529290d097c1679afd6fcd83b7c353fcf360af42 +size 4692670432 diff --git a/GraphMind-LLAMA-3.1-8B.Q5_K_M.gguf b/GraphMind-LLAMA-3.1-8B.Q5_K_M.gguf new file mode 100644 index 0000000..0dd0bf3 --- /dev/null +++ b/GraphMind-LLAMA-3.1-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2f0b0bef5f846d237f7e800410f566b5b52c14a0bc6ba92979ce6c500682e3a +size 5732988896 diff --git a/GraphMind-LLAMA-3.1-8B.Q5_K_S.gguf b/GraphMind-LLAMA-3.1-8B.Q5_K_S.gguf new file mode 100644 index 0000000..1e10dd6 --- /dev/null +++ b/GraphMind-LLAMA-3.1-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f52f30a0febeaf133d505b7a2a75b2025cd0ae1048d154fe6d44a11d71a2b13 +size 5599295456 diff --git a/GraphMind-LLAMA-3.1-8B.Q6_K.gguf b/GraphMind-LLAMA-3.1-8B.Q6_K.gguf new file mode 100644 index 0000000..2c2d9fd --- /dev/null +++ b/GraphMind-LLAMA-3.1-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e986f510b1d02939c8e1d37e9a8477da6de8195cce6ad9e646d5b3cf6fc73ae +size 6596007904 diff --git a/GraphMind-LLAMA-3.1-8B.Q8_0.gguf b/GraphMind-LLAMA-3.1-8B.Q8_0.gguf new file mode 100644 index 0000000..4d87ddd --- /dev/null +++ b/GraphMind-LLAMA-3.1-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f03c43d92d3f49fdf894d17b0dbb72979087cd3cad07713afa7c058e04b9e3c1 +size 8540772320 diff --git a/GraphMind-LLAMA-3.1-8B.f16.gguf b/GraphMind-LLAMA-3.1-8B.f16.gguf new file mode 100644 index 0000000..f4713e6 --- /dev/null +++ b/GraphMind-LLAMA-3.1-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c94e7820fba1b0d67816b2b93c668ee1945b482294e8506000cf0640418c398 +size 16068892640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c1ac610 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: HKUST-DSAIL/GraphMind-LLAMA-3.1-8B +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama-factory +- full +- generated_from_trainer +--- +## About + + + + + + + + + +static quants of https://huggingface.co/HKUST-DSAIL/GraphMind-LLAMA-3.1-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GraphMind-LLAMA-3.1-8B-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/GraphMind-LLAMA-3.1-8B-GGUF/resolve/main/GraphMind-LLAMA-3.1-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/GraphMind-LLAMA-3.1-8B-GGUF/resolve/main/GraphMind-LLAMA-3.1-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/GraphMind-LLAMA-3.1-8B-GGUF/resolve/main/GraphMind-LLAMA-3.1-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GraphMind-LLAMA-3.1-8B-GGUF/resolve/main/GraphMind-LLAMA-3.1-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/GraphMind-LLAMA-3.1-8B-GGUF/resolve/main/GraphMind-LLAMA-3.1-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/GraphMind-LLAMA-3.1-8B-GGUF/resolve/main/GraphMind-LLAMA-3.1-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GraphMind-LLAMA-3.1-8B-GGUF/resolve/main/GraphMind-LLAMA-3.1-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GraphMind-LLAMA-3.1-8B-GGUF/resolve/main/GraphMind-LLAMA-3.1-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/GraphMind-LLAMA-3.1-8B-GGUF/resolve/main/GraphMind-LLAMA-3.1-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/GraphMind-LLAMA-3.1-8B-GGUF/resolve/main/GraphMind-LLAMA-3.1-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GraphMind-LLAMA-3.1-8B-GGUF/resolve/main/GraphMind-LLAMA-3.1-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GraphMind-LLAMA-3.1-8B-GGUF/resolve/main/GraphMind-LLAMA-3.1-8B.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. + +