commit d8a289bbbc5f396656937b0b2e31efac139e8c70 Author: ModelHub XC Date: Sun Aug 30 21:06:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ToolGen-Hierarchical-Llama-3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d3224d8 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +ToolGen-Hierarchical-Llama-3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ToolGen-Hierarchical-Llama-3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ToolGen-Hierarchical-Llama-3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +ToolGen-Hierarchical-Llama-3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ToolGen-Hierarchical-Llama-3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ToolGen-Hierarchical-Llama-3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ToolGen-Hierarchical-Llama-3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ToolGen-Hierarchical-Llama-3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ToolGen-Hierarchical-Llama-3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ToolGen-Hierarchical-Llama-3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ToolGen-Hierarchical-Llama-3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..62a5c27 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: reasonwang/ToolGen-Hierarchical-Llama-3-8B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/reasonwang/ToolGen-Hierarchical-Llama-3-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ToolGen-Hierarchical-Llama-3-8B-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/ToolGen-Hierarchical-Llama-3-8B-GGUF/resolve/main/ToolGen-Hierarchical-Llama-3-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/ToolGen-Hierarchical-Llama-3-8B-GGUF/resolve/main/ToolGen-Hierarchical-Llama-3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/ToolGen-Hierarchical-Llama-3-8B-GGUF/resolve/main/ToolGen-Hierarchical-Llama-3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ToolGen-Hierarchical-Llama-3-8B-GGUF/resolve/main/ToolGen-Hierarchical-Llama-3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/ToolGen-Hierarchical-Llama-3-8B-GGUF/resolve/main/ToolGen-Hierarchical-Llama-3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/ToolGen-Hierarchical-Llama-3-8B-GGUF/resolve/main/ToolGen-Hierarchical-Llama-3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ToolGen-Hierarchical-Llama-3-8B-GGUF/resolve/main/ToolGen-Hierarchical-Llama-3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ToolGen-Hierarchical-Llama-3-8B-GGUF/resolve/main/ToolGen-Hierarchical-Llama-3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/ToolGen-Hierarchical-Llama-3-8B-GGUF/resolve/main/ToolGen-Hierarchical-Llama-3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/ToolGen-Hierarchical-Llama-3-8B-GGUF/resolve/main/ToolGen-Hierarchical-Llama-3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ToolGen-Hierarchical-Llama-3-8B-GGUF/resolve/main/ToolGen-Hierarchical-Llama-3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ToolGen-Hierarchical-Llama-3-8B-GGUF/resolve/main/ToolGen-Hierarchical-Llama-3-8B.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. + + diff --git a/ToolGen-Hierarchical-Llama-3-8B.IQ4_XS.gguf b/ToolGen-Hierarchical-Llama-3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..56b6917 --- /dev/null +++ b/ToolGen-Hierarchical-Llama-3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0713195ee8764ca9f2945dc190a6f3d154f5cc786919b545ef803ae3bfdf400d +size 4484362816 diff --git a/ToolGen-Hierarchical-Llama-3-8B.Q2_K.gguf b/ToolGen-Hierarchical-Llama-3-8B.Q2_K.gguf new file mode 100644 index 0000000..097f26c --- /dev/null +++ b/ToolGen-Hierarchical-Llama-3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:050846b84b3b310ae2fc0517f4270f0c06fbaa67dca3c26b9bd8b8f5f2d4e71a +size 3179131456 diff --git a/ToolGen-Hierarchical-Llama-3-8B.Q3_K_L.gguf b/ToolGen-Hierarchical-Llama-3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..66caed4 --- /dev/null +++ b/ToolGen-Hierarchical-Llama-3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:834a2ac5b247477cca5bec01e49619e2d31ce217749a6a81c52d71923aba2552 +size 4321956416 diff --git a/ToolGen-Hierarchical-Llama-3-8B.Q3_K_M.gguf b/ToolGen-Hierarchical-Llama-3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..095201b --- /dev/null +++ b/ToolGen-Hierarchical-Llama-3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c871e975f68de7efe060690f2ca14e7b1bafc7e1acad1ae89aa008bf7a36056 +size 4018917952 diff --git a/ToolGen-Hierarchical-Llama-3-8B.Q3_K_S.gguf b/ToolGen-Hierarchical-Llama-3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..ba4a771 --- /dev/null +++ b/ToolGen-Hierarchical-Llama-3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b7eae231707612623bd21dfd372d1648f704d16f0f2a940b196c14b671bfc84 +size 3664499264 diff --git a/ToolGen-Hierarchical-Llama-3-8B.Q4_K_M.gguf b/ToolGen-Hierarchical-Llama-3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..afc6458 --- /dev/null +++ b/ToolGen-Hierarchical-Llama-3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41b3056f158faa77bec814fadb7324bb1421e2e5f5288ea7a396173ed03e5975 +size 4920734272 diff --git a/ToolGen-Hierarchical-Llama-3-8B.Q4_K_S.gguf b/ToolGen-Hierarchical-Llama-3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..ecc5724 --- /dev/null +++ b/ToolGen-Hierarchical-Llama-3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c15cc1588c077f47d4f27f8360c17a4a12f67a2019f5ab162c6b11d796531c4 +size 4692668992 diff --git a/ToolGen-Hierarchical-Llama-3-8B.Q5_K_M.gguf b/ToolGen-Hierarchical-Llama-3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..613047b --- /dev/null +++ b/ToolGen-Hierarchical-Llama-3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c835e387e2cc50233cb00d7db2484bd159210e9141696a83f116a099be43cc8a +size 5732987456 diff --git a/ToolGen-Hierarchical-Llama-3-8B.Q5_K_S.gguf b/ToolGen-Hierarchical-Llama-3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..7a7a44e --- /dev/null +++ b/ToolGen-Hierarchical-Llama-3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:530dc53bbe057c1050ac53edbf4aff704b0c7fb155a50ac44d4957e8ffecc2e8 +size 5599294016 diff --git a/ToolGen-Hierarchical-Llama-3-8B.Q6_K.gguf b/ToolGen-Hierarchical-Llama-3-8B.Q6_K.gguf new file mode 100644 index 0000000..9902a05 --- /dev/null +++ b/ToolGen-Hierarchical-Llama-3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69cedfa371a53d6025cd77aaf773604cd5b3ca93c955deb376199796cd73d450 +size 6596006464 diff --git a/ToolGen-Hierarchical-Llama-3-8B.Q8_0.gguf b/ToolGen-Hierarchical-Llama-3-8B.Q8_0.gguf new file mode 100644 index 0000000..a26a03f --- /dev/null +++ b/ToolGen-Hierarchical-Llama-3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b14ad2306130e45af65c92fb6eba8f1ab768b682ab754dd9433dbff6f0dfdd8e +size 8540770880 diff --git a/ToolGen-Hierarchical-Llama-3-8B.f16.gguf b/ToolGen-Hierarchical-Llama-3-8B.f16.gguf new file mode 100644 index 0000000..ab07b81 --- /dev/null +++ b/ToolGen-Hierarchical-Llama-3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9238334aad68cf5ad1ceac2badf0285b005903c8c0650d70ae53d968412781bb +size 16068891200