commit 4adf01a7052a8199df9aa72588416b3500794ab8 Author: ModelHub XC Date: Fri Jun 26 00:21:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Cassandre-RAG-Llama-3.2-3B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2f7ff79 --- /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 +Cassandre-RAG-Llama-3.2-3B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Cassandre-RAG-Llama-3.2-3B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Cassandre-RAG-Llama-3.2-3B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Cassandre-RAG-Llama-3.2-3B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cassandre-RAG-Llama-3.2-3B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cassandre-RAG-Llama-3.2-3B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cassandre-RAG-Llama-3.2-3B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cassandre-RAG-Llama-3.2-3B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cassandre-RAG-Llama-3.2-3B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cassandre-RAG-Llama-3.2-3B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Cassandre-RAG-Llama-3.2-3B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Cassandre-RAG-Llama-3.2-3B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Cassandre-RAG-Llama-3.2-3B-Instruct.IQ4_XS.gguf b/Cassandre-RAG-Llama-3.2-3B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..9bd001d --- /dev/null +++ b/Cassandre-RAG-Llama-3.2-3B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ff3d9a33af2244654cca7526025f0a38bf6a9c216fe5a8b108de612a6d7d380 +size 1840906848 diff --git a/Cassandre-RAG-Llama-3.2-3B-Instruct.Q2_K.gguf b/Cassandre-RAG-Llama-3.2-3B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..9aaca51 --- /dev/null +++ b/Cassandre-RAG-Llama-3.2-3B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffff65d08021273c24a75465801ac130fbbfe15808ca8f11a169b97be22ac21b +size 1363935840 diff --git a/Cassandre-RAG-Llama-3.2-3B-Instruct.Q3_K_L.gguf b/Cassandre-RAG-Llama-3.2-3B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..f743b21 --- /dev/null +++ b/Cassandre-RAG-Llama-3.2-3B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dea0042f2ace7c7f82c881424abb3ddabdbf45689ac897e384415acaf702e80 +size 1815347808 diff --git a/Cassandre-RAG-Llama-3.2-3B-Instruct.Q3_K_M.gguf b/Cassandre-RAG-Llama-3.2-3B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..942c115 --- /dev/null +++ b/Cassandre-RAG-Llama-3.2-3B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:160f639958ecd2d6dc4878360ca3cc3274b3328305a205abaca3ae40d0234a91 +size 1687159392 diff --git a/Cassandre-RAG-Llama-3.2-3B-Instruct.Q3_K_S.gguf b/Cassandre-RAG-Llama-3.2-3B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..bff62ea --- /dev/null +++ b/Cassandre-RAG-Llama-3.2-3B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2d487173ac86a21bc7e608e25c74f097aadcf7edc86827b9a4435b1997acab9 +size 1542849120 diff --git a/Cassandre-RAG-Llama-3.2-3B-Instruct.Q4_K_M.gguf b/Cassandre-RAG-Llama-3.2-3B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..ca97b5f --- /dev/null +++ b/Cassandre-RAG-Llama-3.2-3B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bda2761f48021a732f22b803c4ad3be2997963cde7ad0c6dba98e1d306314d86 +size 2019377760 diff --git a/Cassandre-RAG-Llama-3.2-3B-Instruct.Q4_K_S.gguf b/Cassandre-RAG-Llama-3.2-3B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..e461b5d --- /dev/null +++ b/Cassandre-RAG-Llama-3.2-3B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f10ba408cc4d05250cbb19ca4d169c532b8d7826302cc169edfb8d93d638382b +size 1928200800 diff --git a/Cassandre-RAG-Llama-3.2-3B-Instruct.Q5_K_M.gguf b/Cassandre-RAG-Llama-3.2-3B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..3312730 --- /dev/null +++ b/Cassandre-RAG-Llama-3.2-3B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1a65d97b5adb690884a4ec13ba48f0fdcaef83d44c8fbca384a0f13732d4f31 +size 2322154080 diff --git a/Cassandre-RAG-Llama-3.2-3B-Instruct.Q5_K_S.gguf b/Cassandre-RAG-Llama-3.2-3B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..278feca --- /dev/null +++ b/Cassandre-RAG-Llama-3.2-3B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7381b308e3995fe3f29281e1d10241055b5df37c41de359d33a7b928765ca70e +size 2269512288 diff --git a/Cassandre-RAG-Llama-3.2-3B-Instruct.Q6_K.gguf b/Cassandre-RAG-Llama-3.2-3B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..a105277 --- /dev/null +++ b/Cassandre-RAG-Llama-3.2-3B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f30fc988bf64eb916e8a1975a0ba4141f7e6385ea74a944a2f5f46475ae2f67 +size 2643853920 diff --git a/Cassandre-RAG-Llama-3.2-3B-Instruct.Q8_0.gguf b/Cassandre-RAG-Llama-3.2-3B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..ae331e3 --- /dev/null +++ b/Cassandre-RAG-Llama-3.2-3B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:139c09162a402d10e5ec9f78a6acffa963e380e64461e1a1a740283238f69745 +size 3421899360 diff --git a/Cassandre-RAG-Llama-3.2-3B-Instruct.f16.gguf b/Cassandre-RAG-Llama-3.2-3B-Instruct.f16.gguf new file mode 100644 index 0000000..fd3fe8e --- /dev/null +++ b/Cassandre-RAG-Llama-3.2-3B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df7e9c619b9f9f97b7a74068070b7b83b1282656361f161464f9fc2fd3b587f6 +size 6433688160 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c49cde3 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: jbl2024/Cassandre-RAG-Llama-3.2-3B-Instruct +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/jbl2024/Cassandre-RAG-Llama-3.2-3B-Instruct + + +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/Cassandre-RAG-Llama-3.2-3B-Instruct-GGUF/resolve/main/Cassandre-RAG-Llama-3.2-3B-Instruct.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Cassandre-RAG-Llama-3.2-3B-Instruct-GGUF/resolve/main/Cassandre-RAG-Llama-3.2-3B-Instruct.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Cassandre-RAG-Llama-3.2-3B-Instruct-GGUF/resolve/main/Cassandre-RAG-Llama-3.2-3B-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Cassandre-RAG-Llama-3.2-3B-Instruct-GGUF/resolve/main/Cassandre-RAG-Llama-3.2-3B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Cassandre-RAG-Llama-3.2-3B-Instruct-GGUF/resolve/main/Cassandre-RAG-Llama-3.2-3B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Cassandre-RAG-Llama-3.2-3B-Instruct-GGUF/resolve/main/Cassandre-RAG-Llama-3.2-3B-Instruct.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Cassandre-RAG-Llama-3.2-3B-Instruct-GGUF/resolve/main/Cassandre-RAG-Llama-3.2-3B-Instruct.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Cassandre-RAG-Llama-3.2-3B-Instruct-GGUF/resolve/main/Cassandre-RAG-Llama-3.2-3B-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Cassandre-RAG-Llama-3.2-3B-Instruct-GGUF/resolve/main/Cassandre-RAG-Llama-3.2-3B-Instruct.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Cassandre-RAG-Llama-3.2-3B-Instruct-GGUF/resolve/main/Cassandre-RAG-Llama-3.2-3B-Instruct.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Cassandre-RAG-Llama-3.2-3B-Instruct-GGUF/resolve/main/Cassandre-RAG-Llama-3.2-3B-Instruct.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Cassandre-RAG-Llama-3.2-3B-Instruct-GGUF/resolve/main/Cassandre-RAG-Llama-3.2-3B-Instruct.f16.gguf) | f16 | 6.5 | 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. + +