初始化项目，由ModelHub XC社区提供模型

Model: mradermacher/Cassandre-RAG-Llama-3.2-3B-GGUF
Source: Original Platform

.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.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Cassandre-RAG-Llama-3.2-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Cassandre-RAG-Llama-3.2-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Cassandre-RAG-Llama-3.2-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Cassandre-RAG-Llama-3.2-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Cassandre-RAG-Llama-3.2-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Cassandre-RAG-Llama-3.2-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Cassandre-RAG-Llama-3.2-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Cassandre-RAG-Llama-3.2-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Cassandre-RAG-Llama-3.2-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Cassandre-RAG-Llama-3.2-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Cassandre-RAG-Llama-3.2-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text

Cassandre-RAG-Llama-3.2-3B.IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64b13b93d60ae34c2f67d8613e00df5e38d4d3993ca51245943e3a3aa6bb4241
+size 1840902912

Cassandre-RAG-Llama-3.2-3B.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d69a01ef49a3174172dde0f1ce99e6eae40bba91ca1287a49f429f9b0c45d5da
+size 1363931904

Cassandre-RAG-Llama-3.2-3B.Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1c384840055b48e463464a05ba652868eeb51de6899c368a6638f47d4b74ac9
+size 1815343872

Cassandre-RAG-Llama-3.2-3B.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:165f7f224cffca31635243bf4c696a62815254f174191c707a15c06c84cd35ff
+size 1687155456

Cassandre-RAG-Llama-3.2-3B.Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df2ff673d01ead2085e24cd37e5b40a74125b2b1ac8dc8efd6e3e698255c3933
+size 1542845184

Cassandre-RAG-Llama-3.2-3B.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:256e0ef8314055705c5c87bf4875a8ecbf991afdbc1a23ae870add23233686d3
+size 2019373824

Cassandre-RAG-Llama-3.2-3B.Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cafbf3f75f31a0ecbe48b603c92d74c5add65210080edbaba9b06b8c0f1bbb41
+size 1928196864

Cassandre-RAG-Llama-3.2-3B.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01ce618de78410456f0a16bc5ea5b7d7a49b7372037f6f187945e64df61317d4
+size 2322150144

Cassandre-RAG-Llama-3.2-3B.Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:761bb4910317f01f5c88c2714380650a0c0ac51e378ba4d1c19aac52978125ae
+size 2269508352

Cassandre-RAG-Llama-3.2-3B.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02bea84833bd8a39381d0693d07daa62d79ad9a1ab4b89b1ff2ed59531d66be7
+size 2643849984

Cassandre-RAG-Llama-3.2-3B.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:545ea8c79ce10c279c95303795d6166a2eba9e01b0859c3854d9f043db897b5a
+size 3421895424

Cassandre-RAG-Llama-3.2-3B.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a9a88c744520c21ab7b14efcec2896ff4374656552bff00a8a7a3cf08b06bba
+size 6433684224

README.md

@@ -0,0 +1,69 @@
+---
+base_model: jbl2024/Cassandre-RAG-Llama-3.2-3B
+language:
+- en
+library_name: transformers
+license: mit
+mradermacher:
+  readme_rev: 1
+quantized_by: mradermacher
+---
+## About
+
+<!-- ### quantize_version: 2 -->
+<!-- ### output_tensor_quantised: 1 -->
+<!-- ### convert_type: hf -->
+<!-- ### vocab_type:  -->
+<!-- ### tags:  -->
+static quants of https://huggingface.co/jbl2024/Cassandre-RAG-Llama-3.2-3B
+
+<!-- provided-files -->
+
+***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Cassandre-RAG-Llama-3.2-3B-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/Cassandre-RAG-Llama-3.2-3B-GGUF/resolve/main/Cassandre-RAG-Llama-3.2-3B.Q2_K.gguf) | Q2_K | 1.5 |  |
+| [GGUF](https://huggingface.co/mradermacher/Cassandre-RAG-Llama-3.2-3B-GGUF/resolve/main/Cassandre-RAG-Llama-3.2-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/Cassandre-RAG-Llama-3.2-3B-GGUF/resolve/main/Cassandre-RAG-Llama-3.2-3B.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/Cassandre-RAG-Llama-3.2-3B-GGUF/resolve/main/Cassandre-RAG-Llama-3.2-3B.Q3_K_L.gguf) | Q3_K_L | 1.9 |  |
+| [GGUF](https://huggingface.co/mradermacher/Cassandre-RAG-Llama-3.2-3B-GGUF/resolve/main/Cassandre-RAG-Llama-3.2-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 |  |
+| [GGUF](https://huggingface.co/mradermacher/Cassandre-RAG-Llama-3.2-3B-GGUF/resolve/main/Cassandre-RAG-Llama-3.2-3B.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Cassandre-RAG-Llama-3.2-3B-GGUF/resolve/main/Cassandre-RAG-Llama-3.2-3B.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Cassandre-RAG-Llama-3.2-3B-GGUF/resolve/main/Cassandre-RAG-Llama-3.2-3B.Q5_K_S.gguf) | Q5_K_S | 2.4 |  |
+| [GGUF](https://huggingface.co/mradermacher/Cassandre-RAG-Llama-3.2-3B-GGUF/resolve/main/Cassandre-RAG-Llama-3.2-3B.Q5_K_M.gguf) | Q5_K_M | 2.4 |  |
+| [GGUF](https://huggingface.co/mradermacher/Cassandre-RAG-Llama-3.2-3B-GGUF/resolve/main/Cassandre-RAG-Llama-3.2-3B.Q6_K.gguf) | Q6_K | 2.7 | very good quality |
+| [GGUF](https://huggingface.co/mradermacher/Cassandre-RAG-Llama-3.2-3B-GGUF/resolve/main/Cassandre-RAG-Llama-3.2-3B.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality |
+| [GGUF](https://huggingface.co/mradermacher/Cassandre-RAG-Llama-3.2-3B-GGUF/resolve/main/Cassandre-RAG-Llama-3.2-3B.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.
+
+<!-- end -->