commit 8fb41fe2698c83c7b27d1f4f7b5d64f0d3274804 Author: ModelHub XC Date: Sat Jul 4 00:30:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/CIA-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6c2bc6f --- /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 +CIA-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +CIA-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +CIA-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +CIA-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CIA-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CIA-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CIA-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CIA-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CIA-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CIA-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +CIA-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +CIA-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/CIA-4B.IQ4_XS.gguf b/CIA-4B.IQ4_XS.gguf new file mode 100644 index 0000000..4266788 --- /dev/null +++ b/CIA-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:849efbc9dd45188e6bc6025575bee949177f2a108f508526277cf7bb2fdfc2f7 +size 2492949600 diff --git a/CIA-4B.Q2_K.gguf b/CIA-4B.Q2_K.gguf new file mode 100644 index 0000000..14f96bc --- /dev/null +++ b/CIA-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a958edec7e6e8ff85dd13b53b58cfeacd9db48585ce2c006140c076f7e17db2a +size 1797126240 diff --git a/CIA-4B.Q3_K_L.gguf b/CIA-4B.Q3_K_L.gguf new file mode 100644 index 0000000..0f555ed --- /dev/null +++ b/CIA-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a89f315bf9a4661f39e0e8fa78924e4630b4502893d086af7d19d3e1bb5f725 +size 2406915680 diff --git a/CIA-4B.Q3_K_M.gguf b/CIA-4B.Q3_K_M.gguf new file mode 100644 index 0000000..3dd49e1 --- /dev/null +++ b/CIA-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd8c4d0736fa86f23482318748ac947b87997304f08ecb11f87191535234553f +size 2242748000 diff --git a/CIA-4B.Q3_K_S.gguf b/CIA-4B.Q3_K_S.gguf new file mode 100644 index 0000000..f5b461f --- /dev/null +++ b/CIA-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b34dc3efcb8535228fb4e9f8774482fb91bc8ac96e0d55ba2f7f12a914866251 +size 2054127200 diff --git a/CIA-4B.Q4_K_M.gguf b/CIA-4B.Q4_K_M.gguf new file mode 100644 index 0000000..ed179ee --- /dev/null +++ b/CIA-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c93d69b669f26da6ef71af228bd7764783b7ccf6182bb917b7c6f8b84de4ef7 +size 2716068960 diff --git a/CIA-4B.Q4_K_S.gguf b/CIA-4B.Q4_K_S.gguf new file mode 100644 index 0000000..fd35758 --- /dev/null +++ b/CIA-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:102ce3ef513430b5a3ea7e78a7fa2b0872e6e0b996540b5cb0ac3391a85a03b3 +size 2602097760 diff --git a/CIA-4B.Q5_K_M.gguf b/CIA-4B.Q5_K_M.gguf new file mode 100644 index 0000000..e4619a3 --- /dev/null +++ b/CIA-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4445f6c00f23c9c450227c5bfda83e9f7becb1a62098a2e572bfe21c57c21cb2 +size 3156921440 diff --git a/CIA-4B.Q5_K_S.gguf b/CIA-4B.Q5_K_S.gguf new file mode 100644 index 0000000..8f68ffc --- /dev/null +++ b/CIA-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15505147741ea6ad6f8ac737493a1685b69df53b688edeffaec290f2e4d6fa65 +size 3091119200 diff --git a/CIA-4B.Q6_K.gguf b/CIA-4B.Q6_K.gguf new file mode 100644 index 0000000..16cabe8 --- /dev/null +++ b/CIA-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7545161ee1b453acc86c0bc6c32a0efabdb9b35ad70aeb8adbf543c78d6dd66a +size 3625327200 diff --git a/CIA-4B.Q8_0.gguf b/CIA-4B.Q8_0.gguf new file mode 100644 index 0000000..2c85e05 --- /dev/null +++ b/CIA-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:853c3bb0cd6b3245ae82325b80566f415a3e5264003fc8d0fcd96cf0ab958a9d +size 4693671520 diff --git a/CIA-4B.f16.gguf b/CIA-4B.f16.gguf new file mode 100644 index 0000000..13c155f --- /dev/null +++ b/CIA-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a7abb68dee2e4338f48c09142c6dae77216e6d9f6db3f0d7508142747dfc116 +size 8829197920 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2a2c4c6 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: iaa01/CIA-4B +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/iaa01/CIA-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#CIA-4B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/CIA-4B-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/CIA-4B-GGUF/resolve/main/CIA-4B.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/CIA-4B-GGUF/resolve/main/CIA-4B.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/CIA-4B-GGUF/resolve/main/CIA-4B.Q3_K_M.gguf) | Q3_K_M | 2.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/CIA-4B-GGUF/resolve/main/CIA-4B.Q3_K_L.gguf) | Q3_K_L | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/CIA-4B-GGUF/resolve/main/CIA-4B.IQ4_XS.gguf) | IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/CIA-4B-GGUF/resolve/main/CIA-4B.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CIA-4B-GGUF/resolve/main/CIA-4B.Q4_K_M.gguf) | Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CIA-4B-GGUF/resolve/main/CIA-4B.Q5_K_S.gguf) | Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/CIA-4B-GGUF/resolve/main/CIA-4B.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/CIA-4B-GGUF/resolve/main/CIA-4B.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/CIA-4B-GGUF/resolve/main/CIA-4B.Q8_0.gguf) | Q8_0 | 4.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/CIA-4B-GGUF/resolve/main/CIA-4B.f16.gguf) | f16 | 8.9 | 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. + +