commit 48ef97bc77daef5f9f52cccc2eaa2d8a656a80da Author: ModelHub XC Date: Thu Apr 30 23:24:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SearchAgent-8B-hq-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1553647 --- /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 +SearchAgent-8B-hq.f16.gguf filter=lfs diff=lfs merge=lfs -text +SearchAgent-8B-hq.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SearchAgent-8B-hq.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SearchAgent-8B-hq.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SearchAgent-8B-hq.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SearchAgent-8B-hq.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SearchAgent-8B-hq.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SearchAgent-8B-hq.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SearchAgent-8B-hq.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SearchAgent-8B-hq.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SearchAgent-8B-hq.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SearchAgent-8B-hq.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..85ce60e --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: aidenjhwu/SearchAgent-8B-hq +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/aidenjhwu/SearchAgent-8B-hq + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#SearchAgent-8B-hq-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/SearchAgent-8B-hq-GGUF/resolve/main/SearchAgent-8B-hq.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/SearchAgent-8B-hq-GGUF/resolve/main/SearchAgent-8B-hq.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/SearchAgent-8B-hq-GGUF/resolve/main/SearchAgent-8B-hq.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SearchAgent-8B-hq-GGUF/resolve/main/SearchAgent-8B-hq.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/SearchAgent-8B-hq-GGUF/resolve/main/SearchAgent-8B-hq.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/SearchAgent-8B-hq-GGUF/resolve/main/SearchAgent-8B-hq.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SearchAgent-8B-hq-GGUF/resolve/main/SearchAgent-8B-hq.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SearchAgent-8B-hq-GGUF/resolve/main/SearchAgent-8B-hq.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/SearchAgent-8B-hq-GGUF/resolve/main/SearchAgent-8B-hq.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/SearchAgent-8B-hq-GGUF/resolve/main/SearchAgent-8B-hq.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SearchAgent-8B-hq-GGUF/resolve/main/SearchAgent-8B-hq.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SearchAgent-8B-hq-GGUF/resolve/main/SearchAgent-8B-hq.f16.gguf) | f16 | 16.5 | 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. + + diff --git a/SearchAgent-8B-hq.IQ4_XS.gguf b/SearchAgent-8B-hq.IQ4_XS.gguf new file mode 100644 index 0000000..9e9f8a1 --- /dev/null +++ b/SearchAgent-8B-hq.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0296978797f45804bbbba4c2c7b5ac349a807b9349c1d2602360f436d147f77d +size 4593296768 diff --git a/SearchAgent-8B-hq.Q2_K.gguf b/SearchAgent-8B-hq.Q2_K.gguf new file mode 100644 index 0000000..0845646 --- /dev/null +++ b/SearchAgent-8B-hq.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57593f5633db5f1786e6279e36dbc305240d7a684a4d307d7d0e91e83853fb75 +size 3281732992 diff --git a/SearchAgent-8B-hq.Q3_K_L.gguf b/SearchAgent-8B-hq.Q3_K_L.gguf new file mode 100644 index 0000000..29d93d9 --- /dev/null +++ b/SearchAgent-8B-hq.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f6d40b89eee2b81862bff0a36583d6e4c0e4d099573de5728da76f24988c731 +size 4431394176 diff --git a/SearchAgent-8B-hq.Q3_K_M.gguf b/SearchAgent-8B-hq.Q3_K_M.gguf new file mode 100644 index 0000000..b7c6755 --- /dev/null +++ b/SearchAgent-8B-hq.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3e8a638c5fb156f6c385c1c79395f179c0355cac5d341bd57fdb418a52ae71f +size 4124161408 diff --git a/SearchAgent-8B-hq.Q3_K_S.gguf b/SearchAgent-8B-hq.Q3_K_S.gguf new file mode 100644 index 0000000..b5582ca --- /dev/null +++ b/SearchAgent-8B-hq.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a71e2240439bca11a653e1df8560e9942e55924caded4b6cf51106f0a7cfa2bb +size 3769611648 diff --git a/SearchAgent-8B-hq.Q4_K_M.gguf b/SearchAgent-8B-hq.Q4_K_M.gguf new file mode 100644 index 0000000..f55276d --- /dev/null +++ b/SearchAgent-8B-hq.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a0c3fe3e6760a50708b983480b41c0967a06e42de23096e57f2e5bc777de556 +size 5027784064 diff --git a/SearchAgent-8B-hq.Q4_K_S.gguf b/SearchAgent-8B-hq.Q4_K_S.gguf new file mode 100644 index 0000000..f143ea4 --- /dev/null +++ b/SearchAgent-8B-hq.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7febde905f699681ca8267d53b31df974efed769c3d476a404c265c80c27774c +size 4802012544 diff --git a/SearchAgent-8B-hq.Q5_K_M.gguf b/SearchAgent-8B-hq.Q5_K_M.gguf new file mode 100644 index 0000000..24de269 --- /dev/null +++ b/SearchAgent-8B-hq.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a7cef03797441b7f6c2472404477785cb44abf1eca529126628088cffe4c750 +size 5851112832 diff --git a/SearchAgent-8B-hq.Q5_K_S.gguf b/SearchAgent-8B-hq.Q5_K_S.gguf new file mode 100644 index 0000000..4138a1a --- /dev/null +++ b/SearchAgent-8B-hq.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13dc96593521633799d702704662db8e7011dddd85b6722eb6eaea4f172e492f +size 5720761728 diff --git a/SearchAgent-8B-hq.Q6_K.gguf b/SearchAgent-8B-hq.Q6_K.gguf new file mode 100644 index 0000000..f7aa602 --- /dev/null +++ b/SearchAgent-8B-hq.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44d230fa4beea6d522fc69de560659f0449345c3d62968ba2c222dc2f67782b3 +size 6725899648 diff --git a/SearchAgent-8B-hq.Q8_0.gguf b/SearchAgent-8B-hq.Q8_0.gguf new file mode 100644 index 0000000..b9cef94 --- /dev/null +++ b/SearchAgent-8B-hq.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6a6ad6401975766bdbfc61bda69e3948161332dc732e9856c94b23636f4b88e +size 8709518720 diff --git a/SearchAgent-8B-hq.f16.gguf b/SearchAgent-8B-hq.f16.gguf new file mode 100644 index 0000000..17b720f --- /dev/null +++ b/SearchAgent-8B-hq.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ed624699cd57d6e83e97a291060fbcad2a23f6da3c9da8173635bd4a1ea5f3f +size 16388044160