commit b1ee232d066cbef48911f87708df771d1590d9e8 Author: ModelHub XC Date: Tue Oct 6 05:31:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c769c17 --- /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 +ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..25a2c0b --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Alibaba-NLP/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Alibaba-NLP/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct-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/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct-GGUF/resolve/main/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q2_K.gguf) | Q2_K | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct-GGUF/resolve/main/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct-GGUF/resolve/main/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q3_K_M.gguf) | Q3_K_M | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct-GGUF/resolve/main/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct-GGUF/resolve/main/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct-GGUF/resolve/main/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q4_K_S.gguf) | Q4_K_S | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct-GGUF/resolve/main/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q4_K_M.gguf) | Q4_K_M | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct-GGUF/resolve/main/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q5_K_S.gguf) | Q5_K_S | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct-GGUF/resolve/main/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q5_K_M.gguf) | Q5_K_M | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct-GGUF/resolve/main/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q6_K.gguf) | Q6_K | 3.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct-GGUF/resolve/main/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q8_0.gguf) | Q8_0 | 3.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct-GGUF/resolve/main/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.f16.gguf) | f16 | 7.3 | 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/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.IQ4_XS.gguf b/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..b906212 --- /dev/null +++ b/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:064656b4c1e4fee8447a0d2e50b781048eef64956e5bd6ef85416ee001a8f16d +size 2050220640 diff --git a/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q2_K.gguf b/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q2_K.gguf new file mode 100644 index 0000000..8b4de03 --- /dev/null +++ b/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3796453a5d656e7f84b80461158acf9614ca235463b3018c13e280a6d353c578 +size 1493217888 diff --git a/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q3_K_L.gguf b/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..ca840fb --- /dev/null +++ b/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8f8b0507da79c8c70b40df12910c9bbe5afd4e35461648c36c6427a3f91fe43 +size 1984645728 diff --git a/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q3_K_M.gguf b/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..43efcd6 --- /dev/null +++ b/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccb813be34940f4d339b3a276968f0915aca1fbf9aadbc762984727dbe40a2ab +size 1856457312 diff --git a/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q3_K_S.gguf b/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..4bd1f19 --- /dev/null +++ b/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67b2500cb136e7188f6ead54154a4374ac698e8ebd09d52cfa8a697927575901 +size 1712147040 diff --git a/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q4_K_M.gguf b/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..1c4804c --- /dev/null +++ b/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:092f997dbc3f6258a0e3700b14c78328d37bbab1f9806582203af68aa6164547 +size 2241004128 diff --git a/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q4_K_S.gguf b/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..34c6beb --- /dev/null +++ b/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3668310d73a71f393f33e2bffe59d2606bbeb534b309499ea3f14166d02e384 +size 2149827168 diff --git a/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q5_K_M.gguf b/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..59a7585 --- /dev/null +++ b/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab3078642ea5f30a9d76cbf36a1c67002a6f5951bb860eb576a4c1ede8155854 +size 2593030752 diff --git a/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q5_K_S.gguf b/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..f52efb5 --- /dev/null +++ b/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e86c9ea2822ff143788949c78b9eb7d4dcda5e9e768fa5f236fe334d0d68575 +size 2540388960 diff --git a/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q6_K.gguf b/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q6_K.gguf new file mode 100644 index 0000000..adc98d8 --- /dev/null +++ b/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d23dfad66ecda2d219c1a3e4017c4ad9e1721e1bcebab193d3f43384f331a173 +size 2967059040 diff --git a/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q8_0.gguf b/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q8_0.gguf new file mode 100644 index 0000000..c151793 --- /dev/null +++ b/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caae534f65e6e9e502aef55e407ce1cad36d77b4383692326a92e1912954b88c +size 3840526944 diff --git a/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.f16.gguf b/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.f16.gguf new file mode 100644 index 0000000..36ed5d1 --- /dev/null +++ b/ZeroSearch_wiki_V2_Llama_3.2_3B_Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c33ac5d0864eb3052636573ff3064ce7c5d2157fe0028b6aaa6c059e2085e37 +size 7221693024