commit fe011024c426361ca0cb75bcb45759302c3b60d1 Author: ModelHub XC Date: Tue Sep 15 04:56:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Explore_Llama-3.2-1B-Inst_v1.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e628f2c --- /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 +Explore_Llama-3.2-1B-Inst_v1.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Explore_Llama-3.2-1B-Inst_v1.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Explore_Llama-3.2-1B-Inst_v1.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Explore_Llama-3.2-1B-Inst_v1.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Explore_Llama-3.2-1B-Inst_v1.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Explore_Llama-3.2-1B-Inst_v1.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Explore_Llama-3.2-1B-Inst_v1.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Explore_Llama-3.2-1B-Inst_v1.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Explore_Llama-3.2-1B-Inst_v1.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Explore_Llama-3.2-1B-Inst_v1.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Explore_Llama-3.2-1B-Inst_v1.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Explore_Llama-3.2-1B-Inst_v1.1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Explore_Llama-3.2-1B-Inst_v1.1.IQ4_XS.gguf b/Explore_Llama-3.2-1B-Inst_v1.1.IQ4_XS.gguf new file mode 100644 index 0000000..7fb05c6 --- /dev/null +++ b/Explore_Llama-3.2-1B-Inst_v1.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd9188e34f1d42ff423a793dbc5841868e45a682f0dc9e2d5e80b31bd873bd83 +size 748384704 diff --git a/Explore_Llama-3.2-1B-Inst_v1.1.Q2_K.gguf b/Explore_Llama-3.2-1B-Inst_v1.1.Q2_K.gguf new file mode 100644 index 0000000..42d34dc --- /dev/null +++ b/Explore_Llama-3.2-1B-Inst_v1.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed9ca2bb61c8fb852cecd43b605e7d9a761fcaafbd41c3391ee3f63d602e0979 +size 580874688 diff --git a/Explore_Llama-3.2-1B-Inst_v1.1.Q3_K_L.gguf b/Explore_Llama-3.2-1B-Inst_v1.1.Q3_K_L.gguf new file mode 100644 index 0000000..4576008 --- /dev/null +++ b/Explore_Llama-3.2-1B-Inst_v1.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fa27d2001c19d6ebbe98a507396e631e41cd63054d1a5b6c841bbac4ebb74d5 +size 732524992 diff --git a/Explore_Llama-3.2-1B-Inst_v1.1.Q3_K_M.gguf b/Explore_Llama-3.2-1B-Inst_v1.1.Q3_K_M.gguf new file mode 100644 index 0000000..3004675 --- /dev/null +++ b/Explore_Llama-3.2-1B-Inst_v1.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc788d1c3ea3377da57edf78fdc8e60b2db2a51140e465aedb5fcfa50831b5d4 +size 690844096 diff --git a/Explore_Llama-3.2-1B-Inst_v1.1.Q3_K_S.gguf b/Explore_Llama-3.2-1B-Inst_v1.1.Q3_K_S.gguf new file mode 100644 index 0000000..54a89e4 --- /dev/null +++ b/Explore_Llama-3.2-1B-Inst_v1.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:347ef484068e90723380dbd4dd68c4449f4569429f55efac9a605eef2ab71101 +size 641692096 diff --git a/Explore_Llama-3.2-1B-Inst_v1.1.Q4_K_M.gguf b/Explore_Llama-3.2-1B-Inst_v1.1.Q4_K_M.gguf new file mode 100644 index 0000000..ac67f87 --- /dev/null +++ b/Explore_Llama-3.2-1B-Inst_v1.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63f5e36b1138b8fa889567b4b3ca6d95723d958b9eb9dd85ade2bee13de420f1 +size 807694784 diff --git a/Explore_Llama-3.2-1B-Inst_v1.1.Q4_K_S.gguf b/Explore_Llama-3.2-1B-Inst_v1.1.Q4_K_S.gguf new file mode 100644 index 0000000..43ddec9 --- /dev/null +++ b/Explore_Llama-3.2-1B-Inst_v1.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b156a81cff3ba3c853f71da22f699942b940fbd015f092b8c49c69523518f48a +size 775647680 diff --git a/Explore_Llama-3.2-1B-Inst_v1.1.Q5_K_M.gguf b/Explore_Llama-3.2-1B-Inst_v1.1.Q5_K_M.gguf new file mode 100644 index 0000000..50bfba6 --- /dev/null +++ b/Explore_Llama-3.2-1B-Inst_v1.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e32f8152503c9c0929ea6a682db92c1b8a38fb412e45a8f3d4b227aa8ddd5a95 +size 911503808 diff --git a/Explore_Llama-3.2-1B-Inst_v1.1.Q5_K_S.gguf b/Explore_Llama-3.2-1B-Inst_v1.1.Q5_K_S.gguf new file mode 100644 index 0000000..158adea --- /dev/null +++ b/Explore_Llama-3.2-1B-Inst_v1.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dad67ba1d30b779e88416e749ca837f6d2e09415af4e1cf8bd34630fe10bdf62 +size 892563904 diff --git a/Explore_Llama-3.2-1B-Inst_v1.1.Q6_K.gguf b/Explore_Llama-3.2-1B-Inst_v1.1.Q6_K.gguf new file mode 100644 index 0000000..2b0aa01 --- /dev/null +++ b/Explore_Llama-3.2-1B-Inst_v1.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbbf9aaf40c2b7324424380885a278e7ef4bc52058dc7d76d6140b08626a0a16 +size 1021800896 diff --git a/Explore_Llama-3.2-1B-Inst_v1.1.Q8_0.gguf b/Explore_Llama-3.2-1B-Inst_v1.1.Q8_0.gguf new file mode 100644 index 0000000..9bee144 --- /dev/null +++ b/Explore_Llama-3.2-1B-Inst_v1.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b82e7d85ecda1e4226567e9e50c03276b42159c6681127ac402fd9cf5e25f319 +size 1321083328 diff --git a/Explore_Llama-3.2-1B-Inst_v1.1.f16.gguf b/Explore_Llama-3.2-1B-Inst_v1.1.f16.gguf new file mode 100644 index 0000000..0d2c33a --- /dev/null +++ b/Explore_Llama-3.2-1B-Inst_v1.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44e4c2d05b5ee5cd8212908b5089cdfd1f6ce098551676b6ba32514f10792c75 +size 2479595968 diff --git a/README.md b/README.md new file mode 100644 index 0000000..18d1894 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: DeepAuto-AI/Explore_Llama-3.2-1B-Inst_v1.1 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/DeepAuto-AI/Explore_Llama-3.2-1B-Inst_v1.1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Explore_Llama-3.2-1B-Inst_v1.1-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/Explore_Llama-3.2-1B-Inst_v1.1-GGUF/resolve/main/Explore_Llama-3.2-1B-Inst_v1.1.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Explore_Llama-3.2-1B-Inst_v1.1-GGUF/resolve/main/Explore_Llama-3.2-1B-Inst_v1.1.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Explore_Llama-3.2-1B-Inst_v1.1-GGUF/resolve/main/Explore_Llama-3.2-1B-Inst_v1.1.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Explore_Llama-3.2-1B-Inst_v1.1-GGUF/resolve/main/Explore_Llama-3.2-1B-Inst_v1.1.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Explore_Llama-3.2-1B-Inst_v1.1-GGUF/resolve/main/Explore_Llama-3.2-1B-Inst_v1.1.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Explore_Llama-3.2-1B-Inst_v1.1-GGUF/resolve/main/Explore_Llama-3.2-1B-Inst_v1.1.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Explore_Llama-3.2-1B-Inst_v1.1-GGUF/resolve/main/Explore_Llama-3.2-1B-Inst_v1.1.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Explore_Llama-3.2-1B-Inst_v1.1-GGUF/resolve/main/Explore_Llama-3.2-1B-Inst_v1.1.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Explore_Llama-3.2-1B-Inst_v1.1-GGUF/resolve/main/Explore_Llama-3.2-1B-Inst_v1.1.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Explore_Llama-3.2-1B-Inst_v1.1-GGUF/resolve/main/Explore_Llama-3.2-1B-Inst_v1.1.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Explore_Llama-3.2-1B-Inst_v1.1-GGUF/resolve/main/Explore_Llama-3.2-1B-Inst_v1.1.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Explore_Llama-3.2-1B-Inst_v1.1-GGUF/resolve/main/Explore_Llama-3.2-1B-Inst_v1.1.f16.gguf) | f16 | 2.6 | 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. + +