commit 937753769bdd6bb0768300f496a7a22fd623cf36 Author: ModelHub XC Date: Fri May 8 14:02:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TinyV-1.5B-Think-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5a0488f --- /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 +TinyV-1.5B-Think.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TinyV-1.5B-Think.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyV-1.5B-Think.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TinyV-1.5B-Think.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyV-1.5B-Think.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyV-1.5B-Think.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyV-1.5B-Think.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyV-1.5B-Think.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyV-1.5B-Think.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyV-1.5B-Think.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyV-1.5B-Think.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TinyV-1.5B-Think.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..452011b --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: zhangchenxu/TinyV-1.5B-Think +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama-factory +- full +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/zhangchenxu/TinyV-1.5B-Think + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#TinyV-1.5B-Think-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/TinyV-1.5B-Think-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/TinyV-1.5B-Think-GGUF/resolve/main/TinyV-1.5B-Think.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/TinyV-1.5B-Think-GGUF/resolve/main/TinyV-1.5B-Think.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyV-1.5B-Think-GGUF/resolve/main/TinyV-1.5B-Think.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TinyV-1.5B-Think-GGUF/resolve/main/TinyV-1.5B-Think.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/TinyV-1.5B-Think-GGUF/resolve/main/TinyV-1.5B-Think.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/TinyV-1.5B-Think-GGUF/resolve/main/TinyV-1.5B-Think.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyV-1.5B-Think-GGUF/resolve/main/TinyV-1.5B-Think.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyV-1.5B-Think-GGUF/resolve/main/TinyV-1.5B-Think.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/TinyV-1.5B-Think-GGUF/resolve/main/TinyV-1.5B-Think.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/TinyV-1.5B-Think-GGUF/resolve/main/TinyV-1.5B-Think.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TinyV-1.5B-Think-GGUF/resolve/main/TinyV-1.5B-Think.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TinyV-1.5B-Think-GGUF/resolve/main/TinyV-1.5B-Think.f16.gguf) | f16 | 3.2 | 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/TinyV-1.5B-Think.IQ4_XS.gguf b/TinyV-1.5B-Think.IQ4_XS.gguf new file mode 100644 index 0000000..e529465 --- /dev/null +++ b/TinyV-1.5B-Think.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63941d1708e2bebc3b66fce581fd7be725399f4a1b8939618638fc9284448c94 +size 902183168 diff --git a/TinyV-1.5B-Think.Q2_K.gguf b/TinyV-1.5B-Think.Q2_K.gguf new file mode 100644 index 0000000..d17e070 --- /dev/null +++ b/TinyV-1.5B-Think.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de6a83f878926153fa06d203fcd53c7f60784562f92ffefc8e3210f626409494 +size 676305152 diff --git a/TinyV-1.5B-Think.Q3_K_L.gguf b/TinyV-1.5B-Think.Q3_K_L.gguf new file mode 100644 index 0000000..3374510 --- /dev/null +++ b/TinyV-1.5B-Think.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbfcce301200dbf918cc865005cf58b1059075f7f5aec2bb8fd047fccdd2896b +size 880163072 diff --git a/TinyV-1.5B-Think.Q3_K_M.gguf b/TinyV-1.5B-Think.Q3_K_M.gguf new file mode 100644 index 0000000..bdfee8e --- /dev/null +++ b/TinyV-1.5B-Think.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c2beb7deb992fd925cc98fa95072e530b4eee28a7c3cc783b91333f9a6251de +size 824178944 diff --git a/TinyV-1.5B-Think.Q3_K_S.gguf b/TinyV-1.5B-Think.Q3_K_S.gguf new file mode 100644 index 0000000..948fa46 --- /dev/null +++ b/TinyV-1.5B-Think.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ae3fbe7af615a0af0715d9e158afd90e4a8b1d879aa0d261f87f07720a32a5b +size 760944896 diff --git a/TinyV-1.5B-Think.Q4_K_M.gguf b/TinyV-1.5B-Think.Q4_K_M.gguf new file mode 100644 index 0000000..0124b30 --- /dev/null +++ b/TinyV-1.5B-Think.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d266f9af2d7677a6cf6381003081215771fbb60e25364908d843df5b6989495 +size 986048768 diff --git a/TinyV-1.5B-Think.Q4_K_S.gguf b/TinyV-1.5B-Think.Q4_K_S.gguf new file mode 100644 index 0000000..0d9ab5d --- /dev/null +++ b/TinyV-1.5B-Think.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f889fe96fa10bfe6e0f8d0fb834f9b0b0cdda5b91c5f4662d3440945e7256d7f +size 940312832 diff --git a/TinyV-1.5B-Think.Q5_K_M.gguf b/TinyV-1.5B-Think.Q5_K_M.gguf new file mode 100644 index 0000000..196ff97 --- /dev/null +++ b/TinyV-1.5B-Think.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55bb6549de10e3ec662d228ccee57925eac1fa0fd9b5e354961c2ea7f6d1417c +size 1125050624 diff --git a/TinyV-1.5B-Think.Q5_K_S.gguf b/TinyV-1.5B-Think.Q5_K_S.gguf new file mode 100644 index 0000000..a17dda5 --- /dev/null +++ b/TinyV-1.5B-Think.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36fbc17632ab3a8adf8cca69829f109c8bec6eac747630b5a21bd8edba23b3c3 +size 1098729728 diff --git a/TinyV-1.5B-Think.Q6_K.gguf b/TinyV-1.5B-Think.Q6_K.gguf new file mode 100644 index 0000000..129ea7f --- /dev/null +++ b/TinyV-1.5B-Think.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9735b80e67ae943d6b2c4b69a34ac7ca9d738b025973f67cfb09a0e9302f808b +size 1272740096 diff --git a/TinyV-1.5B-Think.Q8_0.gguf b/TinyV-1.5B-Think.Q8_0.gguf new file mode 100644 index 0000000..9596772 --- /dev/null +++ b/TinyV-1.5B-Think.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58241fa234b664d39745dd27081d3c6ceed555761e779f37a6645f9808ffdd0e +size 1646573312 diff --git a/TinyV-1.5B-Think.f16.gguf b/TinyV-1.5B-Think.f16.gguf new file mode 100644 index 0000000..5213ae6 --- /dev/null +++ b/TinyV-1.5B-Think.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c9653bc962fc0d6a01fef90fcfe53db0c6902797096c66f6ceba11b89418d71 +size 3093669632