commit 8fda4d868aa8c955ce96f8b38aa9a56261b55f70 Author: ModelHub XC Date: Mon Jul 20 19:50:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ITDR-SFT-Qwen2.5-3B-v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7a2b1f6 --- /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 +ITDR-SFT-Qwen2.5-3B-v1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ITDR-SFT-Qwen2.5-3B-v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ITDR-SFT-Qwen2.5-3B-v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ITDR-SFT-Qwen2.5-3B-v1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ITDR-SFT-Qwen2.5-3B-v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ITDR-SFT-Qwen2.5-3B-v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ITDR-SFT-Qwen2.5-3B-v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ITDR-SFT-Qwen2.5-3B-v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ITDR-SFT-Qwen2.5-3B-v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ITDR-SFT-Qwen2.5-3B-v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ITDR-SFT-Qwen2.5-3B-v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ITDR-SFT-Qwen2.5-3B-v1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ITDR-SFT-Qwen2.5-3B-v1.IQ4_XS.gguf b/ITDR-SFT-Qwen2.5-3B-v1.IQ4_XS.gguf new file mode 100644 index 0000000..d313d42 --- /dev/null +++ b/ITDR-SFT-Qwen2.5-3B-v1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64b4179fa7241571dbce2a205765e1303d21658ea4d83e0d5ea42a23f48c1d9c +size 1753185216 diff --git a/ITDR-SFT-Qwen2.5-3B-v1.Q2_K.gguf b/ITDR-SFT-Qwen2.5-3B-v1.Q2_K.gguf new file mode 100644 index 0000000..fd1bbb0 --- /dev/null +++ b/ITDR-SFT-Qwen2.5-3B-v1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:902a48e8f04bd127da8d4dcf63eb6525472d8a23ef76c28bc1e4bd263e9fd206 +size 1274756032 diff --git a/ITDR-SFT-Qwen2.5-3B-v1.Q3_K_L.gguf b/ITDR-SFT-Qwen2.5-3B-v1.Q3_K_L.gguf new file mode 100644 index 0000000..c45af87 --- /dev/null +++ b/ITDR-SFT-Qwen2.5-3B-v1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7b070a0a8c9b607ce901514ab5013826c803fb73222cd7b2e88436d38cf9ac4 +size 1707391936 diff --git a/ITDR-SFT-Qwen2.5-3B-v1.Q3_K_M.gguf b/ITDR-SFT-Qwen2.5-3B-v1.Q3_K_M.gguf new file mode 100644 index 0000000..798b81a --- /dev/null +++ b/ITDR-SFT-Qwen2.5-3B-v1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71d3148283c2335948fce65a2b059f4c7f88d328b220ff5a84794c8a9c19fa4a +size 1590475712 diff --git a/ITDR-SFT-Qwen2.5-3B-v1.Q3_K_S.gguf b/ITDR-SFT-Qwen2.5-3B-v1.Q3_K_S.gguf new file mode 100644 index 0000000..084c19e --- /dev/null +++ b/ITDR-SFT-Qwen2.5-3B-v1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5261dab27592fcb1e92a846d634201d940a568949a150e6a1e5f1b9d2e94451c +size 1454357440 diff --git a/ITDR-SFT-Qwen2.5-3B-v1.Q4_K_M.gguf b/ITDR-SFT-Qwen2.5-3B-v1.Q4_K_M.gguf new file mode 100644 index 0000000..0ba5594 --- /dev/null +++ b/ITDR-SFT-Qwen2.5-3B-v1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41fcdfcedcc0eaaa10d245a91cbd7cfda0ea56bf19bb6e349ea77c3abd357607 +size 1929903040 diff --git a/ITDR-SFT-Qwen2.5-3B-v1.Q4_K_S.gguf b/ITDR-SFT-Qwen2.5-3B-v1.Q4_K_S.gguf new file mode 100644 index 0000000..6dd5b44 --- /dev/null +++ b/ITDR-SFT-Qwen2.5-3B-v1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba9feda8bde695913564062e06a8e1b4ddcfb93122d2dcc9b553ef4527140127 +size 1834384320 diff --git a/ITDR-SFT-Qwen2.5-3B-v1.Q5_K_M.gguf b/ITDR-SFT-Qwen2.5-3B-v1.Q5_K_M.gguf new file mode 100644 index 0000000..8bf7134 --- /dev/null +++ b/ITDR-SFT-Qwen2.5-3B-v1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fc8cc50ff4b472f670c6c2a7510474eea0f400b33024b080de49f0c0f321342 +size 2224815040 diff --git a/ITDR-SFT-Qwen2.5-3B-v1.Q5_K_S.gguf b/ITDR-SFT-Qwen2.5-3B-v1.Q5_K_S.gguf new file mode 100644 index 0000000..93f65c2 --- /dev/null +++ b/ITDR-SFT-Qwen2.5-3B-v1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dd8ae768026aca33605ace705d7569b69f5ebf9ec8c272feb1da250288cd5f5 +size 2169666496 diff --git a/ITDR-SFT-Qwen2.5-3B-v1.Q6_K.gguf b/ITDR-SFT-Qwen2.5-3B-v1.Q6_K.gguf new file mode 100644 index 0000000..8e4cff2 --- /dev/null +++ b/ITDR-SFT-Qwen2.5-3B-v1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c930317f0b17890d6a6d25353917f7cb4855a898589b3d5d893fc3de1124f0c +size 2538159040 diff --git a/ITDR-SFT-Qwen2.5-3B-v1.Q8_0.gguf b/ITDR-SFT-Qwen2.5-3B-v1.Q8_0.gguf new file mode 100644 index 0000000..d1d08af --- /dev/null +++ b/ITDR-SFT-Qwen2.5-3B-v1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:096007de969edb30abb5ce3c883b0d8bf728765c4adc872fd67f5450114fc993 +size 3285476288 diff --git a/ITDR-SFT-Qwen2.5-3B-v1.f16.gguf b/ITDR-SFT-Qwen2.5-3B-v1.f16.gguf new file mode 100644 index 0000000..b0dd023 --- /dev/null +++ b/ITDR-SFT-Qwen2.5-3B-v1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:497b6e5f9b5f92ea5bf505e69e90e7e3f6d9bb0006c330f2eaa59af54c846921 +size 6178317248 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d74426c --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: Varadrajan/ITDR-SFT-Qwen2.5-3B-v1 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- gguf +- llama.cpp +- unsloth +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Varadrajan/ITDR-SFT-Qwen2.5-3B-v1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ITDR-SFT-Qwen2.5-3B-v1-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/ITDR-SFT-Qwen2.5-3B-v1-GGUF/resolve/main/ITDR-SFT-Qwen2.5-3B-v1.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/ITDR-SFT-Qwen2.5-3B-v1-GGUF/resolve/main/ITDR-SFT-Qwen2.5-3B-v1.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/ITDR-SFT-Qwen2.5-3B-v1-GGUF/resolve/main/ITDR-SFT-Qwen2.5-3B-v1.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ITDR-SFT-Qwen2.5-3B-v1-GGUF/resolve/main/ITDR-SFT-Qwen2.5-3B-v1.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/ITDR-SFT-Qwen2.5-3B-v1-GGUF/resolve/main/ITDR-SFT-Qwen2.5-3B-v1.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/ITDR-SFT-Qwen2.5-3B-v1-GGUF/resolve/main/ITDR-SFT-Qwen2.5-3B-v1.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ITDR-SFT-Qwen2.5-3B-v1-GGUF/resolve/main/ITDR-SFT-Qwen2.5-3B-v1.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ITDR-SFT-Qwen2.5-3B-v1-GGUF/resolve/main/ITDR-SFT-Qwen2.5-3B-v1.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/ITDR-SFT-Qwen2.5-3B-v1-GGUF/resolve/main/ITDR-SFT-Qwen2.5-3B-v1.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/ITDR-SFT-Qwen2.5-3B-v1-GGUF/resolve/main/ITDR-SFT-Qwen2.5-3B-v1.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ITDR-SFT-Qwen2.5-3B-v1-GGUF/resolve/main/ITDR-SFT-Qwen2.5-3B-v1.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ITDR-SFT-Qwen2.5-3B-v1-GGUF/resolve/main/ITDR-SFT-Qwen2.5-3B-v1.f16.gguf) | f16 | 6.3 | 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. + +