commit d954d61faaacf1928fc3ce9055588038925c82a7 Author: ModelHub XC Date: Fri Jun 12 18:41:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/elle-qwen-3b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a155558 --- /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 +elle-qwen-3b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +elle-qwen-3b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +elle-qwen-3b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +elle-qwen-3b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +elle-qwen-3b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +elle-qwen-3b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +elle-qwen-3b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +elle-qwen-3b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +elle-qwen-3b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +elle-qwen-3b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +elle-qwen-3b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +elle-qwen-3b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..c700418 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: jonathanbrink77/elle-qwen-3b +language: +- en +library_name: transformers +license: other +license_link: https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE +license_name: qwen-research +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- base_model:adapter:Qwen/Qwen2.5-3B-Instruct +- lora +- transformers +--- +## About + + + + + + + + + +static quants of https://huggingface.co/jonathanbrink77/elle-qwen-3b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#elle-qwen-3b-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/elle-qwen-3b-GGUF/resolve/main/elle-qwen-3b.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/elle-qwen-3b-GGUF/resolve/main/elle-qwen-3b.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/elle-qwen-3b-GGUF/resolve/main/elle-qwen-3b.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/elle-qwen-3b-GGUF/resolve/main/elle-qwen-3b.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/elle-qwen-3b-GGUF/resolve/main/elle-qwen-3b.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/elle-qwen-3b-GGUF/resolve/main/elle-qwen-3b.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/elle-qwen-3b-GGUF/resolve/main/elle-qwen-3b.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/elle-qwen-3b-GGUF/resolve/main/elle-qwen-3b.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/elle-qwen-3b-GGUF/resolve/main/elle-qwen-3b.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/elle-qwen-3b-GGUF/resolve/main/elle-qwen-3b.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/elle-qwen-3b-GGUF/resolve/main/elle-qwen-3b.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/elle-qwen-3b-GGUF/resolve/main/elle-qwen-3b.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. + + diff --git a/elle-qwen-3b.IQ4_XS.gguf b/elle-qwen-3b.IQ4_XS.gguf new file mode 100644 index 0000000..a83bf2a --- /dev/null +++ b/elle-qwen-3b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d46d6b0a879e610b28b651e6b7237ed04fcc0a7c35b3dc4d357f6bc25aeaa2e1 +size 1753185696 diff --git a/elle-qwen-3b.Q2_K.gguf b/elle-qwen-3b.Q2_K.gguf new file mode 100644 index 0000000..b137b08 --- /dev/null +++ b/elle-qwen-3b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58a09e1384a49da9cc8d4286ca37a4a024fd7f0a97c31350570da11784ce0d2d +size 1274756512 diff --git a/elle-qwen-3b.Q3_K_L.gguf b/elle-qwen-3b.Q3_K_L.gguf new file mode 100644 index 0000000..1af07b1 --- /dev/null +++ b/elle-qwen-3b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2564523a0a89c664952000fd1087be6ef473ac11dc9f307d2b395529f8130a7b +size 1707392416 diff --git a/elle-qwen-3b.Q3_K_M.gguf b/elle-qwen-3b.Q3_K_M.gguf new file mode 100644 index 0000000..f49921c --- /dev/null +++ b/elle-qwen-3b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2631c621db0dbb209fb2ce87ffde5f5e46ed6fb766eeec1bae46baaf679052f9 +size 1590476192 diff --git a/elle-qwen-3b.Q3_K_S.gguf b/elle-qwen-3b.Q3_K_S.gguf new file mode 100644 index 0000000..560abd3 --- /dev/null +++ b/elle-qwen-3b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24179e8eb3b27a6f02add7d497a09d9944473a125b9687568c19e18a756d552b +size 1454357920 diff --git a/elle-qwen-3b.Q4_K_M.gguf b/elle-qwen-3b.Q4_K_M.gguf new file mode 100644 index 0000000..0afdb47 --- /dev/null +++ b/elle-qwen-3b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:405664559e981f0b4f5d2d28a22cacd48e0aa93be31c8f4a6060a9c918603c89 +size 1929903520 diff --git a/elle-qwen-3b.Q4_K_S.gguf b/elle-qwen-3b.Q4_K_S.gguf new file mode 100644 index 0000000..f97e925 --- /dev/null +++ b/elle-qwen-3b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25432550ea4f8f920ac6f1f029264d793145f6a202d4451580963b76a3d8f97d +size 1834384800 diff --git a/elle-qwen-3b.Q5_K_M.gguf b/elle-qwen-3b.Q5_K_M.gguf new file mode 100644 index 0000000..24c84b2 --- /dev/null +++ b/elle-qwen-3b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15d80aa759a2076ffbf030e3a54a61d089365b1c0c3f4674f5e817bb2934b78e +size 2224815520 diff --git a/elle-qwen-3b.Q5_K_S.gguf b/elle-qwen-3b.Q5_K_S.gguf new file mode 100644 index 0000000..e2dab40 --- /dev/null +++ b/elle-qwen-3b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec425af30ee8602d7b35cb2eaca7fbe8b0a48b4d3293f6181a0c40c630bd8219 +size 2169666976 diff --git a/elle-qwen-3b.Q6_K.gguf b/elle-qwen-3b.Q6_K.gguf new file mode 100644 index 0000000..ffa8357 --- /dev/null +++ b/elle-qwen-3b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86d8bd848cd8582388dd0ed1547ab5f6c05b9126f7c8d3ef114c2814969c00ca +size 2538159520 diff --git a/elle-qwen-3b.Q8_0.gguf b/elle-qwen-3b.Q8_0.gguf new file mode 100644 index 0000000..41cd061 --- /dev/null +++ b/elle-qwen-3b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c18885acc41520e5eb5ca23daee53631866550569d79a5dd8398cbcd6083704 +size 3285476768 diff --git a/elle-qwen-3b.f16.gguf b/elle-qwen-3b.f16.gguf new file mode 100644 index 0000000..214862f --- /dev/null +++ b/elle-qwen-3b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d33dac324781da2f9a64f9d425c28b14f3cbc562173753f30876179acbf33dc +size 6178317728