commit 68ba400296a4b29763cd7197abc63a646c2b1c6c Author: ModelHub XC Date: Mon Jul 20 14:14:23 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2-1.5b-ETS-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..43a1cdd --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +Qwen2-1.5b-ETS.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5b-ETS.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5b-ETS.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5b-ETS.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5b-ETS.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5b-ETS.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5b-ETS.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5b-ETS.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5b-ETS.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5b-ETS.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5b-ETS.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5b-ETS.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5b-ETS.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5b-ETS.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5b-ETS.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2-1.5b-ETS.IQ3_M.gguf b/Qwen2-1.5b-ETS.IQ3_M.gguf new file mode 100644 index 0000000..1b61457 --- /dev/null +++ b/Qwen2-1.5b-ETS.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a1579eecea9bed83944f46566a65aa6fad0ab72b5de61cf51cc148b360e89e8 +size 776661536 diff --git a/Qwen2-1.5b-ETS.IQ3_S.gguf b/Qwen2-1.5b-ETS.IQ3_S.gguf new file mode 100644 index 0000000..b27abdb --- /dev/null +++ b/Qwen2-1.5b-ETS.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adb5c826a17cb514c5cf73ff500e513a662100ca2778eae0051caee793746360 +size 762404384 diff --git a/Qwen2-1.5b-ETS.IQ3_XS.gguf b/Qwen2-1.5b-ETS.IQ3_XS.gguf new file mode 100644 index 0000000..8603a85 --- /dev/null +++ b/Qwen2-1.5b-ETS.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8b785f200a003c3078cfa58a6010dbe345d2941fcd0738ad7d2e9f6068f9cfc +size 731696672 diff --git a/Qwen2-1.5b-ETS.IQ4_XS.gguf b/Qwen2-1.5b-ETS.IQ4_XS.gguf new file mode 100644 index 0000000..034da53 --- /dev/null +++ b/Qwen2-1.5b-ETS.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f86c754edb4f6579b43de0acac76bcab789078472d4aa31b591128af66d42ac0 +size 902180384 diff --git a/Qwen2-1.5b-ETS.Q2_K.gguf b/Qwen2-1.5b-ETS.Q2_K.gguf new file mode 100644 index 0000000..10a3f36 --- /dev/null +++ b/Qwen2-1.5b-ETS.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:069614b27dad95489894d088ef34d1c290638023692a171a8a971b224a5090e0 +size 676302368 diff --git a/Qwen2-1.5b-ETS.Q3_K_L.gguf b/Qwen2-1.5b-ETS.Q3_K_L.gguf new file mode 100644 index 0000000..703843e --- /dev/null +++ b/Qwen2-1.5b-ETS.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8a3d07e6be2277bc3bbd1d0284cdc65a2c3606447025ce290ea158808317715 +size 880160288 diff --git a/Qwen2-1.5b-ETS.Q3_K_M.gguf b/Qwen2-1.5b-ETS.Q3_K_M.gguf new file mode 100644 index 0000000..a89b669 --- /dev/null +++ b/Qwen2-1.5b-ETS.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb8c11156dbebb1f9216ce67ac524b6ea0f165dd893d3c913833d7ed3435efe4 +size 824176160 diff --git a/Qwen2-1.5b-ETS.Q3_K_S.gguf b/Qwen2-1.5b-ETS.Q3_K_S.gguf new file mode 100644 index 0000000..7011e0c --- /dev/null +++ b/Qwen2-1.5b-ETS.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d54aadd7e13240056f085d7f0ce41f81fb3fc29a440835b56a642f02ff3eb4af +size 760942112 diff --git a/Qwen2-1.5b-ETS.Q4_K_M.gguf b/Qwen2-1.5b-ETS.Q4_K_M.gguf new file mode 100644 index 0000000..f4219df --- /dev/null +++ b/Qwen2-1.5b-ETS.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0a4cfdd73d45528b9125dee70ba374e1a50730e0d00c2074f08a2a68710b6cf +size 986045984 diff --git a/Qwen2-1.5b-ETS.Q4_K_S.gguf b/Qwen2-1.5b-ETS.Q4_K_S.gguf new file mode 100644 index 0000000..ace03e2 --- /dev/null +++ b/Qwen2-1.5b-ETS.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74c4d8323eaf0a62dc2b29c69e736d3c863ff407b4a89cf54b29fbfeee92340b +size 940310048 diff --git a/Qwen2-1.5b-ETS.Q5_K_M.gguf b/Qwen2-1.5b-ETS.Q5_K_M.gguf new file mode 100644 index 0000000..296a682 --- /dev/null +++ b/Qwen2-1.5b-ETS.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bfc78ca20f4006b5c9610a3cc0a4500c6ba159206d286e34b89588615eb9baa +size 1125047840 diff --git a/Qwen2-1.5b-ETS.Q5_K_S.gguf b/Qwen2-1.5b-ETS.Q5_K_S.gguf new file mode 100644 index 0000000..243f377 --- /dev/null +++ b/Qwen2-1.5b-ETS.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69bd0e0eefe656e52205f431a4ce09c044aa5651d6162f767ef13716520ed207 +size 1098726944 diff --git a/Qwen2-1.5b-ETS.Q6_K.gguf b/Qwen2-1.5b-ETS.Q6_K.gguf new file mode 100644 index 0000000..7b54c05 --- /dev/null +++ b/Qwen2-1.5b-ETS.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a449dc0b78126a997c9f330821ed4e8f258c04b1590d148f19ef42a328b21199 +size 1272737312 diff --git a/Qwen2-1.5b-ETS.Q8_0.gguf b/Qwen2-1.5b-ETS.Q8_0.gguf new file mode 100644 index 0000000..ee3ca19 --- /dev/null +++ b/Qwen2-1.5b-ETS.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4930eec280d3378024582b18cbf8436edd11eb741dc0c70f50d6fca9b27ca240 +size 1646570528 diff --git a/Qwen2-1.5b-ETS.f16.gguf b/Qwen2-1.5b-ETS.f16.gguf new file mode 100644 index 0000000..4429c4c --- /dev/null +++ b/Qwen2-1.5b-ETS.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0ec0cfe6058cfd219d4efc2ee1fc00c6f38eb9cd5fdc6bec8a9409303399966 +size 3093666848 diff --git a/README.md b/README.md new file mode 100644 index 0000000..099518a --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: notmebug/Qwen2-1.5b-ETS +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/notmebug/Qwen2-1.5b-ETS + + +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/Qwen2-1.5b-ETS-GGUF/resolve/main/Qwen2-1.5b-ETS.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5b-ETS-GGUF/resolve/main/Qwen2-1.5b-ETS.IQ3_XS.gguf) | IQ3_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5b-ETS-GGUF/resolve/main/Qwen2-1.5b-ETS.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5b-ETS-GGUF/resolve/main/Qwen2-1.5b-ETS.IQ3_S.gguf) | IQ3_S | 0.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5b-ETS-GGUF/resolve/main/Qwen2-1.5b-ETS.IQ3_M.gguf) | IQ3_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5b-ETS-GGUF/resolve/main/Qwen2-1.5b-ETS.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5b-ETS-GGUF/resolve/main/Qwen2-1.5b-ETS.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5b-ETS-GGUF/resolve/main/Qwen2-1.5b-ETS.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5b-ETS-GGUF/resolve/main/Qwen2-1.5b-ETS.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5b-ETS-GGUF/resolve/main/Qwen2-1.5b-ETS.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5b-ETS-GGUF/resolve/main/Qwen2-1.5b-ETS.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5b-ETS-GGUF/resolve/main/Qwen2-1.5b-ETS.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5b-ETS-GGUF/resolve/main/Qwen2-1.5b-ETS.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5b-ETS-GGUF/resolve/main/Qwen2-1.5b-ETS.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5b-ETS-GGUF/resolve/main/Qwen2-1.5b-ETS.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. + +