commit f722988ca75c5ddcf5996b8f85f18e2f717bc05a Author: ModelHub XC Date: Tue Jul 21 00:56:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2-1.5B-Instruct-Exp-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..dfdc7db --- /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-Instruct-Exp.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct-Exp.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct-Exp.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct-Exp.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct-Exp.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct-Exp.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct-Exp.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct-Exp.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct-Exp.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct-Exp.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct-Exp.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct-Exp.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct-Exp.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct-Exp.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-1.5B-Instruct-Exp.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2-1.5B-Instruct-Exp.IQ3_M.gguf b/Qwen2-1.5B-Instruct-Exp.IQ3_M.gguf new file mode 100644 index 0000000..735c596 --- /dev/null +++ b/Qwen2-1.5B-Instruct-Exp.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3657e267b00feb49c5507d5e91d943c0331c99fd7a3ac6e28f8fc4d1e2241d1a +size 776661760 diff --git a/Qwen2-1.5B-Instruct-Exp.IQ3_S.gguf b/Qwen2-1.5B-Instruct-Exp.IQ3_S.gguf new file mode 100644 index 0000000..1f8294a --- /dev/null +++ b/Qwen2-1.5B-Instruct-Exp.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59d384094d886ff08ccfcd5f6ebee6012725afd34b535f21879e9dba3c723323 +size 762404608 diff --git a/Qwen2-1.5B-Instruct-Exp.IQ3_XS.gguf b/Qwen2-1.5B-Instruct-Exp.IQ3_XS.gguf new file mode 100644 index 0000000..cf962e7 --- /dev/null +++ b/Qwen2-1.5B-Instruct-Exp.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18698f2dec9884868e550cb5f20598c1e71a0c05d5d0f9d2a6bf1c0160ad61d6 +size 731696896 diff --git a/Qwen2-1.5B-Instruct-Exp.IQ4_XS.gguf b/Qwen2-1.5B-Instruct-Exp.IQ4_XS.gguf new file mode 100644 index 0000000..0984c19 --- /dev/null +++ b/Qwen2-1.5B-Instruct-Exp.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b3410401561c276b536d08bc42a773575c945d027af547ee3a1bd35ed448adc +size 902180608 diff --git a/Qwen2-1.5B-Instruct-Exp.Q2_K.gguf b/Qwen2-1.5B-Instruct-Exp.Q2_K.gguf new file mode 100644 index 0000000..4c06ca8 --- /dev/null +++ b/Qwen2-1.5B-Instruct-Exp.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af3f2059c668d028aaf05bf7b97346068c906d99ce87b21df65af033c4bf60bb +size 676302592 diff --git a/Qwen2-1.5B-Instruct-Exp.Q3_K_L.gguf b/Qwen2-1.5B-Instruct-Exp.Q3_K_L.gguf new file mode 100644 index 0000000..2c6715e --- /dev/null +++ b/Qwen2-1.5B-Instruct-Exp.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f885f89fb2699919615838fb67f843ba4dbf27b07f4eccbdfce4cf832bda12e7 +size 880160512 diff --git a/Qwen2-1.5B-Instruct-Exp.Q3_K_M.gguf b/Qwen2-1.5B-Instruct-Exp.Q3_K_M.gguf new file mode 100644 index 0000000..861d046 --- /dev/null +++ b/Qwen2-1.5B-Instruct-Exp.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:febf664cc267bbf571695dfb4ce0271fe02de261ec5c919d3d58e7c3599ef8f0 +size 824176384 diff --git a/Qwen2-1.5B-Instruct-Exp.Q3_K_S.gguf b/Qwen2-1.5B-Instruct-Exp.Q3_K_S.gguf new file mode 100644 index 0000000..a512953 --- /dev/null +++ b/Qwen2-1.5B-Instruct-Exp.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ad11455404e0cdd40af963d1d2853343adff348203717a071aa9b5625eed695 +size 760942336 diff --git a/Qwen2-1.5B-Instruct-Exp.Q4_K_M.gguf b/Qwen2-1.5B-Instruct-Exp.Q4_K_M.gguf new file mode 100644 index 0000000..dc6066b --- /dev/null +++ b/Qwen2-1.5B-Instruct-Exp.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:812c75257c8c861df4449f681b9cae54c249ce79af667ac6b53b0ce685f40c37 +size 986046208 diff --git a/Qwen2-1.5B-Instruct-Exp.Q4_K_S.gguf b/Qwen2-1.5B-Instruct-Exp.Q4_K_S.gguf new file mode 100644 index 0000000..8f2dee8 --- /dev/null +++ b/Qwen2-1.5B-Instruct-Exp.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f4fb02c41b0840b9f0089654bb8f13b2273dfcdc2e2dcf95e1ecf212c16f58e +size 940310272 diff --git a/Qwen2-1.5B-Instruct-Exp.Q5_K_M.gguf b/Qwen2-1.5B-Instruct-Exp.Q5_K_M.gguf new file mode 100644 index 0000000..7e0b439 --- /dev/null +++ b/Qwen2-1.5B-Instruct-Exp.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6210c6f520595e49beac98739c3a7befe83331ca8f622c988341bab2e6e412f6 +size 1125048064 diff --git a/Qwen2-1.5B-Instruct-Exp.Q5_K_S.gguf b/Qwen2-1.5B-Instruct-Exp.Q5_K_S.gguf new file mode 100644 index 0000000..311f416 --- /dev/null +++ b/Qwen2-1.5B-Instruct-Exp.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d3307ff37c291cc8a3f8b80cf5b30acf4cbeb41f61bea6919e962d4035a7eab +size 1098727168 diff --git a/Qwen2-1.5B-Instruct-Exp.Q6_K.gguf b/Qwen2-1.5B-Instruct-Exp.Q6_K.gguf new file mode 100644 index 0000000..274f543 --- /dev/null +++ b/Qwen2-1.5B-Instruct-Exp.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:280c77c9cb2def67a7b58b7762009fc870a509aae69f329beb71f1561e350897 +size 1272737536 diff --git a/Qwen2-1.5B-Instruct-Exp.Q8_0.gguf b/Qwen2-1.5B-Instruct-Exp.Q8_0.gguf new file mode 100644 index 0000000..cbf5d5d --- /dev/null +++ b/Qwen2-1.5B-Instruct-Exp.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b135d78a6e28d6b1ed0f0a52f5180f1853f87018227cee1d904a4b736ba49b6 +size 1646570752 diff --git a/Qwen2-1.5B-Instruct-Exp.f16.gguf b/Qwen2-1.5B-Instruct-Exp.f16.gguf new file mode 100644 index 0000000..9a68e9f --- /dev/null +++ b/Qwen2-1.5B-Instruct-Exp.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63263a0b5e8cb5094b31af74fedb71eb985cb1134abbbe7bab0c40a4338c9ce6 +size 3093667072 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1b8d1a2 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: alibaba-pai/Qwen2-1.5B-Instruct-Exp +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/alibaba-pai/Qwen2-1.5B-Instruct-Exp + + +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-Instruct-Exp-GGUF/resolve/main/Qwen2-1.5B-Instruct-Exp.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-Exp-GGUF/resolve/main/Qwen2-1.5B-Instruct-Exp.IQ3_XS.gguf) | IQ3_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-Exp-GGUF/resolve/main/Qwen2-1.5B-Instruct-Exp.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-Exp-GGUF/resolve/main/Qwen2-1.5B-Instruct-Exp.IQ3_S.gguf) | IQ3_S | 0.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-Exp-GGUF/resolve/main/Qwen2-1.5B-Instruct-Exp.IQ3_M.gguf) | IQ3_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-Exp-GGUF/resolve/main/Qwen2-1.5B-Instruct-Exp.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-Exp-GGUF/resolve/main/Qwen2-1.5B-Instruct-Exp.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-Exp-GGUF/resolve/main/Qwen2-1.5B-Instruct-Exp.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-Exp-GGUF/resolve/main/Qwen2-1.5B-Instruct-Exp.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-Exp-GGUF/resolve/main/Qwen2-1.5B-Instruct-Exp.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-Exp-GGUF/resolve/main/Qwen2-1.5B-Instruct-Exp.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-Exp-GGUF/resolve/main/Qwen2-1.5B-Instruct-Exp.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-Exp-GGUF/resolve/main/Qwen2-1.5B-Instruct-Exp.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-Exp-GGUF/resolve/main/Qwen2-1.5B-Instruct-Exp.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-1.5B-Instruct-Exp-GGUF/resolve/main/Qwen2-1.5B-Instruct-Exp.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. + +