commit bb7415e8386de9246e37015816d2ecb30f0cbbfa Author: ModelHub XC Date: Thu May 7 05:47:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Pawa-Base-0.5B-Qwen-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..dc80e9f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Pawa-Base-0.5B-Qwen.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Pawa-Base-0.5B-Qwen.f16.gguf filter=lfs diff=lfs merge=lfs -text +Pawa-Base-0.5B-Qwen.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Pawa-Base-0.5B-Qwen.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Pawa-Base-0.5B-Qwen.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Pawa-Base-0.5B-Qwen.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Pawa-Base-0.5B-Qwen.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Pawa-Base-0.5B-Qwen.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Pawa-Base-0.5B-Qwen.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Pawa-Base-0.5B-Qwen.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Pawa-Base-0.5B-Qwen.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Pawa-Base-0.5B-Qwen.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Pawa-Base-0.5B-Qwen.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Pawa-Base-0.5B-Qwen.IQ4_XS.gguf b/Pawa-Base-0.5B-Qwen.IQ4_XS.gguf new file mode 100644 index 0000000..b17922f --- /dev/null +++ b/Pawa-Base-0.5B-Qwen.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cb8d90a90dfb2e5009265d959d23517b504ab4e4ed379da4e439c1534b87246 +size 428019264 diff --git a/Pawa-Base-0.5B-Qwen.Q2_K.gguf b/Pawa-Base-0.5B-Qwen.Q2_K.gguf new file mode 100644 index 0000000..0ac08c1 --- /dev/null +++ b/Pawa-Base-0.5B-Qwen.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93efaded95c0e50ef87df25220295975f57d5e2a940bc02bce6e961cde0fd23b +size 415181376 diff --git a/Pawa-Base-0.5B-Qwen.Q3_K_L.gguf b/Pawa-Base-0.5B-Qwen.Q3_K_L.gguf new file mode 100644 index 0000000..3a0695d --- /dev/null +++ b/Pawa-Base-0.5B-Qwen.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43c085c1a6a02c53be51d85c0cff553bcae875c30f7c03fee4e206c852757f30 +size 445932096 diff --git a/Pawa-Base-0.5B-Qwen.Q3_K_M.gguf b/Pawa-Base-0.5B-Qwen.Q3_K_M.gguf new file mode 100644 index 0000000..256c876 --- /dev/null +++ b/Pawa-Base-0.5B-Qwen.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eea58040482d8f6b8c83168ad6a2dec4d52b0693c2a3fbd978a39d981dbaa9e7 +size 432040512 diff --git a/Pawa-Base-0.5B-Qwen.Q3_K_S.gguf b/Pawa-Base-0.5B-Qwen.Q3_K_S.gguf new file mode 100644 index 0000000..d0d4388 --- /dev/null +++ b/Pawa-Base-0.5B-Qwen.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:322a4d86dac3c1b50b42092d04112a2144075f528adfff290ca9a548f44c6996 +size 414837312 diff --git a/Pawa-Base-0.5B-Qwen.Q4_0_4_4.gguf b/Pawa-Base-0.5B-Qwen.Q4_0_4_4.gguf new file mode 100644 index 0000000..e53d628 --- /dev/null +++ b/Pawa-Base-0.5B-Qwen.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9915e1f9dd8497526ec2b605f825246f081ca9dbbc7453c54318b7b88cfb57a4 +size 428728896 diff --git a/Pawa-Base-0.5B-Qwen.Q4_K_M.gguf b/Pawa-Base-0.5B-Qwen.Q4_K_M.gguf new file mode 100644 index 0000000..d3fa418 --- /dev/null +++ b/Pawa-Base-0.5B-Qwen.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4f4c15ba0c13198cb1ba1542c8d6897f14a383bb5cc7d9ac9f3a612c09110ab +size 491398720 diff --git a/Pawa-Base-0.5B-Qwen.Q4_K_S.gguf b/Pawa-Base-0.5B-Qwen.Q4_K_S.gguf new file mode 100644 index 0000000..64fab4c --- /dev/null +++ b/Pawa-Base-0.5B-Qwen.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89f91b7759d42d23992e7bcbf7fa1aff232834a15d87c45417920ab15aa0da58 +size 479062592 diff --git a/Pawa-Base-0.5B-Qwen.Q5_K_M.gguf b/Pawa-Base-0.5B-Qwen.Q5_K_M.gguf new file mode 100644 index 0000000..8ef1573 --- /dev/null +++ b/Pawa-Base-0.5B-Qwen.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00205acc73f9712856bd0ec8d77cf5ff4492cfbd4702f71920efc09362fb2783 +size 522185280 diff --git a/Pawa-Base-0.5B-Qwen.Q5_K_S.gguf b/Pawa-Base-0.5B-Qwen.Q5_K_S.gguf new file mode 100644 index 0000000..e01ac34 --- /dev/null +++ b/Pawa-Base-0.5B-Qwen.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51c2bee207d773f39b51d6a9d3d276105d56920536353fabadf6933c29b18243 +size 514809408 diff --git a/Pawa-Base-0.5B-Qwen.Q6_K.gguf b/Pawa-Base-0.5B-Qwen.Q6_K.gguf new file mode 100644 index 0000000..2f73306 --- /dev/null +++ b/Pawa-Base-0.5B-Qwen.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bbc53e34ae1f34b114197ed42bf1dcf787c9282ad5ad42debbb4b66bc9a4748 +size 650377792 diff --git a/Pawa-Base-0.5B-Qwen.Q8_0.gguf b/Pawa-Base-0.5B-Qwen.Q8_0.gguf new file mode 100644 index 0000000..af274a8 --- /dev/null +++ b/Pawa-Base-0.5B-Qwen.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b082f3db1531e437eebb4f92333275b206cb70e03c269336e622e812435e50e1 +size 675709504 diff --git a/Pawa-Base-0.5B-Qwen.f16.gguf b/Pawa-Base-0.5B-Qwen.f16.gguf new file mode 100644 index 0000000..aef0968 --- /dev/null +++ b/Pawa-Base-0.5B-Qwen.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e09667d7eeec0433224e43978f0d6649659d38ed3e6e716685774c061db4b780 +size 1266424384 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7190ae8 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: sartifyllc/Pawa-Base-0.5B-Qwen +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/sartifyllc/Pawa-Base-0.5B-Qwen + + +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/Pawa-Base-0.5B-Qwen-GGUF/resolve/main/Pawa-Base-0.5B-Qwen.Q3_K_S.gguf) | Q3_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Pawa-Base-0.5B-Qwen-GGUF/resolve/main/Pawa-Base-0.5B-Qwen.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Pawa-Base-0.5B-Qwen-GGUF/resolve/main/Pawa-Base-0.5B-Qwen.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Pawa-Base-0.5B-Qwen-GGUF/resolve/main/Pawa-Base-0.5B-Qwen.Q4_0_4_4.gguf) | Q4_0_4_4 | 0.5 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Pawa-Base-0.5B-Qwen-GGUF/resolve/main/Pawa-Base-0.5B-Qwen.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Pawa-Base-0.5B-Qwen-GGUF/resolve/main/Pawa-Base-0.5B-Qwen.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Pawa-Base-0.5B-Qwen-GGUF/resolve/main/Pawa-Base-0.5B-Qwen.Q4_K_S.gguf) | Q4_K_S | 0.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Pawa-Base-0.5B-Qwen-GGUF/resolve/main/Pawa-Base-0.5B-Qwen.Q4_K_M.gguf) | Q4_K_M | 0.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Pawa-Base-0.5B-Qwen-GGUF/resolve/main/Pawa-Base-0.5B-Qwen.Q5_K_S.gguf) | Q5_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Pawa-Base-0.5B-Qwen-GGUF/resolve/main/Pawa-Base-0.5B-Qwen.Q5_K_M.gguf) | Q5_K_M | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Pawa-Base-0.5B-Qwen-GGUF/resolve/main/Pawa-Base-0.5B-Qwen.Q6_K.gguf) | Q6_K | 0.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Pawa-Base-0.5B-Qwen-GGUF/resolve/main/Pawa-Base-0.5B-Qwen.Q8_0.gguf) | Q8_0 | 0.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Pawa-Base-0.5B-Qwen-GGUF/resolve/main/Pawa-Base-0.5B-Qwen.f16.gguf) | f16 | 1.4 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +