commit ed239f954ba27b9ec3132c76079a5304047ac1d7 Author: ModelHub XC Date: Wed Jul 8 17:47:08 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/AAI-1.5B-Thought-16-Bit-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e966678 --- /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 +AAI-1.5B-Thought-16-Bit.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +AAI-1.5B-Thought-16-Bit.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AAI-1.5B-Thought-16-Bit.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AAI-1.5B-Thought-16-Bit.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AAI-1.5B-Thought-16-Bit.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AAI-1.5B-Thought-16-Bit.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AAI-1.5B-Thought-16-Bit.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AAI-1.5B-Thought-16-Bit.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AAI-1.5B-Thought-16-Bit.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AAI-1.5B-Thought-16-Bit.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +AAI-1.5B-Thought-16-Bit.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +AAI-1.5B-Thought-16-Bit.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AAI-1.5B-Thought-16-Bit.IQ4_XS.gguf b/AAI-1.5B-Thought-16-Bit.IQ4_XS.gguf new file mode 100644 index 0000000..16f8e9f --- /dev/null +++ b/AAI-1.5B-Thought-16-Bit.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afb08a4903790bee00126b044a70747ad59c2f1c538a69a4323721fa1614a362 +size 902180704 diff --git a/AAI-1.5B-Thought-16-Bit.Q2_K.gguf b/AAI-1.5B-Thought-16-Bit.Q2_K.gguf new file mode 100644 index 0000000..d54a285 --- /dev/null +++ b/AAI-1.5B-Thought-16-Bit.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bce8ce79c45bbb7192f6da1d44be866b47cab14e50fd06f637ee927fe2993d5 +size 676302688 diff --git a/AAI-1.5B-Thought-16-Bit.Q3_K_L.gguf b/AAI-1.5B-Thought-16-Bit.Q3_K_L.gguf new file mode 100644 index 0000000..96c5553 --- /dev/null +++ b/AAI-1.5B-Thought-16-Bit.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7adabab5ca89e5e55063d6bae3bcd814481e5bb72f5ec652bed926729009cf99 +size 880160608 diff --git a/AAI-1.5B-Thought-16-Bit.Q3_K_M.gguf b/AAI-1.5B-Thought-16-Bit.Q3_K_M.gguf new file mode 100644 index 0000000..c2abc14 --- /dev/null +++ b/AAI-1.5B-Thought-16-Bit.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3bdb15b79601e8bbcfacfbf9446c32f1d3007429a7e2ec0333588c65dc2dc92 +size 824176480 diff --git a/AAI-1.5B-Thought-16-Bit.Q3_K_S.gguf b/AAI-1.5B-Thought-16-Bit.Q3_K_S.gguf new file mode 100644 index 0000000..b114e76 --- /dev/null +++ b/AAI-1.5B-Thought-16-Bit.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:249a9cb0fe012d545c37ba28f77a107cf4cf24a3f9c765ff9013e64dcb39a8cc +size 760942432 diff --git a/AAI-1.5B-Thought-16-Bit.Q4_K_M.gguf b/AAI-1.5B-Thought-16-Bit.Q4_K_M.gguf new file mode 100644 index 0000000..7638d42 --- /dev/null +++ b/AAI-1.5B-Thought-16-Bit.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2ff1b1f9dec76b7cadb678fba87a39ec052fb1656a601294096e2bbb1dc2c57 +size 986046304 diff --git a/AAI-1.5B-Thought-16-Bit.Q4_K_S.gguf b/AAI-1.5B-Thought-16-Bit.Q4_K_S.gguf new file mode 100644 index 0000000..6873431 --- /dev/null +++ b/AAI-1.5B-Thought-16-Bit.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03962d687ecf9adc2a27b04b5714a19456526b2038a3b24f005710c020d20695 +size 940310368 diff --git a/AAI-1.5B-Thought-16-Bit.Q5_K_M.gguf b/AAI-1.5B-Thought-16-Bit.Q5_K_M.gguf new file mode 100644 index 0000000..32381b1 --- /dev/null +++ b/AAI-1.5B-Thought-16-Bit.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3218272bb78b441ba191d5041aa8890357d7cef6918a9dd125d81c3ef0f9bc5b +size 1125048160 diff --git a/AAI-1.5B-Thought-16-Bit.Q5_K_S.gguf b/AAI-1.5B-Thought-16-Bit.Q5_K_S.gguf new file mode 100644 index 0000000..8e4ec90 --- /dev/null +++ b/AAI-1.5B-Thought-16-Bit.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:793a7bdfc3f64ec9542ad7e5938754e63f1bb5a4bf0882e18c538eebe987166c +size 1098727264 diff --git a/AAI-1.5B-Thought-16-Bit.Q6_K.gguf b/AAI-1.5B-Thought-16-Bit.Q6_K.gguf new file mode 100644 index 0000000..a10c942 --- /dev/null +++ b/AAI-1.5B-Thought-16-Bit.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a680cd9164a1213df28533632e08653bc33f54b8879e5828fb64fbc42c397df +size 1272737632 diff --git a/AAI-1.5B-Thought-16-Bit.Q8_0.gguf b/AAI-1.5B-Thought-16-Bit.Q8_0.gguf new file mode 100644 index 0000000..a338a4f --- /dev/null +++ b/AAI-1.5B-Thought-16-Bit.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c19e2396dc5a59f66cea05692fb92553e087ff721529dc0a019d77dadf268a71 +size 1646570848 diff --git a/AAI-1.5B-Thought-16-Bit.f16.gguf b/AAI-1.5B-Thought-16-Bit.f16.gguf new file mode 100644 index 0000000..b1ae12b --- /dev/null +++ b/AAI-1.5B-Thought-16-Bit.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ee8f88c036df9d3eb4822781ec32ae96454a69249844ece3e45db5b28e6758c +size 3093667168 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9443940 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: alphaaico/AAI-1.5B-Thought-16-Bit +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- gguf +--- +## About + + + + + + +static quants of https://huggingface.co/alphaaico/AAI-1.5B-Thought-16-Bit + + +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/AAI-1.5B-Thought-16-Bit-GGUF/resolve/main/AAI-1.5B-Thought-16-Bit.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/AAI-1.5B-Thought-16-Bit-GGUF/resolve/main/AAI-1.5B-Thought-16-Bit.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/AAI-1.5B-Thought-16-Bit-GGUF/resolve/main/AAI-1.5B-Thought-16-Bit.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AAI-1.5B-Thought-16-Bit-GGUF/resolve/main/AAI-1.5B-Thought-16-Bit.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/AAI-1.5B-Thought-16-Bit-GGUF/resolve/main/AAI-1.5B-Thought-16-Bit.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/AAI-1.5B-Thought-16-Bit-GGUF/resolve/main/AAI-1.5B-Thought-16-Bit.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AAI-1.5B-Thought-16-Bit-GGUF/resolve/main/AAI-1.5B-Thought-16-Bit.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AAI-1.5B-Thought-16-Bit-GGUF/resolve/main/AAI-1.5B-Thought-16-Bit.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/AAI-1.5B-Thought-16-Bit-GGUF/resolve/main/AAI-1.5B-Thought-16-Bit.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/AAI-1.5B-Thought-16-Bit-GGUF/resolve/main/AAI-1.5B-Thought-16-Bit.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/AAI-1.5B-Thought-16-Bit-GGUF/resolve/main/AAI-1.5B-Thought-16-Bit.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/AAI-1.5B-Thought-16-Bit-GGUF/resolve/main/AAI-1.5B-Thought-16-Bit.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. 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. + +