commit 61da49a7f781a5f3751144f5cad92937d9e2783d Author: ModelHub XC Date: Sat May 23 05:30:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DATA-AI_Chat_4_Thinking_0.5B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fd96004 --- /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 +DATA-AI_Chat_4_Thinking_0.5B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +DATA-AI_Chat_4_Thinking_0.5B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DATA-AI_Chat_4_Thinking_0.5B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DATA-AI_Chat_4_Thinking_0.5B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DATA-AI_Chat_4_Thinking_0.5B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DATA-AI_Chat_4_Thinking_0.5B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DATA-AI_Chat_4_Thinking_0.5B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DATA-AI_Chat_4_Thinking_0.5B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DATA-AI_Chat_4_Thinking_0.5B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DATA-AI_Chat_4_Thinking_0.5B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DATA-AI_Chat_4_Thinking_0.5B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DATA-AI_Chat_4_Thinking_0.5B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DATA-AI_Chat_4_Thinking_0.5B.IQ4_XS.gguf b/DATA-AI_Chat_4_Thinking_0.5B.IQ4_XS.gguf new file mode 100644 index 0000000..f621fc5 --- /dev/null +++ b/DATA-AI_Chat_4_Thinking_0.5B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fd6270decdfd58615642628d36aef23f15c48dfdeae1dd56aca27eab1b8b071 +size 351445344 diff --git a/DATA-AI_Chat_4_Thinking_0.5B.Q2_K.gguf b/DATA-AI_Chat_4_Thinking_0.5B.Q2_K.gguf new file mode 100644 index 0000000..0f4847d --- /dev/null +++ b/DATA-AI_Chat_4_Thinking_0.5B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9479cd278c184e4bc1cbfca4e2b3742dca00996a91caefa2a4de614817f31b00 +size 338607456 diff --git a/DATA-AI_Chat_4_Thinking_0.5B.Q3_K_L.gguf b/DATA-AI_Chat_4_Thinking_0.5B.Q3_K_L.gguf new file mode 100644 index 0000000..b95dc8f --- /dev/null +++ b/DATA-AI_Chat_4_Thinking_0.5B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22c18b3478c7cb75a5fb6d603ef68e5edf32cea3bde00ab4f36652a4f80f85b6 +size 369358176 diff --git a/DATA-AI_Chat_4_Thinking_0.5B.Q3_K_M.gguf b/DATA-AI_Chat_4_Thinking_0.5B.Q3_K_M.gguf new file mode 100644 index 0000000..8ec2a04 --- /dev/null +++ b/DATA-AI_Chat_4_Thinking_0.5B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b010a38eeee02fe944f06d7ff1b76a9eae2adef7ba4f75f49e26bc7825eb3f65 +size 355466592 diff --git a/DATA-AI_Chat_4_Thinking_0.5B.Q3_K_S.gguf b/DATA-AI_Chat_4_Thinking_0.5B.Q3_K_S.gguf new file mode 100644 index 0000000..5a6bbed --- /dev/null +++ b/DATA-AI_Chat_4_Thinking_0.5B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2ace9bfe442f33381a059f787dc1c561adc1ee38f2c92fd855b3a8c5fc10527 +size 338263392 diff --git a/DATA-AI_Chat_4_Thinking_0.5B.Q4_K_M.gguf b/DATA-AI_Chat_4_Thinking_0.5B.Q4_K_M.gguf new file mode 100644 index 0000000..96b874f --- /dev/null +++ b/DATA-AI_Chat_4_Thinking_0.5B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:139aca150adf33dfdde84646d84833cdfde5b8ef9a8da6502e958ef029e33892 +size 397807968 diff --git a/DATA-AI_Chat_4_Thinking_0.5B.Q4_K_S.gguf b/DATA-AI_Chat_4_Thinking_0.5B.Q4_K_S.gguf new file mode 100644 index 0000000..b633756 --- /dev/null +++ b/DATA-AI_Chat_4_Thinking_0.5B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:462b858610c2bfb6e2f54a65859755c9fc8036b605e29f140618cd2d132358fe +size 385471840 diff --git a/DATA-AI_Chat_4_Thinking_0.5B.Q5_K_M.gguf b/DATA-AI_Chat_4_Thinking_0.5B.Q5_K_M.gguf new file mode 100644 index 0000000..489f316 --- /dev/null +++ b/DATA-AI_Chat_4_Thinking_0.5B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:435e8d2a43a33e73de2936d6e8187d6b1a9c819f811ab025e564d7fa2e93f7c5 +size 420086112 diff --git a/DATA-AI_Chat_4_Thinking_0.5B.Q5_K_S.gguf b/DATA-AI_Chat_4_Thinking_0.5B.Q5_K_S.gguf new file mode 100644 index 0000000..b5d1c3b --- /dev/null +++ b/DATA-AI_Chat_4_Thinking_0.5B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23c81db924c974d55a1b864e0cf8cb0a8dbacc1da4a71fdc794bcf3571a32245 +size 412710240 diff --git a/DATA-AI_Chat_4_Thinking_0.5B.Q6_K.gguf b/DATA-AI_Chat_4_Thinking_0.5B.Q6_K.gguf new file mode 100644 index 0000000..251642e --- /dev/null +++ b/DATA-AI_Chat_4_Thinking_0.5B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a1f60a12ffa99d727b513f0997e275c8077b31d2e7dfb80053e2577954febe2 +size 505736544 diff --git a/DATA-AI_Chat_4_Thinking_0.5B.Q8_0.gguf b/DATA-AI_Chat_4_Thinking_0.5B.Q8_0.gguf new file mode 100644 index 0000000..238d50b --- /dev/null +++ b/DATA-AI_Chat_4_Thinking_0.5B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc929fb25101260286abfec8438c48613c41d909f0b98a3d0139bf105100c4ed +size 531068256 diff --git a/DATA-AI_Chat_4_Thinking_0.5B.f16.gguf b/DATA-AI_Chat_4_Thinking_0.5B.f16.gguf new file mode 100644 index 0000000..3fb1a09 --- /dev/null +++ b/DATA-AI_Chat_4_Thinking_0.5B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19861dd323b483de9c7b5b1f92bc24f06bee0fd0eb779a4ed42bf35b6e37ae5e +size 994156896 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6496af1 --- /dev/null +++ b/README.md @@ -0,0 +1,106 @@ +--- +base_model: Mattimax/DATA-AI_Chat_4_Thinking_0.5B +language: +- it/ +- en +- es +- ru +- de +- pl +- th +- vi +- sv +- bn +- da +- he +- fa +- sk +- id +- nb +- el +- nl +- hu +- eu +- zh +- eo +- ja +- ca +- cs +- bg +- fi +- pt +- tr +- ro +- ar +- uk +- gl +- fr +- ko +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- human-feedback +- data-ai +--- +## About + + + + + + +static quants of https://huggingface.co/Mattimax/DATA-AI_Chat_4_Thinking_0.5B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#DATA-AI_Chat_4_Thinking_0.5B-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/DATA-AI_Chat_4_Thinking_0.5B-GGUF/resolve/main/DATA-AI_Chat_4_Thinking_0.5B.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/DATA-AI_Chat_4_Thinking_0.5B-GGUF/resolve/main/DATA-AI_Chat_4_Thinking_0.5B.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/DATA-AI_Chat_4_Thinking_0.5B-GGUF/resolve/main/DATA-AI_Chat_4_Thinking_0.5B.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/DATA-AI_Chat_4_Thinking_0.5B-GGUF/resolve/main/DATA-AI_Chat_4_Thinking_0.5B.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DATA-AI_Chat_4_Thinking_0.5B-GGUF/resolve/main/DATA-AI_Chat_4_Thinking_0.5B.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/DATA-AI_Chat_4_Thinking_0.5B-GGUF/resolve/main/DATA-AI_Chat_4_Thinking_0.5B.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DATA-AI_Chat_4_Thinking_0.5B-GGUF/resolve/main/DATA-AI_Chat_4_Thinking_0.5B.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DATA-AI_Chat_4_Thinking_0.5B-GGUF/resolve/main/DATA-AI_Chat_4_Thinking_0.5B.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/DATA-AI_Chat_4_Thinking_0.5B-GGUF/resolve/main/DATA-AI_Chat_4_Thinking_0.5B.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/DATA-AI_Chat_4_Thinking_0.5B-GGUF/resolve/main/DATA-AI_Chat_4_Thinking_0.5B.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DATA-AI_Chat_4_Thinking_0.5B-GGUF/resolve/main/DATA-AI_Chat_4_Thinking_0.5B.Q8_0.gguf) | Q8_0 | 0.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DATA-AI_Chat_4_Thinking_0.5B-GGUF/resolve/main/DATA-AI_Chat_4_Thinking_0.5B.f16.gguf) | f16 | 1.1 | 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. + +