commit 845cf1434f6b7f08c3c87e21132c4e1d4841a910 Author: ModelHub XC Date: Thu Jun 4 20:08:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Atomight-V2.1-0.5B-Inference-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b26037d --- /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 +Atomight-V2.1-0.5B-Inference.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Atomight-V2.1-0.5B-Inference.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Atomight-V2.1-0.5B-Inference.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Atomight-V2.1-0.5B-Inference.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Atomight-V2.1-0.5B-Inference.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Atomight-V2.1-0.5B-Inference.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Atomight-V2.1-0.5B-Inference.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Atomight-V2.1-0.5B-Inference.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Atomight-V2.1-0.5B-Inference.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Atomight-V2.1-0.5B-Inference.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Atomight-V2.1-0.5B-Inference.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Atomight-V2.1-0.5B-Inference.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Atomight-V2.1-0.5B-Inference.IQ4_XS.gguf b/Atomight-V2.1-0.5B-Inference.IQ4_XS.gguf new file mode 100644 index 0000000..09bdfa8 --- /dev/null +++ b/Atomight-V2.1-0.5B-Inference.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:916d521d4f812728d231a620ac1e175ac1859e88610b20aa0e841a737d49d2c3 +size 351446880 diff --git a/Atomight-V2.1-0.5B-Inference.Q2_K.gguf b/Atomight-V2.1-0.5B-Inference.Q2_K.gguf new file mode 100644 index 0000000..70355cb --- /dev/null +++ b/Atomight-V2.1-0.5B-Inference.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56a32a744269b8ec04b4619ea0e2e5fdb8a32d77f04db9028d7b1a1151b96ee3 +size 338608992 diff --git a/Atomight-V2.1-0.5B-Inference.Q3_K_L.gguf b/Atomight-V2.1-0.5B-Inference.Q3_K_L.gguf new file mode 100644 index 0000000..a7ae021 --- /dev/null +++ b/Atomight-V2.1-0.5B-Inference.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fd2db296e277290955b339e27a8813c834590f46d0c85e851c0044c3a3a2c63 +size 369359712 diff --git a/Atomight-V2.1-0.5B-Inference.Q3_K_M.gguf b/Atomight-V2.1-0.5B-Inference.Q3_K_M.gguf new file mode 100644 index 0000000..c6fe134 --- /dev/null +++ b/Atomight-V2.1-0.5B-Inference.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4b1a995ec6d8fe8957c103a4be56dccd086e645ff1d185292048345003b3319 +size 355468128 diff --git a/Atomight-V2.1-0.5B-Inference.Q3_K_S.gguf b/Atomight-V2.1-0.5B-Inference.Q3_K_S.gguf new file mode 100644 index 0000000..a7cffcd --- /dev/null +++ b/Atomight-V2.1-0.5B-Inference.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f8fa202e5579d4c3d93f4b5549a41838aa1b724c6527aa27a9591f24dca798c +size 338264928 diff --git a/Atomight-V2.1-0.5B-Inference.Q4_K_M.gguf b/Atomight-V2.1-0.5B-Inference.Q4_K_M.gguf new file mode 100644 index 0000000..8681175 --- /dev/null +++ b/Atomight-V2.1-0.5B-Inference.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aceead6a07a947bd844c39def1131f075962f753de3bd74151c9201eadebfb9a +size 397809504 diff --git a/Atomight-V2.1-0.5B-Inference.Q4_K_S.gguf b/Atomight-V2.1-0.5B-Inference.Q4_K_S.gguf new file mode 100644 index 0000000..1cc24b6 --- /dev/null +++ b/Atomight-V2.1-0.5B-Inference.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf24229227868eb53757401c83cefcc158a839cc1dee32d0ad21118e8c930bde +size 385473376 diff --git a/Atomight-V2.1-0.5B-Inference.Q5_K_M.gguf b/Atomight-V2.1-0.5B-Inference.Q5_K_M.gguf new file mode 100644 index 0000000..8a8d2ce --- /dev/null +++ b/Atomight-V2.1-0.5B-Inference.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22e56fe68e24be0cffa658d6820e7ae31b713fb18ef3da28f4a806a2b45c8334 +size 420087648 diff --git a/Atomight-V2.1-0.5B-Inference.Q5_K_S.gguf b/Atomight-V2.1-0.5B-Inference.Q5_K_S.gguf new file mode 100644 index 0000000..d7eec44 --- /dev/null +++ b/Atomight-V2.1-0.5B-Inference.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9670599d046f050097c2bb433d0011c316748753a0cdd9d98e66b9ca975f0273 +size 412711776 diff --git a/Atomight-V2.1-0.5B-Inference.Q6_K.gguf b/Atomight-V2.1-0.5B-Inference.Q6_K.gguf new file mode 100644 index 0000000..23896f1 --- /dev/null +++ b/Atomight-V2.1-0.5B-Inference.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc85ba78eee10d3a10cd4266170639d117fff9e956b3bf312dec6a87e3915144 +size 505738080 diff --git a/Atomight-V2.1-0.5B-Inference.Q8_0.gguf b/Atomight-V2.1-0.5B-Inference.Q8_0.gguf new file mode 100644 index 0000000..a4e60b9 --- /dev/null +++ b/Atomight-V2.1-0.5B-Inference.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea13a4d6c161a89a869daceb1ee7ed2a282718925463820543cf0641ceee800d +size 531069792 diff --git a/Atomight-V2.1-0.5B-Inference.f16.gguf b/Atomight-V2.1-0.5B-Inference.f16.gguf new file mode 100644 index 0000000..56af641 --- /dev/null +++ b/Atomight-V2.1-0.5B-Inference.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9fcfd4ee4209d472f63a67661db9f0c14084ef8628ea1de843602f1fee98be0 +size 994158432 diff --git a/README.md b/README.md new file mode 100644 index 0000000..72547e5 --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: NovatasticRoScript/Atomight-V2.1-0.5B-Inference +datasets: +- openai/gsm8k +- openai/openai_humaneval +- cais/mmlu +- allenai/ai2_arc +- bespokelabs/Bespoke-Stratos-17k +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation +- causal-lm +- grpo +- reasoning +- reinforcement-learning +- mini-llm +- text-generation-inference +- lm-evaluation-harness +--- +## About + + + + + + + + + +static quants of https://huggingface.co/NovatasticRoScript/Atomight-V2.1-0.5B-Inference + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Atomight-V2.1-0.5B-Inference-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Atomight-V2.1-0.5B-Inference-i1-GGUF +## 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/Atomight-V2.1-0.5B-Inference-GGUF/resolve/main/Atomight-V2.1-0.5B-Inference.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Atomight-V2.1-0.5B-Inference-GGUF/resolve/main/Atomight-V2.1-0.5B-Inference.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Atomight-V2.1-0.5B-Inference-GGUF/resolve/main/Atomight-V2.1-0.5B-Inference.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Atomight-V2.1-0.5B-Inference-GGUF/resolve/main/Atomight-V2.1-0.5B-Inference.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Atomight-V2.1-0.5B-Inference-GGUF/resolve/main/Atomight-V2.1-0.5B-Inference.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Atomight-V2.1-0.5B-Inference-GGUF/resolve/main/Atomight-V2.1-0.5B-Inference.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Atomight-V2.1-0.5B-Inference-GGUF/resolve/main/Atomight-V2.1-0.5B-Inference.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Atomight-V2.1-0.5B-Inference-GGUF/resolve/main/Atomight-V2.1-0.5B-Inference.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Atomight-V2.1-0.5B-Inference-GGUF/resolve/main/Atomight-V2.1-0.5B-Inference.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Atomight-V2.1-0.5B-Inference-GGUF/resolve/main/Atomight-V2.1-0.5B-Inference.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Atomight-V2.1-0.5B-Inference-GGUF/resolve/main/Atomight-V2.1-0.5B-Inference.Q8_0.gguf) | Q8_0 | 0.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Atomight-V2.1-0.5B-Inference-GGUF/resolve/main/Atomight-V2.1-0.5B-Inference.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. + +