commit 115a0e1a6a6461255adfaaaf7c1efdd69db0aba3 Author: ModelHub XC Date: Tue Oct 20 04:24:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: PLM-Team/PLM-1.8B-Instruct-gguf Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a71c3a3 --- /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 +PLM-1.8B-Instruct-F16.gguf filter=lfs diff=lfs merge=lfs -text +PLM-1.8B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +PLM-1.8B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +PLM-1.8B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PLM-1.8B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PLM-1.8B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +PLM-1.8B-Instruct-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +PLM-1.8B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PLM-1.8B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PLM-1.8B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +PLM-1.8B-Instruct-Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +PLM-1.8B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PLM-1.8B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PLM-1.8B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +PLM-1.8B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/PLM-1.8B-Instruct-F16.gguf b/PLM-1.8B-Instruct-F16.gguf new file mode 100644 index 0000000..05a2929 --- /dev/null +++ b/PLM-1.8B-Instruct-F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:112d6c52b5352f95d23a68c000d2c540010fbf90172401394c17efd1f080ae94 +size 3657161984 diff --git a/PLM-1.8B-Instruct-Q2_K.gguf b/PLM-1.8B-Instruct-Q2_K.gguf new file mode 100644 index 0000000..5dee32a --- /dev/null +++ b/PLM-1.8B-Instruct-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07847d92227b088736d55157ddf6accd517a27a29de33629f2490a74e3ee6a02 +size 826782976 diff --git a/PLM-1.8B-Instruct-Q3_K_L.gguf b/PLM-1.8B-Instruct-Q3_K_L.gguf new file mode 100644 index 0000000..190034e --- /dev/null +++ b/PLM-1.8B-Instruct-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3ba8ec08a886c6c10b569d4af0579363aca24f1a18db5bd796abad6441e466d +size 1085420800 diff --git a/PLM-1.8B-Instruct-Q3_K_M.gguf b/PLM-1.8B-Instruct-Q3_K_M.gguf new file mode 100644 index 0000000..4f65ec5 --- /dev/null +++ b/PLM-1.8B-Instruct-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18e43c205ab0babfda07d9300cd584067d3716f4ae43b92e80f95c9163c77d39 +size 1005729024 diff --git a/PLM-1.8B-Instruct-Q3_K_S.gguf b/PLM-1.8B-Instruct-Q3_K_S.gguf new file mode 100644 index 0000000..4e102a0 --- /dev/null +++ b/PLM-1.8B-Instruct-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee569ff899608ba82703e07f329de3f58530ece112f2a1abb324c6d271b79486 +size 912405760 diff --git a/PLM-1.8B-Instruct-Q4_0.gguf b/PLM-1.8B-Instruct-Q4_0.gguf new file mode 100644 index 0000000..c93dd6d --- /dev/null +++ b/PLM-1.8B-Instruct-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b9a9789f088efdaa5f9bfb93e8d4e5742629803e8f7a674c33bca475ae0aaaf +size 1113502976 diff --git a/PLM-1.8B-Instruct-Q4_1.gguf b/PLM-1.8B-Instruct-Q4_1.gguf new file mode 100644 index 0000000..5386ae6 --- /dev/null +++ b/PLM-1.8B-Instruct-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:379133c35ac83b06c67b48cb9a21123e676fd4d029aeac0f44038f9571df1753 +size 1208136960 diff --git a/PLM-1.8B-Instruct-Q4_K_M.gguf b/PLM-1.8B-Instruct-Q4_K_M.gguf new file mode 100644 index 0000000..2694fe6 --- /dev/null +++ b/PLM-1.8B-Instruct-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b38570ee56ebec82a1e9ef45ab408c0d8230ececef1d7f1b267c49cff35638b8 +size 1182708992 diff --git a/PLM-1.8B-Instruct-Q4_K_S.gguf b/PLM-1.8B-Instruct-Q4_K_S.gguf new file mode 100644 index 0000000..7aa5652 --- /dev/null +++ b/PLM-1.8B-Instruct-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ca0514b1d60b3712b32e0002e1ce7a7c9649c44a3de095b41b4859d82b13eee +size 1121891584 diff --git a/PLM-1.8B-Instruct-Q5_0.gguf b/PLM-1.8B-Instruct-Q5_0.gguf new file mode 100644 index 0000000..9dfad17 --- /dev/null +++ b/PLM-1.8B-Instruct-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d303216c6c522ef95eb6d6c850cb7f53380e70bee68615a368bd6f42c8d61e5 +size 1302770944 diff --git a/PLM-1.8B-Instruct-Q5_1.gguf b/PLM-1.8B-Instruct-Q5_1.gguf new file mode 100644 index 0000000..9a82c83 --- /dev/null +++ b/PLM-1.8B-Instruct-Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d57171f868af1941e12b8d3049cf436f8b7278758e8a3d9777e0513205d5418 +size 1397404928 diff --git a/PLM-1.8B-Instruct-Q5_K_M.gguf b/PLM-1.8B-Instruct-Q5_K_M.gguf new file mode 100644 index 0000000..471a88e --- /dev/null +++ b/PLM-1.8B-Instruct-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c642e0d344f1974b087a5bd70d9650fc0e1e56fee1ca260ede62c2fc12ecf4cf +size 1338422528 diff --git a/PLM-1.8B-Instruct-Q5_K_S.gguf b/PLM-1.8B-Instruct-Q5_K_S.gguf new file mode 100644 index 0000000..1101ae0 --- /dev/null +++ b/PLM-1.8B-Instruct-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f78ed5c05c9d579a621e7506a07da5e893ee0a33ec8e96a9b1eda36fae8cf9d +size 1302770944 diff --git a/PLM-1.8B-Instruct-Q6_K.gguf b/PLM-1.8B-Instruct-Q6_K.gguf new file mode 100644 index 0000000..b96a5ac --- /dev/null +++ b/PLM-1.8B-Instruct-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92e129c9d07e8ba4ceda82cdd3e6672a3bb96226cf39580631f0c25cb1c59198 +size 1503868160 diff --git a/PLM-1.8B-Instruct-Q8_0.gguf b/PLM-1.8B-Instruct-Q8_0.gguf new file mode 100644 index 0000000..9aa39b4 --- /dev/null +++ b/PLM-1.8B-Instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0825c5377cd2d69c9dbc17e0adfe5ae121c3f03f22d1581d448dd3340cb2aefd +size 1945935104 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7693b27 --- /dev/null +++ b/README.md @@ -0,0 +1,110 @@ +--- +base_model: PLM-Team/PLM-1.8B-Instruct +language: +- en +- zh +library_name: transformers +license: apache-2.0 +quantized_by: PLM-Team +pipeline_tag: text-generation +--- +
+plm-logo +

🖲️ PLM: Efficient Peripheral Language Models Hardware-Co-Designed for Ubiquitous Computing

+👉 Project PLM Website +
+ +
+ +|||||||| +|:-:|:-:|:-:|:-:|:-:|:-:|:-:| +||||||| + +
+ +--- + +The PLM (Peripheral Language Model) series introduces a novel model architecture to peripheral computing by delivering powerful language capabilities within the constraints of resource-limited devices. Through modeling and system co-design strategy, PLM optimizes model performance and fits edge system requirements, PLM employs **Multi-head Latent Attention** and **squared ReLU** activation to achieve sparsity, significantly reducing memory footprint and computational demands. Coupled with a meticulously crafted training regimen using curated datasets and a Warmup-Stable-Decay-Constant learning rate scheduler, PLM demonstrates superior performance compared to existing small language models, all while maintaining the lowest activated parameters, making it ideally suited for deployment on diverse peripheral platforms like mobile phones and Raspberry Pis. + + +**Here we present the static quants of https://huggingface.co/PLM-Team/PLM-1.8B-Instruct** + +## Provided Quants + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +|https://huggingface.co/PLM-Team/PLM-1.8B-Instruct-gguf/blob/main/PLM-1.8B-Instruct-F16.gguf|F16| 3.66GB| Recommanded| +|https://huggingface.co/PLM-Team/PLM-1.8B-Instruct-gguf/blob/main/PLM-1.8B-Instruct-Q2_K.gguf|Q2_K| 827 MB| | +|https://huggingface.co/PLM-Team/PLM-1.8B-Instruct-gguf/blob/main/PLM-1.8B-Instruct-Q3_K_L.gguf|Q3_K_L| 1.09 GB| | +|https://huggingface.co/PLM-Team/PLM-1.8B-Instruct-gguf/blob/main/PLM-1.8B-Instruct-Q3_K_M.gguf|Q3_K_M| 1.01 GB| | +|https://huggingface.co/PLM-Team/PLM-1.8B-Instruct-gguf/blob/main/PLM-1.8B-Instruct-Q3_K_S.gguf|Q3_K_S| 912 MB| | +|https://huggingface.co/PLM-Team/PLM-1.8B-Instruct-gguf/blob/main/PLM-1.8B-Instruct-Q4_0.gguf|Q4_0| 1.11 GB| | +|https://huggingface.co/PLM-Team/PLM-1.8B-Instruct-gguf/blob/main/PLM-1.8B-Instruct-Q4_1.gguf|Q4_1| 1.21 GB| | +|https://huggingface.co/PLM-Team/PLM-1.8B-Instruct-gguf/blob/main/PLM-1.8B-Instruct-Q4_K_M.gguf|Q4_K_M| 1.18 GB| Recommanded| +|https://huggingface.co/PLM-Team/PLM-1.8B-Instruct-gguf/blob/main/PLM-1.8B-Instruct-Q4_K_S.gguf|Q4_K_S| 1.12 GB| | +|https://huggingface.co/PLM-Team/PLM-1.8B-Instruct-gguf/blob/main/PLM-1.8B-Instruct-Q5_0.gguf|Q5_0| 1.3 GB| | +|https://huggingface.co/PLM-Team/PLM-1.8B-Instruct-gguf/blob/main/PLM-1.8B-Instruct-Q5_1.gguf|Q5_1| 1.4 GB| | +|https://huggingface.co/PLM-Team/PLM-1.8B-Instruct-gguf/blob/main/PLM-1.8B-Instruct-Q5_K_M.gguf|Q5_K_M| 1.34 GB| | +|https://huggingface.co/PLM-Team/PLM-1.8B-Instruct-gguf/blob/main/PLM-1.8B-Instruct-Q5_K_S.gguf|Q5_K_S| 1.3 GB| | +|https://huggingface.co/PLM-Team/PLM-1.8B-Instruct-gguf/blob/main/PLM-1.8B-Instruct-Q6_K.gguf|Q6_K| 1.5 GB| | +|https://huggingface.co/PLM-Team/PLM-1.8B-Instruct-gguf/blob/main/PLM-1.8B-Instruct-Q8_0.gguf|Q8_0| 1.95 GB| Recommanded| + +## Usage (llama.cpp) + +Now [llama.cpp](https://github.com/ggml-org/llama.cpp) supports our model. Here is the usage: + +```bash +git clone https://github.com/Si1w/llama.cpp.git +cd llama.cpp +``` + +If you want to convert the orginal model into `gguf` form by yourself, you can + +```bash +pip install -r requirements.txt +python convert_hf_to_ggyf.py [model] --outtype {f32,f16,bf16,q8_0,tq1_0,tq2_0,auto} +``` + +Then, we can build with CPU of GPU (e.g. Orin). The build is based on `cmake`. + +- For CPU + +```bash +cmake -B build +cmake --build build --config Release +``` + +- For GPU + +```bash +cmake -B build -DGGML_CUDA=ON +cmake --build build --config Release +``` + +Don't forget to download the GGUF files of the PLM. We use the quantization methods in `llama.cpp` to generate the quantized PLM. + +```bash +huggingface-cli download --resume-download PLM-Team/PLM-1.8B-Instruct-gguf --local-dir PLM-Team/PLM-1.8B-Instruct-gguf +``` + +After build the `llama.cpp`, we can use `llama-cli` script to launch the PLM. + +```bash +./build/bin/llama-cli -m ./PLM-Team/PLM-1.8B-Instruct-gguf/PLM-1.8B-Instruct-Q8_0.gguf -cnv -p "hello!" -n 128 +``` + +## Citation + +If you find Project PLM helpful for your research or applications, please cite as follows: + +``` +@misc{deng2025plmefficientperipherallanguage, + title={PLM: Efficient Peripheral Language Models Hardware-Co-Designed for Ubiquitous Computing}, + author={Cheng Deng and Luoyang Sun and Jiwen Jiang and Yongcheng Zeng and Xinjian Wu and Wenxin Zhao and Qingfa Xiao and Jiachuan Wang and Lei Chen and Lionel M. Ni and Haifeng Zhang and Jun Wang}, + year={2025}, + eprint={2503.12167}, + archivePrefix={arXiv}, + primaryClass={cs.CL}, + url={https://arxiv.org/abs/2503.12167}, +} +``` \ No newline at end of file