Instructions to use PLM-Team/PLM-1.8B-Instruct-id-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PLM-Team/PLM-1.8B-Instruct-id-gguf with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("PLM-Team/PLM-1.8B-Instruct-id-gguf", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use PLM-Team/PLM-1.8B-Instruct-id-gguf with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf PLM-Team/PLM-1.8B-Instruct-id-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf PLM-Team/PLM-1.8B-Instruct-id-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf PLM-Team/PLM-1.8B-Instruct-id-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf PLM-Team/PLM-1.8B-Instruct-id-gguf:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf PLM-Team/PLM-1.8B-Instruct-id-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf PLM-Team/PLM-1.8B-Instruct-id-gguf:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf PLM-Team/PLM-1.8B-Instruct-id-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf PLM-Team/PLM-1.8B-Instruct-id-gguf:Q4_K_M

Use Docker

docker model run hf.co/PLM-Team/PLM-1.8B-Instruct-id-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use PLM-Team/PLM-1.8B-Instruct-id-gguf with Ollama:
```
ollama run hf.co/PLM-Team/PLM-1.8B-Instruct-id-gguf:Q4_K_M
```

Unsloth Studio

How to use PLM-Team/PLM-1.8B-Instruct-id-gguf with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for PLM-Team/PLM-1.8B-Instruct-id-gguf to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for PLM-Team/PLM-1.8B-Instruct-id-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for PLM-Team/PLM-1.8B-Instruct-id-gguf to start chatting

Docker Model Runner
How to use PLM-Team/PLM-1.8B-Instruct-id-gguf with Docker Model Runner:
```
docker model run hf.co/PLM-Team/PLM-1.8B-Instruct-id-gguf:Q4_K_M
```

Lemonade

How to use PLM-Team/PLM-1.8B-Instruct-id-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull PLM-Team/PLM-1.8B-Instruct-id-gguf:Q4_K_M

Run and chat with the model

lemonade run user.PLM-1.8B-Instruct-id-gguf-Q4_K_M

List all available models

lemonade list

Atomic Chat

nielsr HF Staff commited on Mar 18, 2025

Commit

bcd4ec3

verified ·

1 Parent(s): 7380afd

Add pipeline tag and Github link

Browse files

This PR adds the `pipeline_tag: text-generation` to the model card metadata, making the model discoverable through the Hugging Face model index for text generation tasks. It also adds a link to the Github repository, enabling people to find code easier.

Files changed (1) hide show

README.md +3 -0

README.md CHANGED Viewed

@@ -5,7 +5,9 @@ language:
 library_name: transformers
 license: mit
 quantized_by: PLM-Team
 ---
 <center>
 <img src="https://www.cdeng.net/plm/plm_logo.png" alt="k2-logo" width="200"/>
 <h2>🖲️ PLM: Efficient Peripheral Language Models Hardware-Co-Designed for Ubiquitous Computing</h2>
@@ -24,6 +26,7 @@ quantized_by: PLM-Team
 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 for identified model of PLM-1.8B-Instruct**

 library_name: transformers
 license: mit
 quantized_by: PLM-Team
+pipeline_tag: text-generation
 ---
 <center>
 <img src="https://www.cdeng.net/plm/plm_logo.png" alt="k2-logo" width="200"/>
 <h2>🖲️ PLM: Efficient Peripheral Language Models Hardware-Co-Designed for Ubiquitous Computing</h2>
 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.
+Code: https://github.com/plm-team/PLM
 **Here we present the static quants for identified model of PLM-1.8B-Instruct**