Instructions to use RthItalia/Rth-lm-25b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use RthItalia/Rth-lm-25b 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 RthItalia/Rth-lm-25b # Run inference directly in the terminal: llama cli -hf RthItalia/Rth-lm-25b
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf RthItalia/Rth-lm-25b # Run inference directly in the terminal: llama cli -hf RthItalia/Rth-lm-25b
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf RthItalia/Rth-lm-25b # Run inference directly in the terminal: ./build/bin/llama cli -hf RthItalia/Rth-lm-25b
Use Docker
docker model run hf.co/RthItalia/Rth-lm-25b
- Llama new
- LM Studio
- Jan
- Ollama
How to use RthItalia/Rth-lm-25b with Ollama:
ollama run hf.co/RthItalia/Rth-lm-25b
- Unsloth Desktop
- Docker Model Runner
How to use RthItalia/Rth-lm-25b with Docker Model Runner:
docker model run hf.co/RthItalia/Rth-lm-25b
- Lemonade
How to use RthItalia/Rth-lm-25b with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull RthItalia/Rth-lm-25b
Run and chat with the model
lemonade run user.Rth-lm-25b-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
|
Download OLLAMA_PATCH_GUIDE.md from RthItalia/Rth-lm-25b: direct link, hf CLI and curl.
- Browser
- Download file 1.15 kB
-
https://huggingface.co/RthItalia/Rth-lm-25b/resolve/main/OLLAMA_PATCH_GUIDE.md
- Command line
-
hf download hf://RthItalia/Rth-lm-25b/OLLAMA_PATCH_GUIDE.md
-
curl -L -o OLLAMA_PATCH_GUIDE.md https://huggingface.co/RthItalia/Rth-lm-25b/resolve/main/OLLAMA_PATCH_GUIDE.md
1.15 kB
π οΈ ZetaGrid-Ollama Patch: Setup Guide
To run RTH-LM (Fractal TCN) natively in your local environment via Ollama, you need to add support for the TCN operators to the underlying llama.cpp engine.
π¦ Prerequisites
- GGUF Model: Download rth_lm_25b_v1.gguf
- Ollama Source: Clone the official repository or use our fork.
π οΈ Step 1: Add Custom Kernels
Copy the provided C++ files into the llama.cpp source tree:
- Move
rth_tcn_ops.cppandrth_tcn_ops.htollama.cpp/src/ - Register
GGML_OP_CAUSAL_CONV1DandGGML_OP_FRACTAL_GATEinggml.c
ποΈ Step 2: Compile
Rebuild llama.cpp or your Ollama binary:
make -j
# or for Ollama
go generate ./...
go build .
π Step 3: Create & Run
Use the provided Modelfile_RTH-LM to register the model:
ollama create rth-lm -f Modelfile_RTH-LM
ollama run rth-lm
Why this matters: RTH-LM is a pioneer in non-Transformer architectures for local inference. By applying this patch, you are at the forefront of the TCN revolution. π«‘ππ¦