How to use from
llama.cppInstall from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tom1669/PhoGPT-4B-Chat# Run inference directly in the terminal:
llama-cli -hf tom1669/PhoGPT-4B-ChatUse 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 tom1669/PhoGPT-4B-Chat# Run inference directly in the terminal:
./llama-cli -hf tom1669/PhoGPT-4B-ChatBuild 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 tom1669/PhoGPT-4B-Chat# Run inference directly in the terminal:
./build/bin/llama-cli -hf tom1669/PhoGPT-4B-ChatUse Docker
docker model run hf.co/tom1669/PhoGPT-4B-ChatQuick Links
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
GGUF format files of the model vinai/PhoGPT-4B-Chat.
This model file is compatible with the latest llama.cpp
Context: I was trying to get PhoGPT to work with llama-cpp and llama-cpp-python. I found nguyenviet/PhoGPT-4B-Chat-GGUF but cannot get it to work:
from llama_cpp import Llama
llm = Llama.from_pretrained(
repo_id="nguyenviet/PhoGPT-4B-Chat-GGUF",
filename="*q3_k_m.gguf*",
)
...
llama_model_load: error loading model: done_getting_tensors: wrong number of tensors; expected 388, got 387
llama_load_model_from_file: failed to load model
...
After my opening issue at the PhoGPT repo was resolved, I was able to create the gguf file.
I figure people want to try the model in Colab. So here it is, so you don't have to create it yourself
- Downloads last month
- 9
Hardware compatibility
Log In to add your hardware
We're not able to determine the quantization variants.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Install from brew
# Start a local OpenAI-compatible server with a web UI: llama-server -hf tom1669/PhoGPT-4B-Chat# Run inference directly in the terminal: llama-cli -hf tom1669/PhoGPT-4B-Chat