Instructions to use Wangtwohappy/T4_code 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 Wangtwohappy/T4_code 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 Wangtwohappy/T4_code:Q4_K_M # Run inference directly in the terminal: llama cli -hf Wangtwohappy/T4_code:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Wangtwohappy/T4_code:Q4_K_M # Run inference directly in the terminal: llama cli -hf Wangtwohappy/T4_code: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 Wangtwohappy/T4_code:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Wangtwohappy/T4_code: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 Wangtwohappy/T4_code:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Wangtwohappy/T4_code:Q4_K_M
Use Docker
docker model run hf.co/Wangtwohappy/T4_code:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use Wangtwohappy/T4_code with Ollama:
ollama run hf.co/Wangtwohappy/T4_code:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use Wangtwohappy/T4_code with Docker Model Runner:
docker model run hf.co/Wangtwohappy/T4_code:Q4_K_M
- Lemonade
How to use Wangtwohappy/T4_code with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Wangtwohappy/T4_code:Q4_K_M
Run and chat with the model
lemonade run user.T4_code-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Download Direct_Transformers/load.py from Wangtwohappy/T4_code: direct link, hf CLI and curl.
- Browser
- Download file 389 Bytes
-
https://huggingface.co/Wangtwohappy/T4_code/resolve/main/Direct_Transformers/load.py
- Command line
-
hf download hf://Wangtwohappy/T4_code/Direct_Transformers/load.py
-
curl -L -o load.py https://huggingface.co/Wangtwohappy/T4_code/resolve/main/Direct_Transformers/load.py
389 Bytes
| from transformers import AutoModel, AutoTokenizer | |
| import torch | |
| import time | |
| model_id = "openbmb/MiniCPM-V-4-int4" | |
| model = AutoModel.from_pretrained( | |
| model_id, | |
| trust_remote_code=True, | |
| attn_implementation='sdpa', | |
| torch_dtype=torch.bfloat16 | |
| ) | |
| model = model.eval().cuda() | |
| tokenizer = AutoTokenizer.from_pretrained( | |
| model_id, trust_remote_code=True | |
| ) | |
| time.sleep(1000000) |