Forge 1
Collection
The series of stable coding models built by North ML. Optimized for speed, clarity and efficiency. • 4 items • Updated
How to use from
llama.cppInstall from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf North-ML1/Forge-1-GGUF:F16# Run inference directly in the terminal:
llama cli -hf North-ML1/Forge-1-GGUF:F16Use 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 North-ML1/Forge-1-GGUF:F16# Run inference directly in the terminal:
./llama-cli -hf North-ML1/Forge-1-GGUF:F16Build 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 North-ML1/Forge-1-GGUF:F16# Run inference directly in the terminal:
./build/bin/llama-cli -hf North-ML1/Forge-1-GGUF:F16Use Docker
docker model run hf.co/North-ML1/Forge-1-GGUF:F16Quick Links
Forge-1 GGUF
GGUF exports for North-ML1/Forge-1.
Files:
forge-1-f16.gguf- F16 GGUF export.forge-1-q4_k_m.gguf- Q4_K_M quantized GGUF for practical local inference.
Source model: North-ML1/Forge-1, moved from North-ML1/Forge-1-Base.
Conversion notes:
- Converted with
llama.cppfrom the Hugging Face safetensors export. - The model uses a locally trained ByteLevel BPE tokenizer. Current
llama.cppdid not recognize its tokenizer hash, so the converter was patched to mark this ByteLevel BPE tokenizer asgpt-2pre-tokenization. - A smoke test with
llama-cliloadedforge-1-q4_k_m.ggufand answered2 + 2 = 4.
Example:
llama-cli -m forge-1-q4_k_m.gguf -p '<|im_start|>user\nWhat is 2 + 2?<|im_end|>\n<|im_start|>assistant\n' -n 32 --temp 0
SHA256:
56b5f16b11e742e82874f11f5db20bc9be497793626989a5ed4000108773a87c forge-1-f16.gguf
2272f246381687462abac21a8f9b8cda1d891fa0cdba22d45c16f77c7527c51c forge-1-q4_k_m.gguf
Prompt Format
Forge-1 is ChatML-tuned. Use a ChatML prompt, for example:
<|im_start|>user
What is 2 + 2?<|im_end|>
<|im_start|>assistant
Plain completion prompts are not reliable for this checkpoint. If your UI has a chat-template selector, choose ChatML.
- Downloads last month
- 73
Hardware compatibility
Log In to add your hardware
4-bit
16-bit
Model tree for North-ML1/Forge-1-GGUF
Base model
North-ML1/Forge-1
Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf North-ML1/Forge-1-GGUF:F16# Run inference directly in the terminal: llama cli -hf North-ML1/Forge-1-GGUF:F16