Debil 1.5
Collection
3 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 RaspizdAI/debil-1.5-GGUF:# Run inference directly in the terminal:
llama cli -hf RaspizdAI/debil-1.5-GGUF: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 RaspizdAI/debil-1.5-GGUF:# Run inference directly in the terminal:
./llama-cli -hf RaspizdAI/debil-1.5-GGUF: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 RaspizdAI/debil-1.5-GGUF:# Run inference directly in the terminal:
./build/bin/llama-cli -hf RaspizdAI/debil-1.5-GGUF:Use Docker
docker model run hf.co/RaspizdAI/debil-1.5-GGUF:Quick Links
🚀 debil-1.5 GGUF
debil-1.5 in GGUF format, available in multiple quantization levels.
Technical Specifications:
- Total Parameters: 46,538,400 (~46.5M)
- Vocabulary Size: 50,257
- Embedding Dimensions: 480
- Hidden Layers: 8
- Attention Heads: 8
- Head Dimension: 60
- Format: GGUF
Available Quantizations:
| Quantization | File |
|---|---|
| FP16 | debil-1.5-fp16.gguf |
| Q8_0 | debil-1.5-Q8_0.gguf |
| Q4_K_M | debil-1.5-Q4_K_M.gguf |
| IQ2_XXS | debil-1.5-IQ2_XXS.gguf |
| IQ1_S | debil-1.5-IQ1_S.gguf |
Quantization Details:
- FP16 — unquantized version with FP16 weights.
- Q8_0 — 8-bit quantization with minimal quality loss.
- Q4_K_M — 4-bit K-quants offering a good size/quality balance.
- IQ2_XXS — ultra-low-bit importance quantization.
- IQ1_S — extremely aggressive 1-bit-class quantization for minimal file size.
- Downloads last month
- 208
Hardware compatibility
Log In to add your hardware
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf RaspizdAI/debil-1.5-GGUF:# Run inference directly in the terminal: llama cli -hf RaspizdAI/debil-1.5-GGUF: