Instructions to use jolovicdev/Lacuna-V1-GGUF-Q4_K_M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use jolovicdev/Lacuna-V1-GGUF-Q4_K_M with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="jolovicdev/Lacuna-V1-GGUF-Q4_K_M", filename="lacuna-v1-Q4_K_M.gguf", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use jolovicdev/Lacuna-V1-GGUF-Q4_K_M with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf jolovicdev/Lacuna-V1-GGUF-Q4_K_M:Q4_K_M # Run inference directly in the terminal: llama-cli -hf jolovicdev/Lacuna-V1-GGUF-Q4_K_M:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf jolovicdev/Lacuna-V1-GGUF-Q4_K_M:Q4_K_M # Run inference directly in the terminal: llama-cli -hf jolovicdev/Lacuna-V1-GGUF-Q4_K_M: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 jolovicdev/Lacuna-V1-GGUF-Q4_K_M:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf jolovicdev/Lacuna-V1-GGUF-Q4_K_M: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 jolovicdev/Lacuna-V1-GGUF-Q4_K_M:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf jolovicdev/Lacuna-V1-GGUF-Q4_K_M:Q4_K_M
Use Docker
docker model run hf.co/jolovicdev/Lacuna-V1-GGUF-Q4_K_M:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use jolovicdev/Lacuna-V1-GGUF-Q4_K_M with Ollama:
ollama run hf.co/jolovicdev/Lacuna-V1-GGUF-Q4_K_M:Q4_K_M
- Unsloth Studio
How to use jolovicdev/Lacuna-V1-GGUF-Q4_K_M with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for jolovicdev/Lacuna-V1-GGUF-Q4_K_M to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for jolovicdev/Lacuna-V1-GGUF-Q4_K_M to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for jolovicdev/Lacuna-V1-GGUF-Q4_K_M to start chatting
- Atomic Chat new
- Docker Model Runner
How to use jolovicdev/Lacuna-V1-GGUF-Q4_K_M with Docker Model Runner:
docker model run hf.co/jolovicdev/Lacuna-V1-GGUF-Q4_K_M:Q4_K_M
- Lemonade
How to use jolovicdev/Lacuna-V1-GGUF-Q4_K_M with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull jolovicdev/Lacuna-V1-GGUF-Q4_K_M:Q4_K_M
Run and chat with the model
lemonade run user.Lacuna-V1-GGUF-Q4_K_M-Q4_K_M
List all available models
lemonade list
Lacuna V1 GGUF Q4_K_M
Q4_K_MGGUF quantization of Lacuna V1.
Lacuna V1 is an experimental code edit completion model. It predicts replacement code for numbered edit regions inside a Seed-Coder FIM prompt.
At A Glance
| Field | Value |
|---|---|
| Format | GGUF |
| Quantization | Q4_K_M |
| Task | Code edit completion |
| Prompt style | Seed-Coder FIM + numbered markers |
| License | Apache-2.0 |
Marker Contract
Markers define the regions to replace.
| Region | Open marker | Close marker |
|---|---|---|
| 1 | <|marker_1|> |
<|marker_2|> |
| 2 | <|marker_3|> |
<|marker_4|> |
| N | <|marker_2N-1|> |
<|marker_2N|> |
The prompt contains the surrounding code context and marker placeholders. The completion starts at the first marker and returns the replacement span with markers included.
Typical Input
<[fim-suffix]>
return total;
}
<[fim-prefix]>
function sum(items) {
let total = 0;
for (const item of items) {
<|marker_1|><|marker_2|>
}
<[fim-middle]>
<|marker_1|>
Typical Output
<|marker_1|>
total += item.value;
<|marker_2|>
llama.cpp
llama-server \
-m lacuna-v1-Q4_K_M.gguf \
--ctx-size 4096 \
--host 127.0.0.1 \
--port 8080
Completion Settings
| Setting | Value |
|---|---|
temperature |
0 |
top_p |
1 |
max_tokens |
256 |
Use a larger max_tokens value for longer or multi-region edits.
Limitations
Lacuna V1 is experimental. Quantized output can differ from the full model. Validate output before applying edits automatically.
License
Apache-2.0.
- Downloads last month
- 44
4-bit
Model tree for jolovicdev/Lacuna-V1-GGUF-Q4_K_M
Base model
ByteDance-Seed/Seed-Coder-8B-Base