Text Classification
GGUF
llama.cpp
laya
system-one
calibrated-decisions
rlcd
classification
routing
scoring
guardrails
moderation
reinforcement-learning
commercial-use
feature-extraction
Instructions to use fr0stbit3/laya-gguf 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 fr0stbit3/laya-gguf 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 fr0stbit3/laya-gguf:Q4_K_M # Run inference directly in the terminal: llama cli -hf fr0stbit3/laya-gguf:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf fr0stbit3/laya-gguf:Q4_K_M # Run inference directly in the terminal: llama cli -hf fr0stbit3/laya-gguf: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 fr0stbit3/laya-gguf:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf fr0stbit3/laya-gguf: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 fr0stbit3/laya-gguf:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf fr0stbit3/laya-gguf:Q4_K_M
Use Docker
docker model run hf.co/fr0stbit3/laya-gguf:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use fr0stbit3/laya-gguf with Ollama:
ollama run hf.co/fr0stbit3/laya-gguf:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use fr0stbit3/laya-gguf with Docker Model Runner:
docker model run hf.co/fr0stbit3/laya-gguf:Q4_K_M
- Lemonade
How to use fr0stbit3/laya-gguf with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull fr0stbit3/laya-gguf:Q4_K_M
Run and chat with the model
lemonade run user.laya-gguf-Q4_K_M
List all available models
lemonade list
- Atomic Chat
File size: 550 Bytes
ce2afdc | 1 2 3 4 5 6 7 8 9 10 11 12 13 | """Load the Laya decision head + config from <name>-head.safetensors (sits next to the GGUF backbone)."""
import json, sys
from safetensors import safe_open
def load_head(path):
"""-> (config dict, {tensor_name: torch.float32 tensor}); names match the original PyTorch state_dict."""
with safe_open(path, "pt") as f:
cfg = json.loads(f.metadata()["laya.config"])
return cfg, {k: f.get_tensor(k) for k in f.keys()}
if __name__ == "__main__":
cfg, h = load_head(sys.argv[1]); print(len(h), "head tensors;", list(cfg)[:5])
|