enpisi-coder

LoRA adapter for npcsh agentic command execution.

Trained on npcsh benchmark traces to improve tool calling, shell command generation, and file operation reasoning.

Supported Families

Family Status
Qwen3.5 Planned
Gemma4 Planned

Structure

adapters/
β”œβ”€β”€ qwen3.5/         # Qwen3.5 family
β”‚   β”œβ”€β”€ mlx/         # Planned
β”‚   β”œβ”€β”€ hf/          # Planned
β”‚   └── gguf/        # Planned
β”œβ”€β”€ gemma4/          # Gemma4 family
β”‚   β”œβ”€β”€ mlx/         # Planned
β”‚   β”œβ”€β”€ hf/          # Planned
β”‚   └── gguf/        # Planned

Usage

from npcpy.ft.sft import load_sft_model, predict_sft

model, tokenizer = load_sft_model("npc-worldwide/enpisi-coder")
response = predict_sft(
    model, tokenizer,
    "Find the largest log file in /var/log and show the last 20 lines",
    max_new_tokens=500,
)

Ecosystem

  • npcpy β€” training toolkit
  • npcsh β€” NPC shell
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support