kisoku-3b-sft

Superseded. This is Kisoku v1, an earlier 3B model. The current release is Kisoku 1.6B. Training log, benchmark charts and run instructions: 0arch.io/kisoku.

Kisoku 3B SFT

The instruction-tuned version of Kisoku 3B Base, fine-tuned using supervised fine-tuning (SFT) on Google Cloud TPUs with MaxText.

Trained entirely from scratch (pretraining + SFT) by a solo researcher, supported by Google's TPU Research Cloud (TRC).

Overview

This model was SFT'd from the Kisoku 3B base checkpoint using a custom text-only chat template (### User / ### Assistant format) designed to avoid out-of-vocabulary special token issues common with Llama-family tokenizers.

The model uses Granite architecture (identical to Llama but with runtime logit scaling), enabling GGUF conversion and local deployment via llama.cpp.

Architecture

Training Details

Pretraining (Base Model)

SFT

Local Deployment (GGUF)

A GGUF quantized version (Q8_0, 3.5GB) is available for local serving via llama.cpp:

# Serve with llama-server
llama-server -m kisoku-3b-sft-q8.gguf -c 4096 --port 8900

# Use with any OpenAI-compatible client
curl http://localhost:8900/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model": "kisoku", "messages": [{"role": "user", "content": "Hello!"}]}'

Note: Due to Granite logit scaling (55.4x), use temperature ~0.01 for standard behavior, or use the included proxy script that auto-adjusts temperature and injects logit_bias for special tokens.

Limitations

• Undertrained base model (needs more pretraining tokens for competitive performance)
• English-focused
• No safety alignment (RLHF/DPO) applied
• Granite logit scaling requires temperature adjustment at inference

Acknowledgments

Research supported with Cloud TPUs from Google's TPU Research Cloud (TRC).

License

Apache 2.0