Downloads · 30 days
6
13% of all-time downloads
chess-lora-20260111-134720-step1806
agi-noobs/chess-lora-20260111-134720-step1806
chess-lora-20260111-134720-step1806 is a machine learning model from agi-noobs. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Fine-tuned on chess positions to predict the best move.
All-time downloads
47
Public
Parameters
4B
8.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Jan 11, 2026
- Updated
- Jan 11, 2026
- SHA
- 9406c8c0
Base models
Model card
From the Hugging Face model README
Chess LoRA - chess-lora-20260111-134720 (step 1806)
Fine-tuned on chess positions to predict the best move.
Training Details
- Base Model: Qwen/Qwen3-4B-Instruct-2507
- Dataset: agi-noobs/chess-sft-10m-stockfish
- Checkpoint Step: 1806
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("agi-noobs/chess-lora-20260111-134720-step1806")
tokenizer = AutoTokenizer.from_pretrained("agi-noobs/chess-lora-20260111-134720-step1806")
Trained using Tinker by Thinking Machines Lab.
- Type
- qwen3
- License
- apache-2.0
- Created
- Jan 11, 2026
- Updated
- Jan 11, 2026