mirror of
https://github.com/zenlm/zen-coder.git
synced 2026-11-10 21:30:01 +00:00
- Rename Qwen2.5-Coder-* examples to zen-coder-* (consistent Zen branding) - Add LLM.md knowledge base (symlinked as CLAUDE.md/AGENTS.md/etc.) - Update .gitignore: exclude model weights and AI symlink files - Add training configs, inference scripts, test suite - Add MLX README, model card, Makefile for common operations
40 lines
983 B
JSON
40 lines
983 B
JSON
{
|
|
"adapter_path": "/Users/z/work/zen/zen-coder/training/adapters",
|
|
"batch_size": 1,
|
|
"config": null,
|
|
"data": "/Users/z/work/zen/zen-coder/training/full_data",
|
|
"fine_tune_type": "lora",
|
|
"grad_accumulation_steps": 4,
|
|
"grad_checkpoint": true,
|
|
"iters": 837500,
|
|
"learning_rate": 1e-05,
|
|
"lora_parameters": {
|
|
"rank": 8,
|
|
"dropout": 0.0,
|
|
"scale": 20.0
|
|
},
|
|
"lr_schedule": null,
|
|
"mask_prompt": true,
|
|
"max_seq_length": 1024,
|
|
"model": "Qwen/Qwen3-4B-Instruct-2507",
|
|
"num_layers": 4,
|
|
"optimizer": "adamw",
|
|
"optimizer_config": {
|
|
"adam": {},
|
|
"adamw": {},
|
|
"muon": {},
|
|
"sgd": {},
|
|
"adafactor": {}
|
|
},
|
|
"project_name": null,
|
|
"report_to": null,
|
|
"resume_adapter_file": null,
|
|
"save_every": 5000,
|
|
"seed": 0,
|
|
"steps_per_eval": 25000,
|
|
"steps_per_report": 10,
|
|
"test": false,
|
|
"test_batches": 500,
|
|
"train": true,
|
|
"val_batches": 25
|
|
} |