Hugging Face's logo

ApplauseLab
/
bankai-v1

Text Generation
MLX
Safetensors
GGUF
quantized
lora
qwen3-next
orchestrator
agent
Model card Files
xet
 Community
bankai-v1
File size: 1,269 Bytes
83469f9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
{
    "adapter_path": "artifacts/askai-v1/adapter",
    "batch_size": 1,
    "clear_cache_threshold": 0,
    "config": "configs/askai-v1-lora.yaml",
    "data": "artifacts/askai-v1/data",
    "fine_tune_type": "lora",
    "grad_accumulation_steps": 2,
    "grad_checkpoint": true,
    "iters": 612,
    "learning_rate": 1e-05,
    "lora_parameters": {
        "rank": 8,
        "dropout": 0.0,
        "scale": 16.0,
        "keys": [
            "linear_attn.in_proj_qkvz",
            "linear_attn.in_proj_ba",
            "linear_attn.out_proj",
            "self_attn.q_proj",
            "self_attn.k_proj",
            "self_attn.v_proj",
            "self_attn.o_proj"
        ]
    },
    "lr_schedule": null,
    "mask_prompt": true,
    "max_seq_length": 2048,
    "model": "mlx-community/Qwen3-Coder-Next-4bit",
    "num_layers": 16,
    "optimizer": "adamw",
    "optimizer_config": {
        "adam": {},
        "adamw": {},
        "muon": {},
        "sgd": {},
        "adafactor": {}
    },
    "project_name": null,
    "report_to": null,
    "resume_adapter_file": null,
    "save_every": 100,
    "seed": 42,
    "steps_per_eval": 100,
    "steps_per_report": 5,
    "test": false,
    "test_batches": 500,
    "train": true,
    "val_batches": 8
}