YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Merged Model
- Base model:
N/A - Algorithm:
wudi_merge - Save path:
/outs/wudi_cold_start_300 - Fine-tuned checkpoints: ['MergeBench/Llama-3.2-3B_instruction', 'MergeBench/Llama-3.2-3B_math', 'MergeBench/Llama-3.2-3B_coding']
- Merge runtime (s): 867.746
Arguments
{
"out": "/outs/wudi_cold_start_300",
"scaling": 1.0,
"dtype": "bfloat16",
"device_map": "cpu",
"merge_method": "wudi_merge",
"exclude": [
".*embed.*",
".*lm_head.*"
],
"wudi_variant": "wudi_all_linear",
"wudi_iter": 300,
"wudi_lr": 1e-05,
"wudi_weight_decay": 0.0,
"wudi_device": "cuda",
"wudi_warm_start": false,
"wudi_cfs_ridge": 1e-05,
"wudi_fallback": "task_arithmetic",
"wudi_fallback_scaling": 1.0,
"wudi_K": 0.7,
"wudi_sparsify_variant": "ties_sparsify",
"wudi_loss_log_csv": null,
"effective_exclude": [
".*embed_tokens\\.weight$",
".*lm_head\\.weight$",
".*embed.*",
".*lm_head.*"
]
}
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support