YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

Merged Model

  • Base model: meta-llama/Llama-3.2-3B
  • Algorithm: Consensus
  • Save path: ./merged_models/Llama-3.2-3B_merged/Consensus_scaling_coef_0.3_k_2_lamda_[0.5, 0.6, 0.4]_lamda_tuning_False
  • Fine-tuned checkpoints: ['MergeBench/Llama-3.2-3B_instruction', 'MergeBench/Llama-3.2-3B_math', 'MergeBench/Llama-3.2-3B_coding']
  • Merge runtime (s): 118.768

Arguments

{
  "local_rank": 0,
  "scaling_coef": 0.3,
  "K": 0.2,
  "merge_func": "sum",
  "p": 0.8,
  "sigmoid_bias": 3,
  "sparsity": 0.1,
  "lr": 100000000.0,
  "n_epochs": 1,
  "l1_strength": 0.0,
  "dataless": false,
  "k": 2,
  "lamda": [
    0.5,
    0.6,
    0.4
  ],
  "lamda_tuning": false,
  "task_names": null,
  "reduction": null,
  "fisher_only": false,
  "merge_only": false,
  "save_group": null,
  "model_coeff_value": 0.3,
  "keep_checkpoints": false,
  "beta_coef": 1,
  "n": 64,
  "m": 256,
  "pruned_subdir": "pruned_models",
  "save_pruned_models": true,
  "warn_min_overlap_fallback": true,
  "base_model": "meta-llama/Llama-3.2-3B",
  "algo": "Consensus",
  "save_path": "./merged_models/"
}

Merge kwargs

{
  "scaling_coef": 0.3,
  "k": 2,
  "lamda": [
    0.5,
    0.6,
    0.4
  ],
  "lamda_tuning": false
}
Downloads last month
12
Safetensors
Model size
3B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support