| { |
| "alora_invocation_tokens": null, |
| "alpha_pattern": {}, |
| "arrow_config": null, |
| "auto_mapping": null, |
| "base_model_name_or_path": "/opt/tiger/dedup_research/scratch/models/qwen3_8b_ar_fast_skeleton", |
| "bias": "none", |
| "corda_config": null, |
| "ensure_weight_tying": false, |
| "eva_config": null, |
| "exclude_modules": null, |
| "fan_in_fan_out": false, |
| "inference_mode": true, |
| "init_lora_weights": true, |
| "layer_replication": null, |
| "layers_pattern": null, |
| "layers_to_transform": null, |
| "loftq_config": {}, |
| "lora_alpha": 256, |
| "lora_bias": false, |
| "lora_dropout": 0.05, |
| "lora_ga_config": null, |
| "megatron_config": null, |
| "megatron_core": "megatron.core", |
| "modules_to_save": [ |
| "model.layers.0.self_attn.q_norm", |
| "model.layers.0.self_attn.k_norm", |
| "model.layers.0.input_layernorm", |
| "model.layers.0.post_attention_layernorm", |
| "model.layers.1.self_attn.q_norm", |
| "model.layers.1.self_attn.k_norm", |
| "model.layers.1.input_layernorm", |
| "model.layers.1.post_attention_layernorm", |
| "model.layers.2.self_attn.q_norm", |
| "model.layers.2.self_attn.k_norm", |
| "model.layers.2.input_layernorm", |
| "model.layers.2.post_attention_layernorm", |
| "model.layers.3.self_attn.q_norm", |
| "model.layers.3.self_attn.k_norm", |
| "model.layers.3.input_layernorm", |
| "model.layers.3.post_attention_layernorm", |
| "model.layers.4.self_attn.q_norm", |
| "model.layers.4.self_attn.k_norm", |
| "model.layers.4.input_layernorm", |
| "model.layers.4.post_attention_layernorm", |
| "model.layers.5.self_attn.q_norm", |
| "model.layers.5.self_attn.k_norm", |
| "model.layers.5.input_layernorm", |
| "model.layers.5.post_attention_layernorm", |
| "model.layers.6.self_attn.q_norm", |
| "model.layers.6.self_attn.k_norm", |
| "model.layers.6.input_layernorm", |
| "model.layers.6.post_attention_layernorm", |
| "model.layers.7.self_attn.q_norm", |
| "model.layers.7.self_attn.k_norm", |
| "model.layers.7.input_layernorm", |
| "model.layers.7.post_attention_layernorm", |
| "model.layers.8.self_attn.q_norm", |
| "model.layers.8.self_attn.k_norm", |
| "model.layers.8.input_layernorm", |
| "model.layers.8.post_attention_layernorm", |
| "model.layers.9.self_attn.q_norm", |
| "model.layers.9.self_attn.k_norm", |
| "model.layers.9.input_layernorm", |
| "model.layers.9.post_attention_layernorm", |
| "model.layers.10.self_attn.q_norm", |
| "model.layers.10.self_attn.k_norm", |
| "model.layers.10.input_layernorm", |
| "model.layers.10.post_attention_layernorm", |
| "model.layers.11.self_attn.q_norm", |
| "model.layers.11.self_attn.k_norm", |
| "model.layers.11.input_layernorm", |
| "model.layers.11.post_attention_layernorm", |
| "model.layers.12.self_attn.q_norm", |
| "model.layers.12.self_attn.k_norm", |
| "model.layers.12.input_layernorm", |
| "model.layers.12.post_attention_layernorm", |
| "model.layers.13.self_attn.q_norm", |
| "model.layers.13.self_attn.k_norm", |
| "model.layers.13.input_layernorm", |
| "model.layers.13.post_attention_layernorm", |
| "model.layers.14.self_attn.q_norm", |
| "model.layers.14.self_attn.k_norm", |
| "model.layers.14.input_layernorm", |
| "model.layers.14.post_attention_layernorm", |
| "model.layers.15.self_attn.q_norm", |
| "model.layers.15.self_attn.k_norm", |
| "model.layers.15.input_layernorm", |
| "model.layers.15.post_attention_layernorm", |
| "model.layers.16.self_attn.q_norm", |
| "model.layers.16.self_attn.k_norm", |
| "model.layers.16.input_layernorm", |
| "model.layers.16.post_attention_layernorm", |
| "model.layers.17.self_attn.q_norm", |
| "model.layers.17.self_attn.k_norm", |
| "model.layers.17.input_layernorm", |
| "model.layers.17.post_attention_layernorm", |
| "model.layers.18.self_attn.q_norm", |
| "model.layers.18.self_attn.k_norm", |
| "model.layers.18.input_layernorm", |
| "model.layers.18.post_attention_layernorm", |
| "model.layers.19.self_attn.q_norm", |
| "model.layers.19.self_attn.k_norm", |
| "model.layers.19.input_layernorm", |
| "model.layers.19.post_attention_layernorm", |
| "model.layers.20.self_attn.q_norm", |
| "model.layers.20.self_attn.k_norm", |
| "model.layers.20.input_layernorm", |
| "model.layers.20.post_attention_layernorm", |
| "model.layers.21.self_attn.q_norm", |
| "model.layers.21.self_attn.k_norm", |
| "model.layers.21.input_layernorm", |
| "model.layers.21.post_attention_layernorm", |
| "model.layers.22.self_attn.q_norm", |
| "model.layers.22.self_attn.k_norm", |
| "model.layers.22.input_layernorm", |
| "model.layers.22.post_attention_layernorm", |
| "model.layers.23.self_attn.q_norm", |
| "model.layers.23.self_attn.k_norm", |
| "model.layers.23.input_layernorm", |
| "model.layers.23.post_attention_layernorm", |
| "model.layers.24.self_attn.q_norm", |
| "model.layers.24.self_attn.k_norm", |
| "model.layers.24.input_layernorm", |
| "model.layers.24.post_attention_layernorm", |
| "model.layers.25.self_attn.q_norm", |
| "model.layers.25.self_attn.k_norm", |
| "model.layers.25.input_layernorm", |
| "model.layers.25.post_attention_layernorm", |
| "model.layers.26.self_attn.q_norm", |
| "model.layers.26.self_attn.k_norm", |
| "model.layers.26.input_layernorm", |
| "model.layers.26.post_attention_layernorm", |
| "model.layers.27.self_attn.q_norm", |
| "model.layers.27.self_attn.k_norm", |
| "model.layers.27.input_layernorm", |
| "model.layers.27.post_attention_layernorm", |
| "model.layers.28.self_attn.q_norm", |
| "model.layers.28.self_attn.k_norm", |
| "model.layers.28.input_layernorm", |
| "model.layers.28.post_attention_layernorm", |
| "model.layers.29.self_attn.q_norm", |
| "model.layers.29.self_attn.k_norm", |
| "model.layers.29.input_layernorm", |
| "model.layers.29.post_attention_layernorm", |
| "model.layers.30.self_attn.q_norm", |
| "model.layers.30.self_attn.k_norm", |
| "model.layers.30.input_layernorm", |
| "model.layers.30.post_attention_layernorm", |
| "model.layers.31.self_attn.q_norm", |
| "model.layers.31.self_attn.k_norm", |
| "model.layers.31.input_layernorm", |
| "model.layers.31.post_attention_layernorm", |
| "model.layers.32.self_attn.q_norm", |
| "model.layers.32.self_attn.k_norm", |
| "model.layers.32.input_layernorm", |
| "model.layers.32.post_attention_layernorm", |
| "model.layers.33.self_attn.q_norm", |
| "model.layers.33.self_attn.k_norm", |
| "model.layers.33.input_layernorm", |
| "model.layers.33.post_attention_layernorm", |
| "model.layers.34.self_attn.q_norm", |
| "model.layers.34.self_attn.k_norm", |
| "model.layers.34.input_layernorm", |
| "model.layers.34.post_attention_layernorm", |
| "model.layers.35.self_attn.q_norm", |
| "model.layers.35.self_attn.k_norm", |
| "model.layers.35.input_layernorm", |
| "model.layers.35.post_attention_layernorm", |
| "model.norm" |
| ], |
| "peft_type": "LORA", |
| "peft_version": "0.19.1", |
| "qalora_group_size": 16, |
| "r": 128, |
| "rank_pattern": {}, |
| "revision": null, |
| "target_modules": [ |
| "o_proj", |
| "up_proj", |
| "q_proj", |
| "k_proj", |
| "lm_head", |
| "v_proj", |
| "model.embed_tokens", |
| "down_proj", |
| "gate_proj" |
| ], |
| "target_parameters": null, |
| "task_type": "CAUSAL_LM", |
| "trainable_token_indices": null, |
| "use_bdlora": null, |
| "use_dora": false, |
| "use_qalora": false, |
| "use_rslora": false |
| } |
