File size: 1,138 Bytes
d8789a2 | 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 | {
"alora_invocation_tokens": null,
"alpha_pattern": {},
"arrow_config": null,
"auto_mapping": null,
"base_model_name_or_path": "Qwen/Qwen3.5-35B-A3B",
"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": 32,
"lora_bias": false,
"lora_dropout": 0.0,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": [],
"peft_type": "LORA",
"peft_version": "0.18.1",
"qalora_group_size": 16,
"r": 8,
"rank_pattern": {},
"revision": null,
"target_modules": "^(?!.*visual).*(?:o_proj|up_proj|v_proj|down_proj|k_proj|q_proj|gate_proj|in_proj_qkv|in_proj_z|in_proj_b|in_proj_a|shared_expert_gate).*",
"target_parameters": [
"mlp.experts.gate_up_proj",
"mlp.experts.down_proj"
],
"task_type": "CAUSAL_LM",
"trainable_token_indices": null,
"use_dora": false,
"use_qalora": false,
"use_rslora": false
} |