| { | |
| "_name_or_path": "MerantixMomentum/acip_llama1_7b", | |
| "adapter_config": { | |
| "peft_config": { | |
| "default": { | |
| "alpha_pattern": {}, | |
| "auto_mapping": null, | |
| "base_model_name_or_path": "jeffwan/llama-7b-hf", | |
| "bias": "none", | |
| "eva_config": null, | |
| "exclude_modules": [ | |
| "base", | |
| "ortho", | |
| "parametrization" | |
| ], | |
| "fan_in_fan_out": false, | |
| "inference_mode": false, | |
| "init_lora_weights": true, | |
| "layer_replication": null, | |
| "layers_pattern": null, | |
| "layers_to_transform": null, | |
| "loftq_config": {}, | |
| "lora_alpha": 16, | |
| "lora_bias": false, | |
| "lora_dropout": 0.05, | |
| "megatron_config": null, | |
| "megatron_core": "megatron.core", | |
| "modules_to_save": null, | |
| "peft_type": "LORA", | |
| "r": 32, | |
| "rank_pattern": {}, | |
| "revision": null, | |
| "target_modules": [ | |
| "base", | |
| "gate_proj", | |
| "up_proj", | |
| "ortho", | |
| "o_proj", | |
| "v_proj", | |
| "q_proj", | |
| "k_proj", | |
| "down_proj" | |
| ], | |
| "task_type": "CAUSAL_LM", | |
| "use_dora": false, | |
| "use_rslora": false | |
| } | |
| } | |
| }, | |
| "architectures": [ | |
| "ACIPModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "acip_model.ACIPModelConfig", | |
| "AutoModel": "acip_model.ACIPModel" | |
| }, | |
| "base_model_config": { | |
| "pretrained_config": null, | |
| "pretrained_model_cls": "transformers.models.auto.modeling_auto.AutoModelForCausalLM", | |
| "pretrained_model_kwargs": { | |
| "pretrained_model_name_or_path": "jeffwan/llama-7b-hf", | |
| "torch_dtype": "bfloat16" | |
| } | |
| }, | |
| "model_mode": "train", | |
| "model_type": "acip_model", | |
| "parametrization_config": { | |
| "exclude_modules": null, | |
| "module_factory_cls": "svd", | |
| "module_factory_kwargs": { | |
| "mask_func": "ste", | |
| "mask_scaling_factor": 0.02 | |
| }, | |
| "target_modules": [ | |
| "k_proj", | |
| "down_proj", | |
| "o_proj", | |
| "v_proj", | |
| "gate_proj", | |
| "q_proj", | |
| "up_proj" | |
| ] | |
| }, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.46.3", | |
| "weight_quantization_config": { | |
| "exclude_modules": null, | |
| "module_factory_cls": "bitsandbytes.nn.Linear4bit", | |
| "module_factory_kwargs": { | |
| "compute_dtype": "torch.bfloat16", | |
| "quant_type": "fp4" | |
| }, | |
| "target_modules": [ | |
| "ortho", | |
| "base", | |
| "base_layer" | |
| ] | |
| } | |
| } | |