| { | |
| "QuantizedLinear": { | |
| "is_quant_weight": false, | |
| "outlier_ids": {}, | |
| "replace": false, | |
| "training_mode": "train_full" | |
| }, | |
| "_name_or_path": "/home/llm_compression/Quantization/Ebft/llama-2-13b-ebft-sparsegpt-2@4-wiki-block-outlier", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "clip_softmax_eta": 1, | |
| "clip_softmax_gamma": 0, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 13824, | |
| "max_position_embeddings": 4096, | |
| "model_type": "llama", | |
| "num_attention_heads": 40, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 40, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "symmetric_quantizer": { | |
| "add": false, | |
| "layer_bit": {}, | |
| "learnable_scale": false | |
| }, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.38.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 32000, | |
| "weight_quant_bitnoise": { | |
| "add": false, | |
| "compute_scale": false, | |
| "layer_bit": {}, | |
| "learnable_scale": false, | |
| "noise_type": "normal", | |
| "predict": false | |
| }, | |
| "weight_quant_noise": { | |
| "add": false, | |
| "block_size": null, | |
| "compute_scale": false, | |
| "fp_cols_num": null, | |
| "layer_bit": {}, | |
| "predict": false | |
| } | |
| } | |