| { |
| "architectures": [ |
| "PhiForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "bos_token_id": 50256, |
| "embd_pdrop": 0.0, |
| "eos_token_id": 50256, |
| "hidden_act": "gelu_new", |
| "hidden_size": 2560, |
| "initializer_range": 0.02, |
| "intermediate_size": 10240, |
| "layer_norm_eps": 1e-05, |
| "max_position_embeddings": 2048, |
| "model_type": "phi", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 32, |
| "partial_rotary_factor": 0.4, |
| "qk_layernorm": false, |
| "quantization_config": { |
| "act_bits": 16, |
| "act_data_type": "int", |
| "act_dynamic": true, |
| "act_group_size": 128, |
| "act_sym": true, |
| "amp": true, |
| "autoround_version": "0.5.1", |
| "backend": "auto", |
| "batch_size": 8, |
| "bits": 4, |
| "data_type": "int", |
| "dataset": "NeelNanda/pile-10k", |
| "enable_minmax_tuning": true, |
| "enable_norm_bias_tuning": false, |
| "enable_quanted_input": true, |
| "gradient_accumulate_steps": 1, |
| "group_size": 128, |
| "iters": 200, |
| "low_gpu_mem_usage": false, |
| "lr": 0.005, |
| "minmax_lr": 0.005, |
| "nsamples": 128, |
| "packing_format": "auto_round:auto_gptq", |
| "quant_method": "auto-round", |
| "scale_dtype": "torch.float16", |
| "seqlen": 2048, |
| "super_bits": null, |
| "super_group_size": null, |
| "sym": true, |
| "to_quant_block_names": null |
| }, |
| "resid_pdrop": 0.1, |
| "rope_scaling": null, |
| "rope_theta": 10000.0, |
| "tie_word_embeddings": false, |
| "torch_dtype": "float16", |
| "transformers_version": "4.52.1", |
| "use_cache": true, |
| "vocab_size": 51200 |
| } |
|
|
