| { | |
| "_name_or_path": "/data/nikit_ws/LOLA-Megatron-DeepSpeed/lola_ws/fine-tune/instruction-ft/output_model", | |
| "activation_function": "gelu_fast", | |
| "architectures": [ | |
| "LOLALMHeadModel" | |
| ], | |
| "attn_pdrop": 0.1, | |
| "auto_map": { | |
| "AutoConfig": "configuration_lola_gpt2.LOLAConfig", | |
| "AutoModelForCausalLM": "modeling_lola_gpt2.LOLALMHeadModel" | |
| }, | |
| "bos_token_id": 0, | |
| "embd_pdrop": 0.1, | |
| "eos_token_id": 5, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "model_type": "lola_v1", | |
| "n_embd": 2048, | |
| "n_head": 16, | |
| "n_inner": 8192, | |
| "n_layer": 24, | |
| "n_positions": 2048, | |
| "num_experts": 16, | |
| "reorder_and_upcast_attn": false, | |
| "resid_pdrop": 0.1, | |
| "scale_attn_by_inverse_layer_idx": false, | |
| "scale_attn_weights": true, | |
| "summary_activation": null, | |
| "summary_first_dropout": 0.1, | |
| "summary_proj_to_labels": true, | |
| "summary_type": "cls_index", | |
| "summary_use_proj": true, | |
| "tokenizer_class": "GPT2TokenizerFast", | |
| "topk": 1, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.39.1", | |
| "use_cache": true, | |
| "vocab_size": 100000 | |
| } | |