| { | |
| "_name_or_path": "distributed/optimized-gpt2-1b-vtestnet-v2", | |
| "activation_function": "gelu_new", | |
| "all_reduce_scores": { | |
| "0": "NON_PARTICIPATING", | |
| "1": "SUCCESS", | |
| "2": "NON_PARTICIPATING", | |
| "3": "NON_PARTICIPATING", | |
| "4": "NON_PARTICIPATING", | |
| "5": "NON_PARTICIPATING", | |
| "6": "NON_PARTICIPATING", | |
| "7": "NON_PARTICIPATING", | |
| "8": "NON_PARTICIPATING", | |
| "9": "NON_PARTICIPATING" | |
| }, | |
| "architectures": [ | |
| "GPTOptim" | |
| ], | |
| "attn_pdrop": 0.1, | |
| "auto_map": { | |
| "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig", | |
| "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim" | |
| }, | |
| "block_size": 1024, | |
| "bos_token_id": 50256, | |
| "embd_pdrop": 0.1, | |
| "eos_token_id": 50256, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "model_type": "gpt_optimized", | |
| "n_embd": 1280, | |
| "n_head": 32, | |
| "n_inner": null, | |
| "n_layer": 48, | |
| "n_positions": 1024, | |
| "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, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.39.3", | |
| "use_cache": true, | |
| "vocab_size": 50257 | |
| } | |