| { | |
| "_name_or_path": "/mnt/scratch/output_models/test020-20k/checkpoint-2000", | |
| "alibi": false, | |
| "apply_residual_connection_post_layernorm": false, | |
| "architectures": [ | |
| "RWForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_RW.RWConfig", | |
| "AutoModel": "modelling_RW.RWModel", | |
| "AutoModelForCausalLM": "modelling_RW.RWForCausalLM", | |
| "AutoModelForQuestionAnswering": "modelling_RW.RWForQuestionAnswering", | |
| "AutoModelForSequenceClassification": "modelling_RW.RWForSequenceClassification", | |
| "AutoModelForTokenClassification": "modelling_RW.RWForTokenClassification" | |
| }, | |
| "bias": false, | |
| "bos_token_id": 11, | |
| "eos_token_id": 11, | |
| "hidden_dropout": 0.0, | |
| "hidden_size": 8192, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "model_type": "RefinedWeb", | |
| "n_head": 128, | |
| "n_head_kv": 8, | |
| "n_layer": 60, | |
| "parallel_attn": true, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.31.0", | |
| "use_cache": true, | |
| "rope_theta": 1000000, | |
| "vocab_size": 65040 | |
| } | |