| { | |
| "_name_or_path": "/fsx/bigcode/experiments/pretraining/conversions/starcoder-3b", | |
| "activation_function": "gelu_pytorch_tanh", | |
| "architectures": [ | |
| "GPTBigCodeForCausalLM" | |
| ], | |
| "attention_softmax_in_fp32": true, | |
| "multi_query": true, | |
| "attn_pdrop": 0.1, | |
| "bos_token_id": 0, | |
| "embd_pdrop": 0.1, | |
| "eos_token_id": 0, | |
| "inference_runner": 0, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "max_batch_size": null, | |
| "max_sequence_length": null, | |
| "model_type": "gpt_bigcode", | |
| "n_embd": 2816, | |
| "n_head": 22, | |
| "n_inner": 11264, | |
| "n_layer": 36, | |
| "n_positions": 8192, | |
| "pad_key_length": true, | |
| "pre_allocate_kv_cache": false, | |
| "resid_pdrop": 0.1, | |
| "scale_attention_softmax_in_fp32": true, | |
| "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": "float32", | |
| "transformers_version": "4.28.1", | |
| "use_cache": true, | |
| "validate_runner_input": true, | |
| "vocab_size": 49152 | |
| } |