| { | |
| "_name_or_path": "SebastianSchramm/Cerebras-GPT-111M-instruction", | |
| "activation_function": "gelu", | |
| "architectures": [ | |
| "GPT2LMHeadModel" | |
| ], | |
| "attn_pdrop": 0.0, | |
| "bos_token_id": 50256, | |
| "embd_pdrop": 0.0, | |
| "eos_token_id": 50256, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "model_type": "gpt2", | |
| "n_embd": 768, | |
| "n_head": 12, | |
| "n_inner": 3072, | |
| "n_layer": 10, | |
| "n_positions": 2048, | |
| "quantization_config": { | |
| "batch_size": 1, | |
| "bits": 4, | |
| "block_name_to_quantize": "transformer.h", | |
| "damp_percent": 0.1, | |
| "dataset": "c4", | |
| "desc_act": false, | |
| "disable_exllama": false, | |
| "group_size": 128, | |
| "model_seqlen": 2048, | |
| "module_name_preceding_first_block": [ | |
| "transformer.wte", | |
| "transformer.wpe", | |
| "transformer.drop" | |
| ], | |
| "pad_token_id": null, | |
| "quant_method": "gptq", | |
| "sym": true, | |
| "tokenizer": null, | |
| "true_sequential": true, | |
| "use_cuda_fp16": true | |
| }, | |
| "reorder_and_upcast_attn": false, | |
| "resid_pdrop": 0.0, | |
| "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": "float16", | |
| "transformers_version": "4.33.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 50258 | |
| } | |