| { | |
| "_name_or_path": "hebrew-bad_wiki-gpt_neo-tiny", | |
| "activation_function": "gelu_new", | |
| "architectures": [ | |
| "GPTNeoForCausalLM" | |
| ], | |
| "attention_dropout": 0.1, | |
| "attention_layers": [ | |
| "global", | |
| "global", | |
| "global", | |
| "global", | |
| "global", | |
| "global" | |
| ], | |
| "attention_types": [ | |
| [ | |
| [ | |
| "global" | |
| ], | |
| 6 | |
| ] | |
| ], | |
| "bos_token_id": 50256, | |
| "classifier_dropout": 0.1, | |
| "embed_dropout": 0.1, | |
| "eos_token_id": 50256, | |
| "gradient_checkpointing": false, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": null, | |
| "layer_norm_epsilon": 1e-05, | |
| "max_position_embeddings": 1024, | |
| "model_type": "gpt_neo", | |
| "num_heads": 12, | |
| "num_layers": 6, | |
| "quantization_config": { | |
| "_load_in_4bit": true, | |
| "_load_in_8bit": false, | |
| "bnb_4bit_compute_dtype": "float32", | |
| "bnb_4bit_quant_storage": "uint8", | |
| "bnb_4bit_quant_type": "fp4", | |
| "bnb_4bit_use_double_quant": false, | |
| "llm_int8_enable_fp32_cpu_offload": false, | |
| "llm_int8_has_fp16_weight": false, | |
| "llm_int8_skip_modules": null, | |
| "llm_int8_threshold": 6.0, | |
| "load_in_4bit": true, | |
| "load_in_8bit": false, | |
| "quant_method": "bitsandbytes" | |
| }, | |
| "resid_dropout": 0.1, | |
| "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": "4.39.3", | |
| "use_cache": true, | |
| "vocab_size": 50257, | |
| "window_size": 256 | |
| } | |