| { |
| "_name_or_path": "xlm-roberta-large-squad2", |
| "architectures": [ |
| "XLMRobertaForCausalLM" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "bos_token_id": 0, |
| "classifier_dropout": null, |
| "eos_token_id": 2, |
| "gradient_checkpointing": false, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 1024, |
| "initializer_range": 0.02, |
| "intermediate_size": 4096, |
| "language": "english", |
| "layer_norm_eps": 1e-05, |
| "max_position_embeddings": 514, |
| "model_type": "xlm-roberta", |
| "name": "XLMRoberta", |
| "num_attention_heads": 16, |
| "num_hidden_layers": 24, |
| "output_past": true, |
| "pad_token_id": 1, |
| "position_embedding_type": "absolute", |
| "quantization_config": { |
| "_load_in_4bit": false, |
| "_load_in_8bit": true, |
| "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": false, |
| "load_in_8bit": true, |
| "quant_method": "bitsandbytes" |
| }, |
| "torch_dtype": "float16", |
| "transformers_version": "4.39.3", |
| "type_vocab_size": 1, |
| "use_cache": true, |
| "vocab_size": 250002 |
| } |
|
|
