|
{ |
|
"_name_or_path": "facebook/esm2_t33_650M_UR50D", |
|
"architectures": [ |
|
"EsmForSequenceClassification" |
|
], |
|
"attention_probs_dropout_prob": 0.0, |
|
"classifier_dropout": null, |
|
"emb_layer_norm_before": false, |
|
"esmfold_config": null, |
|
"hidden_act": "gelu", |
|
"hidden_dropout_prob": 0.0, |
|
"hidden_size": 1280, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 5120, |
|
"is_folding_model": false, |
|
"layer_norm_eps": 1e-05, |
|
"mask_token_id": 32, |
|
"max_position_embeddings": 1026, |
|
"model_type": "esm", |
|
"num_attention_heads": 20, |
|
"num_hidden_layers": 33, |
|
"pad_token_id": 1, |
|
"position_embedding_type": "rotary", |
|
"problem_type": "single_label_classification", |
|
"quantization_config": { |
|
"bnb_4bit_compute_dtype": "float32", |
|
"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 |
|
}, |
|
"token_dropout": true, |
|
"torch_dtype": "float16", |
|
"transformers_version": "4.31.0", |
|
"use_cache": true, |
|
"vocab_list": null, |
|
"vocab_size": 33 |
|
} |
|
|