cstr's picture
Upload folder using huggingface_hub
c1ecce2 verified
{
"_name_or_path": "cstr/wmt21-dense-24-wide-en-x-st",
"activation_dropout": 0.0,
"activation_function": "relu",
"architectures": [
"M2M100ForConditionalGeneration"
],
"attention_dropout": 0.1,
"bos_token_id": 0,
"d_model": 2048,
"decoder_attention_heads": 32,
"decoder_ffn_dim": 16384,
"decoder_layerdrop": 0,
"decoder_layers": 24,
"decoder_start_token_id": 2,
"dropout": 0.1,
"encoder_attention_heads": 32,
"encoder_ffn_dim": 16384,
"encoder_layerdrop": 0,
"encoder_layers": 24,
"eos_token_id": 2,
"init_std": 0.02,
"is_encoder_decoder": true,
"max_length": 200,
"max_position_embeddings": 1024,
"model_type": "m2m_100",
"num_beams": 5,
"num_hidden_layers": 24,
"pad_token_id": 1,
"quantization_config": {
"_load_in_4bit": false,
"_load_in_8bit": true,
"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,
"quant_method": "bitsandbytes"
},
"scale_embedding": true,
"torch_dtype": "float16",
"transformers_version": "4.38.2",
"use_cache": true,
"vocab_size": 128009
}