Upload with huggingface_hub
Browse files- config.json +58 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
    	
        config.json
    ADDED
    
    | @@ -0,0 +1,58 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "_name_or_path": "t5-small",
         | 
| 3 | 
            +
              "architectures": [
         | 
| 4 | 
            +
                "T5ForConditionalGeneration"
         | 
| 5 | 
            +
              ],
         | 
| 6 | 
            +
              "d_ff": 2048,
         | 
| 7 | 
            +
              "d_kv": 64,
         | 
| 8 | 
            +
              "d_model": 512,
         | 
| 9 | 
            +
              "decoder_start_token_id": 0,
         | 
| 10 | 
            +
              "dropout_rate": 0.1,
         | 
| 11 | 
            +
              "eos_token_id": 1,
         | 
| 12 | 
            +
              "feed_forward_proj": "relu",
         | 
| 13 | 
            +
              "initializer_factor": 1.0,
         | 
| 14 | 
            +
              "is_encoder_decoder": true,
         | 
| 15 | 
            +
              "layer_norm_epsilon": 1e-06,
         | 
| 16 | 
            +
              "model_type": "t5",
         | 
| 17 | 
            +
              "n_positions": 512,
         | 
| 18 | 
            +
              "num_decoder_layers": 6,
         | 
| 19 | 
            +
              "num_heads": 8,
         | 
| 20 | 
            +
              "num_layers": 6,
         | 
| 21 | 
            +
              "output_past": true,
         | 
| 22 | 
            +
              "pad_token_id": 0,
         | 
| 23 | 
            +
              "relative_attention_max_distance": 128,
         | 
| 24 | 
            +
              "relative_attention_num_buckets": 32,
         | 
| 25 | 
            +
              "task_specific_params": {
         | 
| 26 | 
            +
                "summarization": {
         | 
| 27 | 
            +
                  "early_stopping": true,
         | 
| 28 | 
            +
                  "length_penalty": 2.0,
         | 
| 29 | 
            +
                  "max_length": 200,
         | 
| 30 | 
            +
                  "min_length": 30,
         | 
| 31 | 
            +
                  "no_repeat_ngram_size": 3,
         | 
| 32 | 
            +
                  "num_beams": 4,
         | 
| 33 | 
            +
                  "prefix": "summarize: "
         | 
| 34 | 
            +
                },
         | 
| 35 | 
            +
                "translation_en_to_de": {
         | 
| 36 | 
            +
                  "early_stopping": true,
         | 
| 37 | 
            +
                  "max_length": 300,
         | 
| 38 | 
            +
                  "num_beams": 4,
         | 
| 39 | 
            +
                  "prefix": "translate English to German: "
         | 
| 40 | 
            +
                },
         | 
| 41 | 
            +
                "translation_en_to_fr": {
         | 
| 42 | 
            +
                  "early_stopping": true,
         | 
| 43 | 
            +
                  "max_length": 300,
         | 
| 44 | 
            +
                  "num_beams": 4,
         | 
| 45 | 
            +
                  "prefix": "translate English to French: "
         | 
| 46 | 
            +
                },
         | 
| 47 | 
            +
                "translation_en_to_ro": {
         | 
| 48 | 
            +
                  "early_stopping": true,
         | 
| 49 | 
            +
                  "max_length": 300,
         | 
| 50 | 
            +
                  "num_beams": 4,
         | 
| 51 | 
            +
                  "prefix": "translate English to Romanian: "
         | 
| 52 | 
            +
                }
         | 
| 53 | 
            +
              },
         | 
| 54 | 
            +
              "torch_dtype": "float32",
         | 
| 55 | 
            +
              "transformers_version": "4.18.0",
         | 
| 56 | 
            +
              "use_cache": false,
         | 
| 57 | 
            +
              "vocab_size": 32100
         | 
| 58 | 
            +
            }
         | 
    	
        pytorch_model.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:a22cc20907597853170013e3a2e036eac43afefa2eb8d328fed2e7dee0dcdac6
         | 
| 3 | 
            +
            size 242012923
         | 
    	
        special_tokens_map.json
    ADDED
    
    | @@ -0,0 +1 @@ | |
|  | 
|  | |
| 1 | 
            +
            {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
         | 
    	
        tokenizer.json
    ADDED
    
    | The diff for this file is too large to render. 
		See raw diff | 
|  | 
    	
        tokenizer_config.json
    ADDED
    
    | @@ -0,0 +1 @@ | |
|  | 
|  | |
| 1 | 
            +
            {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "truncation_side": "left", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "t5-small", "tokenizer_class": "T5Tokenizer"}
         | 
