Upload T5ForConditionalGeneration
Browse files- config.json +32 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
    	
        config.json
    ADDED
    
    | @@ -0,0 +1,32 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "_name_or_path": "/share/t5_translate_en_ru_zh_small_1024",
         | 
| 3 | 
            +
              "architectures": [
         | 
| 4 | 
            +
                "T5ForConditionalGeneration"
         | 
| 5 | 
            +
              ],
         | 
| 6 | 
            +
              "classifier_dropout": 0.0,
         | 
| 7 | 
            +
              "d_ff": 1024,
         | 
| 8 | 
            +
              "d_kv": 64,
         | 
| 9 | 
            +
              "d_model": 512,
         | 
| 10 | 
            +
              "decoder_start_token_id": 0,
         | 
| 11 | 
            +
              "dense_act_fn": "gelu_new",
         | 
| 12 | 
            +
              "dropout_rate": 0.1,
         | 
| 13 | 
            +
              "eos_token_id": 1,
         | 
| 14 | 
            +
              "feed_forward_proj": "gated-gelu",
         | 
| 15 | 
            +
              "initializer_factor": 1.0,
         | 
| 16 | 
            +
              "is_encoder_decoder": true,
         | 
| 17 | 
            +
              "is_gated_act": true,
         | 
| 18 | 
            +
              "layer_norm_epsilon": 1e-06,
         | 
| 19 | 
            +
              "model_type": "t5",
         | 
| 20 | 
            +
              "num_decoder_layers": 8,
         | 
| 21 | 
            +
              "num_heads": 6,
         | 
| 22 | 
            +
              "num_layers": 8,
         | 
| 23 | 
            +
              "output_past": true,
         | 
| 24 | 
            +
              "pad_token_id": 0,
         | 
| 25 | 
            +
              "relative_attention_max_distance": 128,
         | 
| 26 | 
            +
              "relative_attention_num_buckets": 32,
         | 
| 27 | 
            +
              "tie_word_embeddings": false,
         | 
| 28 | 
            +
              "torch_dtype": "float32",
         | 
| 29 | 
            +
              "transformers_version": "4.36.2",
         | 
| 30 | 
            +
              "use_cache": true,
         | 
| 31 | 
            +
              "vocab_size": 65100
         | 
| 32 | 
            +
            }
         | 
    	
        generation_config.json
    ADDED
    
    | @@ -0,0 +1,6 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "decoder_start_token_id": 0,
         | 
| 3 | 
            +
              "eos_token_id": 1,
         | 
| 4 | 
            +
              "pad_token_id": 0,
         | 
| 5 | 
            +
              "transformers_version": "4.36.2"
         | 
| 6 | 
            +
            }
         | 
    	
        model.safetensors
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:dca087ae1ac368b5d8d1197e84e32f1e7f8a4454db2039dd73fc38105b815d41
         | 
| 3 | 
            +
            size 442920360
         | 
