Adding ONNX file of this model
Browse filesBeep boop I am the [ONNX export bot 🤖🏎️](https://huggingface.co/spaces/onnx/export). On behalf of [fxmarty](https://huggingface.co/fxmarty), I would like to add to this repository the model converted to ONNX.
What is ONNX? It stands for "Open Neural Network Exchange", and is the most commonly used open standard for machine learning interoperability. You can find out more at [onnx.ai](https://onnx.ai/)!
The exported ONNX model can be then be consumed by various backends as TensorRT or TVM, or simply be used in a few lines with 🤗 Optimum through ONNX Runtime, check out how [here](https://huggingface.co/docs/optimum/main/en/onnxruntime/usage_guides/models)!
- onnx/config.json +38 -0
 - onnx/decoder_model.onnx +3 -0
 - onnx/decoder_model_merged.onnx +3 -0
 - onnx/decoder_with_past_model.onnx +3 -0
 - onnx/generation_config.json +6 -0
 - onnx/merges.txt +0 -0
 - onnx/special_tokens_map.json +5 -0
 - onnx/tokenizer.json +0 -0
 - onnx/tokenizer_config.json +9 -0
 - onnx/vocab.json +0 -0
 
    	
        onnx/config.json
    ADDED
    
    | 
         @@ -0,0 +1,38 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            {
         
     | 
| 2 | 
         
            +
              "_name_or_path": "gpt2",
         
     | 
| 3 | 
         
            +
              "activation_function": "gelu_new",
         
     | 
| 4 | 
         
            +
              "architectures": [
         
     | 
| 5 | 
         
            +
                "GPT2LMHeadModel"
         
     | 
| 6 | 
         
            +
              ],
         
     | 
| 7 | 
         
            +
              "attn_pdrop": 0.1,
         
     | 
| 8 | 
         
            +
              "bos_token_id": 50256,
         
     | 
| 9 | 
         
            +
              "embd_pdrop": 0.1,
         
     | 
| 10 | 
         
            +
              "eos_token_id": 50256,
         
     | 
| 11 | 
         
            +
              "initializer_range": 0.02,
         
     | 
| 12 | 
         
            +
              "layer_norm_epsilon": 1e-05,
         
     | 
| 13 | 
         
            +
              "model_type": "gpt2",
         
     | 
| 14 | 
         
            +
              "n_ctx": 1024,
         
     | 
| 15 | 
         
            +
              "n_embd": 768,
         
     | 
| 16 | 
         
            +
              "n_head": 12,
         
     | 
| 17 | 
         
            +
              "n_inner": null,
         
     | 
| 18 | 
         
            +
              "n_layer": 12,
         
     | 
| 19 | 
         
            +
              "n_positions": 1024,
         
     | 
| 20 | 
         
            +
              "reorder_and_upcast_attn": false,
         
     | 
| 21 | 
         
            +
              "resid_pdrop": 0.1,
         
     | 
| 22 | 
         
            +
              "scale_attn_by_inverse_layer_idx": false,
         
     | 
| 23 | 
         
            +
              "scale_attn_weights": true,
         
     | 
| 24 | 
         
            +
              "summary_activation": null,
         
     | 
| 25 | 
         
            +
              "summary_first_dropout": 0.1,
         
     | 
| 26 | 
         
            +
              "summary_proj_to_labels": true,
         
     | 
| 27 | 
         
            +
              "summary_type": "cls_index",
         
     | 
| 28 | 
         
            +
              "summary_use_proj": true,
         
     | 
| 29 | 
         
            +
              "task_specific_params": {
         
     | 
| 30 | 
         
            +
                "text-generation": {
         
     | 
| 31 | 
         
            +
                  "do_sample": true,
         
     | 
| 32 | 
         
            +
                  "max_length": 50
         
     | 
| 33 | 
         
            +
                }
         
     | 
| 34 | 
         
            +
              },
         
     | 
| 35 | 
         
            +
              "transformers_version": "4.30.2",
         
     | 
| 36 | 
         
            +
              "use_cache": true,
         
     | 
| 37 | 
         
            +
              "vocab_size": 50257
         
     | 
| 38 | 
         
            +
            }
         
     | 
    	
        onnx/decoder_model.onnx
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:e3fc9615868ff8f5e0429b892a0f6ca692784ba6c4ca31c4e9ee8218e7cce34f
         
     | 
| 3 | 
         
            +
            size 653665842
         
     | 
    	
        onnx/decoder_model_merged.onnx
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:e6fc046fe5a7cfeeb8bb3c7d4c1b6a8bd90ced7339a75d5567957e3bc9d48abe
         
     | 
| 3 | 
         
            +
            size 655189339
         
     | 
    	
        onnx/decoder_with_past_model.onnx
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:570d958241de81f12d82a8358dfc0b408a7bf44ff2bd10ac4a97dab24a8118db
         
     | 
| 3 | 
         
            +
            size 653672649
         
     | 
    	
        onnx/generation_config.json
    ADDED
    
    | 
         @@ -0,0 +1,6 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            {
         
     | 
| 2 | 
         
            +
              "_from_model_config": true,
         
     | 
| 3 | 
         
            +
              "bos_token_id": 50256,
         
     | 
| 4 | 
         
            +
              "eos_token_id": 50256,
         
     | 
| 5 | 
         
            +
              "transformers_version": "4.30.2"
         
     | 
| 6 | 
         
            +
            }
         
     | 
    	
        onnx/merges.txt
    ADDED
    
    | 
         The diff for this file is too large to render. 
		See raw diff 
     | 
| 
         | 
    	
        onnx/special_tokens_map.json
    ADDED
    
    | 
         @@ -0,0 +1,5 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            {
         
     | 
| 2 | 
         
            +
              "bos_token": "<|endoftext|>",
         
     | 
| 3 | 
         
            +
              "eos_token": "<|endoftext|>",
         
     | 
| 4 | 
         
            +
              "unk_token": "<|endoftext|>"
         
     | 
| 5 | 
         
            +
            }
         
     | 
    	
        onnx/tokenizer.json
    ADDED
    
    | 
         The diff for this file is too large to render. 
		See raw diff 
     | 
| 
         | 
    	
        onnx/tokenizer_config.json
    ADDED
    
    | 
         @@ -0,0 +1,9 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            {
         
     | 
| 2 | 
         
            +
              "add_prefix_space": false,
         
     | 
| 3 | 
         
            +
              "bos_token": "<|endoftext|>",
         
     | 
| 4 | 
         
            +
              "clean_up_tokenization_spaces": true,
         
     | 
| 5 | 
         
            +
              "eos_token": "<|endoftext|>",
         
     | 
| 6 | 
         
            +
              "model_max_length": 1024,
         
     | 
| 7 | 
         
            +
              "tokenizer_class": "GPT2Tokenizer",
         
     | 
| 8 | 
         
            +
              "unk_token": "<|endoftext|>"
         
     | 
| 9 | 
         
            +
            }
         
     | 
    	
        onnx/vocab.json
    ADDED
    
    | 
         The diff for this file is too large to render. 
		See raw diff 
     | 
| 
         |