Upload folder using huggingface_hub
Browse files- checkpoint_1400/config.json +38 -0
- checkpoint_1400/generation_config.json +6 -0
- checkpoint_1400/merges.txt +0 -0
- checkpoint_1400/model.safetensors +3 -0
- checkpoint_1400/special_tokens_map.json +24 -0
- checkpoint_1400/tokenizer.json +0 -0
- checkpoint_1400/tokenizer_config.json +22 -0
- checkpoint_1400/vocab.json +0 -0
    	
        checkpoint_1400/config.json
    ADDED
    
    | @@ -0,0 +1,38 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "activation_function": "gelu_new",
         | 
| 3 | 
            +
              "architectures": [
         | 
| 4 | 
            +
                "GPT2LMHeadModel"
         | 
| 5 | 
            +
              ],
         | 
| 6 | 
            +
              "attn_pdrop": 0.1,
         | 
| 7 | 
            +
              "bos_token_id": 50256,
         | 
| 8 | 
            +
              "embd_pdrop": 0.1,
         | 
| 9 | 
            +
              "eos_token_id": 50256,
         | 
| 10 | 
            +
              "initializer_range": 0.02,
         | 
| 11 | 
            +
              "layer_norm_epsilon": 1e-05,
         | 
| 12 | 
            +
              "model_type": "gpt2",
         | 
| 13 | 
            +
              "n_ctx": 512,
         | 
| 14 | 
            +
              "n_embd": 1024,
         | 
| 15 | 
            +
              "n_head": 16,
         | 
| 16 | 
            +
              "n_inner": null,
         | 
| 17 | 
            +
              "n_layer": 12,
         | 
| 18 | 
            +
              "n_positions": 1024,
         | 
| 19 | 
            +
              "reorder_and_upcast_attn": false,
         | 
| 20 | 
            +
              "resid_pdrop": 0.1,
         | 
| 21 | 
            +
              "scale_attn_by_inverse_layer_idx": false,
         | 
| 22 | 
            +
              "scale_attn_weights": true,
         | 
| 23 | 
            +
              "summary_activation": null,
         | 
| 24 | 
            +
              "summary_first_dropout": 0.1,
         | 
| 25 | 
            +
              "summary_proj_to_labels": true,
         | 
| 26 | 
            +
              "summary_type": "cls_index",
         | 
| 27 | 
            +
              "summary_use_proj": true,
         | 
| 28 | 
            +
              "task_specific_params": {
         | 
| 29 | 
            +
                "text-generation": {
         | 
| 30 | 
            +
                  "do_sample": true,
         | 
| 31 | 
            +
                  "max_length": 50
         | 
| 32 | 
            +
                }
         | 
| 33 | 
            +
              },
         | 
| 34 | 
            +
              "torch_dtype": "bfloat16",
         | 
| 35 | 
            +
              "transformers_version": "4.51.2",
         | 
| 36 | 
            +
              "use_cache": true,
         | 
| 37 | 
            +
              "vocab_size": 50257
         | 
| 38 | 
            +
            }
         | 
    	
        checkpoint_1400/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": "4.51.2"
         | 
| 6 | 
            +
            }
         | 
    	
        checkpoint_1400/merges.txt
    ADDED
    
    | The diff for this file is too large to render. 
		See raw diff | 
|  | 
    	
        checkpoint_1400/model.safetensors
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:a46df8d2d0d099d130368d6b7d1e9b451b8588296e9678f6d011a29228da459d
         | 
| 3 | 
            +
            size 407352216
         | 
    	
        checkpoint_1400/special_tokens_map.json
    ADDED
    
    | @@ -0,0 +1,24 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "bos_token": {
         | 
| 3 | 
            +
                "content": "<|endoftext|>",
         | 
| 4 | 
            +
                "lstrip": false,
         | 
| 5 | 
            +
                "normalized": true,
         | 
| 6 | 
            +
                "rstrip": false,
         | 
| 7 | 
            +
                "single_word": false
         | 
| 8 | 
            +
              },
         | 
| 9 | 
            +
              "eos_token": {
         | 
| 10 | 
            +
                "content": "<|endoftext|>",
         | 
| 11 | 
            +
                "lstrip": false,
         | 
| 12 | 
            +
                "normalized": true,
         | 
| 13 | 
            +
                "rstrip": false,
         | 
| 14 | 
            +
                "single_word": false
         | 
| 15 | 
            +
              },
         | 
| 16 | 
            +
              "pad_token": "<|endoftext|>",
         | 
| 17 | 
            +
              "unk_token": {
         | 
| 18 | 
            +
                "content": "<|endoftext|>",
         | 
| 19 | 
            +
                "lstrip": false,
         | 
| 20 | 
            +
                "normalized": true,
         | 
| 21 | 
            +
                "rstrip": false,
         | 
| 22 | 
            +
                "single_word": false
         | 
| 23 | 
            +
              }
         | 
| 24 | 
            +
            }
         | 
    	
        checkpoint_1400/tokenizer.json
    ADDED
    
    | The diff for this file is too large to render. 
		See raw diff | 
|  | 
    	
        checkpoint_1400/tokenizer_config.json
    ADDED
    
    | @@ -0,0 +1,22 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "add_prefix_space": false,
         | 
| 3 | 
            +
              "added_tokens_decoder": {
         | 
| 4 | 
            +
                "50256": {
         | 
| 5 | 
            +
                  "content": "<|endoftext|>",
         | 
| 6 | 
            +
                  "lstrip": false,
         | 
| 7 | 
            +
                  "normalized": true,
         | 
| 8 | 
            +
                  "rstrip": false,
         | 
| 9 | 
            +
                  "single_word": false,
         | 
| 10 | 
            +
                  "special": true
         | 
| 11 | 
            +
                }
         | 
| 12 | 
            +
              },
         | 
| 13 | 
            +
              "bos_token": "<|endoftext|>",
         | 
| 14 | 
            +
              "clean_up_tokenization_spaces": false,
         | 
| 15 | 
            +
              "eos_token": "<|endoftext|>",
         | 
| 16 | 
            +
              "extra_special_tokens": {},
         | 
| 17 | 
            +
              "model_max_length": 1024,
         | 
| 18 | 
            +
              "pad_token": "<|endoftext|>",
         | 
| 19 | 
            +
              "padding_side": "left",
         | 
| 20 | 
            +
              "tokenizer_class": "GPT2Tokenizer",
         | 
| 21 | 
            +
              "unk_token": "<|endoftext|>"
         | 
| 22 | 
            +
            }
         | 
    	
        checkpoint_1400/vocab.json
    ADDED
    
    | The diff for this file is too large to render. 
		See raw diff | 
|  |