Upload 15 files
Browse files- added_tokens.json +4 -0
- config.json +46 -0
- generation_config.json +9 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +39 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
- vocab.json +0 -0
    	
        added_tokens.json
    ADDED
    
    | @@ -0,0 +1,4 @@ | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "<|pad|>": 30001,
         | 
| 3 | 
            +
              "<|system|>": 30000
         | 
| 4 | 
            +
            }
         | 
    	
        config.json
    ADDED
    
    | @@ -0,0 +1,46 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "activation_function": "gelu_new",
         | 
| 3 | 
            +
              "architectures": [
         | 
| 4 | 
            +
                "GPT2LMHeadModel"
         | 
| 5 | 
            +
              ],
         | 
| 6 | 
            +
              "attn_pdrop": 0.1,
         | 
| 7 | 
            +
              "bos_token_id": 30000,
         | 
| 8 | 
            +
              "dtype": "float32",
         | 
| 9 | 
            +
              "embd_pdrop": 0.1,
         | 
| 10 | 
            +
              "eos_token_id": 0,
         | 
| 11 | 
            +
              "gradient_checkpointing": false,
         | 
| 12 | 
            +
              "initializer_range": 0.02,
         | 
| 13 | 
            +
              "layer_norm_epsilon": 1e-05,
         | 
| 14 | 
            +
              "model_type": "gpt2",
         | 
| 15 | 
            +
              "n_ctx": 1024,
         | 
| 16 | 
            +
              "n_embd": 768,
         | 
| 17 | 
            +
              "n_head": 12,
         | 
| 18 | 
            +
              "n_inner": null,
         | 
| 19 | 
            +
              "n_layer": 12,
         | 
| 20 | 
            +
              "n_positions": 1024,
         | 
| 21 | 
            +
              "pad_token_id": 30001,
         | 
| 22 | 
            +
              "reorder_and_upcast_attn": false,
         | 
| 23 | 
            +
              "resid_pdrop": 0.1,
         | 
| 24 | 
            +
              "scale_attn_by_inverse_layer_idx": false,
         | 
| 25 | 
            +
              "scale_attn_weights": true,
         | 
| 26 | 
            +
              "summary_activation": null,
         | 
| 27 | 
            +
              "summary_first_dropout": 0.1,
         | 
| 28 | 
            +
              "summary_proj_to_labels": true,
         | 
| 29 | 
            +
              "summary_type": "cls_index",
         | 
| 30 | 
            +
              "summary_use_proj": true,
         | 
| 31 | 
            +
              "task_specific_params": {
         | 
| 32 | 
            +
                "text-generation": {
         | 
| 33 | 
            +
                  "do_sample": true,
         | 
| 34 | 
            +
                  "max_length": 100,
         | 
| 35 | 
            +
                  "no_repeat_ngram_size": 4,
         | 
| 36 | 
            +
                  "num_beams": 10,
         | 
| 37 | 
            +
                  "repetition_penalty": 10.0,
         | 
| 38 | 
            +
                  "temperature": 2.0,
         | 
| 39 | 
            +
                  "top_k": 20,
         | 
| 40 | 
            +
                  "top_p": 0.9
         | 
| 41 | 
            +
                }
         | 
| 42 | 
            +
              },
         | 
| 43 | 
            +
              "transformers_version": "4.57.0",
         | 
| 44 | 
            +
              "use_cache": true,
         | 
| 45 | 
            +
              "vocab_size": 30002
         | 
| 46 | 
            +
            }
         | 
    	
        generation_config.json
    ADDED
    
    | @@ -0,0 +1,9 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "_from_model_config": true,
         | 
| 3 | 
            +
              "bos_token_id": 30000,
         | 
| 4 | 
            +
              "eos_token_id": [
         | 
| 5 | 
            +
                0
         | 
| 6 | 
            +
              ],
         | 
| 7 | 
            +
              "pad_token_id": 30001,
         | 
| 8 | 
            +
              "transformers_version": "4.57.0"
         | 
| 9 | 
            +
            }
         | 
    	
        merges.txt
    ADDED
    
    | The diff for this file is too large to render. 
		See raw diff | 
|  | 
    	
        model.safetensors
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:dded4065753de3021ad61f7fe192646787019146cb18cf38fcab5612afc434a6
         | 
| 3 | 
            +
            size 435550848
         | 
    	
        optimizer.pt
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:1638513f196f3231a877ea703afd20080b2ea07cab9df03d7a95e67874f1c0c2
         | 
| 3 | 
            +
            size 871198091
         | 
    	
        rng_state.pth
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:24f1812ae5029e60423075de8b1ce8a73f0965c778c75443f40350fb49c15424
         | 
| 3 | 
            +
            size 14645
         | 
    	
        scaler.pt
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:7d4eeb4982c086f815180d4e480e501809bc353750323ea2bd07aa0bc6cf2f06
         | 
| 3 | 
            +
            size 1383
         | 
    	
        scheduler.pt
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:3877bae0965bc58838137134f4ed5a0dd87b05a25537a52312a7c3aae5a690c9
         | 
| 3 | 
            +
            size 1465
         | 
    	
        special_tokens_map.json
    ADDED
    
    | @@ -0,0 +1,30 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "bos_token": {
         | 
| 3 | 
            +
                "content": "<|system|>",
         | 
| 4 | 
            +
                "lstrip": false,
         | 
| 5 | 
            +
                "normalized": false,
         | 
| 6 | 
            +
                "rstrip": false,
         | 
| 7 | 
            +
                "single_word": false
         | 
| 8 | 
            +
              },
         | 
| 9 | 
            +
              "eos_token": {
         | 
| 10 | 
            +
                "content": "<|endoftext|>",
         | 
| 11 | 
            +
                "lstrip": false,
         | 
| 12 | 
            +
                "normalized": false,
         | 
| 13 | 
            +
                "rstrip": false,
         | 
| 14 | 
            +
                "single_word": false
         | 
| 15 | 
            +
              },
         | 
| 16 | 
            +
              "pad_token": {
         | 
| 17 | 
            +
                "content": "<|pad|>",
         | 
| 18 | 
            +
                "lstrip": false,
         | 
| 19 | 
            +
                "normalized": false,
         | 
| 20 | 
            +
                "rstrip": false,
         | 
| 21 | 
            +
                "single_word": false
         | 
| 22 | 
            +
              },
         | 
| 23 | 
            +
              "unk_token": {
         | 
| 24 | 
            +
                "content": "<|endoftext|>",
         | 
| 25 | 
            +
                "lstrip": false,
         | 
| 26 | 
            +
                "normalized": true,
         | 
| 27 | 
            +
                "rstrip": false,
         | 
| 28 | 
            +
                "single_word": false
         | 
| 29 | 
            +
              }
         | 
| 30 | 
            +
            }
         | 
    	
        tokenizer.json
    ADDED
    
    | The diff for this file is too large to render. 
		See raw diff | 
|  | 
    	
        tokenizer_config.json
    ADDED
    
    | @@ -0,0 +1,39 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "add_bos_token": false,
         | 
| 3 | 
            +
              "add_prefix_space": false,
         | 
| 4 | 
            +
              "added_tokens_decoder": {
         | 
| 5 | 
            +
                "0": {
         | 
| 6 | 
            +
                  "content": "<|endoftext|>",
         | 
| 7 | 
            +
                  "lstrip": false,
         | 
| 8 | 
            +
                  "normalized": false,
         | 
| 9 | 
            +
                  "rstrip": false,
         | 
| 10 | 
            +
                  "single_word": false,
         | 
| 11 | 
            +
                  "special": true
         | 
| 12 | 
            +
                },
         | 
| 13 | 
            +
                "30000": {
         | 
| 14 | 
            +
                  "content": "<|system|>",
         | 
| 15 | 
            +
                  "lstrip": false,
         | 
| 16 | 
            +
                  "normalized": false,
         | 
| 17 | 
            +
                  "rstrip": false,
         | 
| 18 | 
            +
                  "single_word": false,
         | 
| 19 | 
            +
                  "special": true
         | 
| 20 | 
            +
                },
         | 
| 21 | 
            +
                "30001": {
         | 
| 22 | 
            +
                  "content": "<|pad|>",
         | 
| 23 | 
            +
                  "lstrip": false,
         | 
| 24 | 
            +
                  "normalized": false,
         | 
| 25 | 
            +
                  "rstrip": false,
         | 
| 26 | 
            +
                  "single_word": false,
         | 
| 27 | 
            +
                  "special": true
         | 
| 28 | 
            +
                }
         | 
| 29 | 
            +
              },
         | 
| 30 | 
            +
              "bos_token": "<|system|>",
         | 
| 31 | 
            +
              "clean_up_tokenization_spaces": false,
         | 
| 32 | 
            +
              "eos_token": "<|endoftext|>",
         | 
| 33 | 
            +
              "errors": "replace",
         | 
| 34 | 
            +
              "extra_special_tokens": {},
         | 
| 35 | 
            +
              "model_max_length": 1000000000000000019884624838656,
         | 
| 36 | 
            +
              "pad_token": "<|pad|>",
         | 
| 37 | 
            +
              "tokenizer_class": "GPT2Tokenizer",
         | 
| 38 | 
            +
              "unk_token": "<|endoftext|>"
         | 
| 39 | 
            +
            }
         | 
    	
        trainer_state.json
    ADDED
    
    | The diff for this file is too large to render. 
		See raw diff | 
|  | 
    	
        training_args.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:aef5f4b1d6f0c7aa5550b945ec54f29546ab65510ef7c46198dcd3b903f7ad54
         | 
| 3 | 
            +
            size 5777
         | 
    	
        vocab.json
    ADDED
    
    | The diff for this file is too large to render. 
		See raw diff | 
|  | 
