iter_0040000
Browse files- config.json +36 -0
- pytorch_model.bin +3 -0
    	
        config.json
    ADDED
    
    | @@ -0,0 +1,36 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "activation_function": "gelu_fast",
         | 
| 3 | 
            +
              "architectures": [
         | 
| 4 | 
            +
                "GPT2LMHeadCustomModel"
         | 
| 5 | 
            +
              ],
         | 
| 6 | 
            +
              "attention_head_type": "multiquery",
         | 
| 7 | 
            +
              "attn_pdrop": 0.1,
         | 
| 8 | 
            +
              "auto_map": {
         | 
| 9 | 
            +
                "AutoConfig": "configuration_gpt2_mq.GPT2CustomConfig",
         | 
| 10 | 
            +
                "AutoModelForCausalLM": "modeling_gpt2_mq.GPT2LMHeadCustomModel"
         | 
| 11 | 
            +
              },
         | 
| 12 | 
            +
              "bos_token_id": 50256,
         | 
| 13 | 
            +
              "embd_pdrop": 0.1,
         | 
| 14 | 
            +
              "eos_token_id": 50256,
         | 
| 15 | 
            +
              "initializer_range": 0.02,
         | 
| 16 | 
            +
              "layer_norm_epsilon": 1e-05,
         | 
| 17 | 
            +
              "model_type": "gpt2",
         | 
| 18 | 
            +
              "n_embd": 2048,
         | 
| 19 | 
            +
              "n_head": 16,
         | 
| 20 | 
            +
              "n_inner": 8192,
         | 
| 21 | 
            +
              "n_layer": 24,
         | 
| 22 | 
            +
              "n_positions": 2048,
         | 
| 23 | 
            +
              "reorder_and_upcast_attn": false,
         | 
| 24 | 
            +
              "resid_pdrop": 0.1,
         | 
| 25 | 
            +
              "scale_attn_by_inverse_layer_idx": false,
         | 
| 26 | 
            +
              "scale_attn_weights": true,
         | 
| 27 | 
            +
              "summary_activation": null,
         | 
| 28 | 
            +
              "summary_first_dropout": 0.1,
         | 
| 29 | 
            +
              "summary_proj_to_labels": true,
         | 
| 30 | 
            +
              "summary_type": "cls_index",
         | 
| 31 | 
            +
              "summary_use_proj": true,
         | 
| 32 | 
            +
              "torch_dtype": "float32",
         | 
| 33 | 
            +
              "transformers_version": "4.24.0",
         | 
| 34 | 
            +
              "use_cache": true,
         | 
| 35 | 
            +
              "vocab_size": 49280
         | 
| 36 | 
            +
            }
         | 
    	
        pytorch_model.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:4b897eff168c2a9be476c6d6db233d639978a1f3be3aa0133497c573d0b43463
         | 
| 3 | 
            +
            size 4600328417
         |