Add checkpoint for ext1730
Browse files- config.json +3 -3
- pytorch_model.bin +1 -1
    	
        config.json
    CHANGED
    
    | @@ -16,7 +16,7 @@ | |
| 16 | 
             
              "embedding_dropout": 0.0,
         | 
| 17 | 
             
              "eos_token_id": 50282,
         | 
| 18 | 
             
              "global_attn_every_n_layers": 3,
         | 
| 19 | 
            -
              "global_rope_theta":  | 
| 20 | 
             
              "gradient_checkpointing": false,
         | 
| 21 | 
             
              "hidden_activation": "gelu",
         | 
| 22 | 
             
              "hidden_size": 768,
         | 
| @@ -25,8 +25,8 @@ | |
| 25 | 
             
              "intermediate_size": 1152,
         | 
| 26 | 
             
              "layer_norm_eps": 1e-05,
         | 
| 27 | 
             
              "local_attention": 128,
         | 
| 28 | 
            -
              "local_rope_theta":  | 
| 29 | 
            -
              "max_position_embeddings":  | 
| 30 | 
             
              "mlp_bias": false,
         | 
| 31 | 
             
              "mlp_dropout": 0.0,
         | 
| 32 | 
             
              "model_type": "modernbert",
         | 
|  | |
| 16 | 
             
              "embedding_dropout": 0.0,
         | 
| 17 | 
             
              "eos_token_id": 50282,
         | 
| 18 | 
             
              "global_attn_every_n_layers": 3,
         | 
| 19 | 
            +
              "global_rope_theta": 160000.0,
         | 
| 20 | 
             
              "gradient_checkpointing": false,
         | 
| 21 | 
             
              "hidden_activation": "gelu",
         | 
| 22 | 
             
              "hidden_size": 768,
         | 
|  | |
| 25 | 
             
              "intermediate_size": 1152,
         | 
| 26 | 
             
              "layer_norm_eps": 1e-05,
         | 
| 27 | 
             
              "local_attention": 128,
         | 
| 28 | 
            +
              "local_rope_theta": 160000.0,
         | 
| 29 | 
            +
              "max_position_embeddings": 7999,
         | 
| 30 | 
             
              "mlp_bias": false,
         | 
| 31 | 
             
              "mlp_dropout": 0.0,
         | 
| 32 | 
             
              "model_type": "modernbert",
         | 
    	
        pytorch_model.bin
    CHANGED
    
    | @@ -1,3 +1,3 @@ | |
| 1 | 
             
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            -
            oid sha256: | 
| 3 | 
             
            size 598664174
         | 
|  | |
| 1 | 
             
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:eb72de3c2866a940f77bad6c2933d343fa362f529ba0ba27034f7c5237cdc9ac
         | 
| 3 | 
             
            size 598664174
         | 

