(Trained with Unsloth)
Browse files- config.json +2 -30
 
    	
        config.json
    CHANGED
    
    | 
         @@ -1,31 +1,3 @@ 
     | 
|
| 1 | 
         
             
            {
         
     | 
| 2 | 
         
            -
             
     | 
| 3 | 
         
            -
             
     | 
| 4 | 
         
            -
                "Qwen2ForCausalLM"
         
     | 
| 5 | 
         
            -
              ],
         
     | 
| 6 | 
         
            -
              "attention_dropout": 0.0,
         
     | 
| 7 | 
         
            -
              "bos_token_id": 151643,
         
     | 
| 8 | 
         
            -
              "eos_token_id": 151645,
         
     | 
| 9 | 
         
            -
              "hidden_act": "silu",
         
     | 
| 10 | 
         
            -
              "hidden_size": 896,
         
     | 
| 11 | 
         
            -
              "initializer_range": 0.02,
         
     | 
| 12 | 
         
            -
              "intermediate_size": 4864,
         
     | 
| 13 | 
         
            -
              "max_position_embeddings": 32768,
         
     | 
| 14 | 
         
            -
              "max_window_layers": 21,
         
     | 
| 15 | 
         
            -
              "model_type": "qwen2",
         
     | 
| 16 | 
         
            -
              "num_attention_heads": 14,
         
     | 
| 17 | 
         
            -
              "num_hidden_layers": 24,
         
     | 
| 18 | 
         
            -
              "num_key_value_heads": 2,
         
     | 
| 19 | 
         
            -
              "pad_token_id": 151665,
         
     | 
| 20 | 
         
            -
              "rms_norm_eps": 1e-06,
         
     | 
| 21 | 
         
            -
              "rope_scaling": null,
         
     | 
| 22 | 
         
            -
              "rope_theta": 1000000.0,
         
     | 
| 23 | 
         
            -
              "sliding_window": null,
         
     | 
| 24 | 
         
            -
              "tie_word_embeddings": true,
         
     | 
| 25 | 
         
            -
              "torch_dtype": "float16",
         
     | 
| 26 | 
         
            -
              "transformers_version": "4.44.2",
         
     | 
| 27 | 
         
            -
              "unsloth_version": "2024.10.7",
         
     | 
| 28 | 
         
            -
              "use_cache": true,
         
     | 
| 29 | 
         
            -
              "use_sliding_window": false,
         
     | 
| 30 | 
         
            -
              "vocab_size": 151936
         
     | 
| 31 | 
         
            -
            }
         
     | 
| 
         | 
|
| 1 | 
         
             
            {
         
     | 
| 2 | 
         
            +
                "model_type": "qwen2"
         
     | 
| 3 | 
         
            +
            }
         
     | 
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         |