(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 | 
            -
              "eos_token_id": 151645,
         | 
| 8 | 
            -
              "hidden_act": "silu",
         | 
| 9 | 
            -
              "hidden_size": 2048,
         | 
| 10 | 
            -
              "initializer_range": 0.02,
         | 
| 11 | 
            -
              "intermediate_size": 11008,
         | 
| 12 | 
            -
              "max_position_embeddings": 32768,
         | 
| 13 | 
            -
              "max_window_layers": 70,
         | 
| 14 | 
            -
              "model_type": "qwen2",
         | 
| 15 | 
            -
              "num_attention_heads": 16,
         | 
| 16 | 
            -
              "num_hidden_layers": 36,
         | 
| 17 | 
            -
              "num_key_value_heads": 2,
         | 
| 18 | 
            -
              "pad_token_id": 151654,
         | 
| 19 | 
            -
              "rms_norm_eps": 1e-06,
         | 
| 20 | 
            -
              "rope_scaling": null,
         | 
| 21 | 
            -
              "rope_theta": 1000000.0,
         | 
| 22 | 
            -
              "sliding_window": null,
         | 
| 23 | 
            -
              "tie_word_embeddings": true,
         | 
| 24 | 
            -
              "torch_dtype": "bfloat16",
         | 
| 25 | 
            -
              "transformers_version": "4.48.3",
         | 
| 26 | 
            -
              "unsloth_fixed": true,
         | 
| 27 | 
            -
              "unsloth_version": "2025.2.5",
         | 
| 28 | 
            -
              "use_cache": true,
         | 
| 29 | 
            -
              "use_sliding_window": false,
         | 
| 30 | 
            -
              "vocab_size": 151936
         | 
| 31 | 
            -
            }
         | 
|  | |
| 1 | 
             
            {
         | 
| 2 | 
            +
                "model_type": "qwen2"
         | 
| 3 | 
            +
            }
         | 
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
