Spaces:
				
			
			
	
			
			
		Sleeping
		
	
	
	
			
			
	
	
	
	
		
		
		Sleeping
		
	Create config.json
Browse files- config.json +35 -0
    	
        config.json
    ADDED
    
    | @@ -0,0 +1,35 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "architectures": [
         | 
| 3 | 
            +
                "Qwen3ForCausalLM"
         | 
| 4 | 
            +
              ],
         | 
| 5 | 
            +
              "attention_bias": false,
         | 
| 6 | 
            +
              "attention_dropout": 0.0,
         | 
| 7 | 
            +
              "bos_token_id": 151643,
         | 
| 8 | 
            +
              "eos_token_id": 151645,
         | 
| 9 | 
            +
              "head_dim": 128,
         | 
| 10 | 
            +
              "hidden_act": "silu",
         | 
| 11 | 
            +
              "hidden_size": 2560,
         | 
| 12 | 
            +
              "initializer_range": 0.02,
         | 
| 13 | 
            +
              "intermediate_size": 9728,
         | 
| 14 | 
            +
              "max_position_embeddings": 131072,
         | 
| 15 | 
            +
              "max_window_layers": 36,
         | 
| 16 | 
            +
              "model_type": "qwen3",
         | 
| 17 | 
            +
              "num_attention_heads": 32,
         | 
| 18 | 
            +
              "num_hidden_layers": 36,
         | 
| 19 | 
            +
              "num_key_value_heads": 8,
         | 
| 20 | 
            +
              "rms_norm_eps": 1e-06,
         | 
| 21 | 
            +
              "rope_scaling": {
         | 
| 22 | 
            +
                "factor": 4.0,
         | 
| 23 | 
            +
                "original_max_position_embeddings": 32768,
         | 
| 24 | 
            +
                "rope_type": "yarn",
         | 
| 25 | 
            +
                "type": "yarn"
         | 
| 26 | 
            +
              },
         | 
| 27 | 
            +
              "rope_theta": 1000000,
         | 
| 28 | 
            +
              "sliding_window": null,
         | 
| 29 | 
            +
              "tie_word_embeddings": true,
         | 
| 30 | 
            +
              "torch_dtype": "bfloat16",
         | 
| 31 | 
            +
              "transformers_version": "4.51.0",
         | 
| 32 | 
            +
              "use_cache": true,
         | 
| 33 | 
            +
              "use_sliding_window": false,
         | 
| 34 | 
            +
              "vocab_size": 151936
         | 
| 35 | 
            +
            }
         | 
