Upload config.json with huggingface_hub
Browse files- config.json +38 -0
    	
        config.json
    ADDED
    
    | @@ -0,0 +1,38 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "architectures": [
         | 
| 3 | 
            +
                "LlamaForCausalLM"
         | 
| 4 | 
            +
              ],
         | 
| 5 | 
            +
              "attention_bias": false,
         | 
| 6 | 
            +
              "attention_dropout": 0.0,
         | 
| 7 | 
            +
              "bos_token_id": 128000,
         | 
| 8 | 
            +
              "eos_token_id": [
         | 
| 9 | 
            +
                128001,
         | 
| 10 | 
            +
                128008,
         | 
| 11 | 
            +
                128009
         | 
| 12 | 
            +
              ],
         | 
| 13 | 
            +
              "hidden_act": "silu",
         | 
| 14 | 
            +
              "hidden_size": 8192,
         | 
| 15 | 
            +
              "initializer_range": 0.02,
         | 
| 16 | 
            +
              "intermediate_size": 28672,
         | 
| 17 | 
            +
              "max_position_embeddings": 131072,
         | 
| 18 | 
            +
              "mlp_bias": false,
         | 
| 19 | 
            +
              "model_type": "llama",
         | 
| 20 | 
            +
              "num_attention_heads": 64,
         | 
| 21 | 
            +
              "num_hidden_layers": 80,
         | 
| 22 | 
            +
              "num_key_value_heads": 8,
         | 
| 23 | 
            +
              "pretraining_tp": 1,
         | 
| 24 | 
            +
              "rms_norm_eps": 1e-05,
         | 
| 25 | 
            +
              "rope_scaling": {
         | 
| 26 | 
            +
                "factor": 8.0,
         | 
| 27 | 
            +
                "low_freq_factor": 1.0,
         | 
| 28 | 
            +
                "high_freq_factor": 4.0,
         | 
| 29 | 
            +
                "original_max_position_embeddings": 8192,
         | 
| 30 | 
            +
                "rope_type": "llama3"
         | 
| 31 | 
            +
              },
         | 
| 32 | 
            +
              "rope_theta": 500000.0,
         | 
| 33 | 
            +
              "tie_word_embeddings": false,
         | 
| 34 | 
            +
              "torch_dtype": "bfloat16",
         | 
| 35 | 
            +
              "transformers_version": "4.42.3",
         | 
| 36 | 
            +
              "use_cache": true,
         | 
| 37 | 
            +
              "vocab_size": 128256
         | 
| 38 | 
            +
            }
         | 
