Upload config.json with huggingface_hub
Browse files- config.json +35 -0
    	
        config.json
    ADDED
    
    | @@ -0,0 +1,35 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
                "architectures": [
         | 
| 3 | 
            +
                    "CohereForCausalLM"
         | 
| 4 | 
            +
                ],
         | 
| 5 | 
            +
                "attention_bias": false,
         | 
| 6 | 
            +
                "attention_dropout": 0.0,
         | 
| 7 | 
            +
                "bos_token_id": 5,
         | 
| 8 | 
            +
                "eos_token_id": 255001,
         | 
| 9 | 
            +
                "hidden_act": "silu",
         | 
| 10 | 
            +
                "hidden_size": 8192,
         | 
| 11 | 
            +
                "initializer_range": 0.02,
         | 
| 12 | 
            +
                "intermediate_size": 24576,
         | 
| 13 | 
            +
                "layer_norm_eps": 1e-05,
         | 
| 14 | 
            +
                "logit_scale": 0.0625,
         | 
| 15 | 
            +
                "max_position_embeddings": 8192,
         | 
| 16 | 
            +
                "model_type": "cohere",
         | 
| 17 | 
            +
                "num_attention_heads": 64,
         | 
| 18 | 
            +
                "num_hidden_layers": 40,
         | 
| 19 | 
            +
                "num_key_value_heads": 8,
         | 
| 20 | 
            +
                "pad_token_id": 0,
         | 
| 21 | 
            +
                "quantization": {
         | 
| 22 | 
            +
                    "group_size": 64,
         | 
| 23 | 
            +
                    "bits": 3
         | 
| 24 | 
            +
                },
         | 
| 25 | 
            +
                "quantization_config": {
         | 
| 26 | 
            +
                    "group_size": 64,
         | 
| 27 | 
            +
                    "bits": 3
         | 
| 28 | 
            +
                },
         | 
| 29 | 
            +
                "rope_theta": 4000000,
         | 
| 30 | 
            +
                "torch_dtype": "bfloat16",
         | 
| 31 | 
            +
                "transformers_version": "4.44.0",
         | 
| 32 | 
            +
                "use_cache": true,
         | 
| 33 | 
            +
                "use_qk_norm": false,
         | 
| 34 | 
            +
                "vocab_size": 256000
         | 
| 35 | 
            +
            }
         |