uploaded model
Browse files- config.json +45 -0
    	
        config.json
    ADDED
    
    | @@ -0,0 +1,45 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "_name_or_path": "BEEAR-backdoored-Model-5",
         | 
| 3 | 
            +
              "architectures": [
         | 
| 4 | 
            +
                "LlamaForCausalLM"
         | 
| 5 | 
            +
              ],
         | 
| 6 | 
            +
              "attention_bias": false,
         | 
| 7 | 
            +
              "attention_dropout": 0.0,
         | 
| 8 | 
            +
              "bos_token_id": 1,
         | 
| 9 | 
            +
              "eos_token_id": 2,
         | 
| 10 | 
            +
              "head_dim": 128,
         | 
| 11 | 
            +
              "hidden_act": "silu",
         | 
| 12 | 
            +
              "hidden_size": 4096,
         | 
| 13 | 
            +
              "initializer_range": 0.02,
         | 
| 14 | 
            +
              "intermediate_size": 11008,
         | 
| 15 | 
            +
              "max_position_embeddings": 4096,
         | 
| 16 | 
            +
              "mlp_bias": false,
         | 
| 17 | 
            +
              "model_type": "llama",
         | 
| 18 | 
            +
              "num_attention_heads": 32,
         | 
| 19 | 
            +
              "num_hidden_layers": 32,
         | 
| 20 | 
            +
              "num_key_value_heads": 32,
         | 
| 21 | 
            +
              "pretraining_tp": 1,
         | 
| 22 | 
            +
              "quantization_config": {
         | 
| 23 | 
            +
                "_load_in_4bit": false,
         | 
| 24 | 
            +
                "_load_in_8bit": true,
         | 
| 25 | 
            +
                "bnb_4bit_compute_dtype": "float32",
         | 
| 26 | 
            +
                "bnb_4bit_quant_storage": "uint8",
         | 
| 27 | 
            +
                "bnb_4bit_quant_type": "fp4",
         | 
| 28 | 
            +
                "bnb_4bit_use_double_quant": false,
         | 
| 29 | 
            +
                "llm_int8_enable_fp32_cpu_offload": false,
         | 
| 30 | 
            +
                "llm_int8_has_fp16_weight": false,
         | 
| 31 | 
            +
                "llm_int8_skip_modules": null,
         | 
| 32 | 
            +
                "llm_int8_threshold": 6.0,
         | 
| 33 | 
            +
                "load_in_4bit": false,
         | 
| 34 | 
            +
                "load_in_8bit": true,
         | 
| 35 | 
            +
                "quant_method": "bitsandbytes"
         | 
| 36 | 
            +
              },
         | 
| 37 | 
            +
              "rms_norm_eps": 1e-05,
         | 
| 38 | 
            +
              "rope_scaling": null,
         | 
| 39 | 
            +
              "rope_theta": 10000.0,
         | 
| 40 | 
            +
              "tie_word_embeddings": false,
         | 
| 41 | 
            +
              "torch_dtype": "float16",
         | 
| 42 | 
            +
              "transformers_version": "4.47.1",
         | 
| 43 | 
            +
              "use_cache": false,
         | 
| 44 | 
            +
              "vocab_size": 32000
         | 
| 45 | 
            +
            }
         | 
