config.json

{
    "_name_or_path": "/covalent/.cache/models/tmpllocszfs2mvqsj5j",
    "architectures": [
        "LlamaForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 128000,
    "eos_token_id": [
        128001,
        128008,
        128009
    ],
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 3072,
    "initializer_range": 0.02,
    "intermediate_size": 8192,
    "max_position_embeddings": 131072,
    "mlp_bias": false,
    "model_type": "llama",
    "num_attention_heads": 24,
    "num_hidden_layers": 28,
    "num_key_value_heads": 8,
    "pretraining_tp": 1,
    "quantization_config": {
        "_load_in_4bit": false,
        "_load_in_8bit": true,
        "bnb_4bit_compute_dtype": "bfloat16",
        "bnb_4bit_quant_storage": "uint8",
        "bnb_4bit_quant_type": "fp4",
        "bnb_4bit_use_double_quant": false,
        "llm_int8_enable_fp32_cpu_offload": false,
        "llm_int8_has_fp16_weight": false,
        "llm_int8_skip_modules": [
            "lm_head"
        ],
        "llm_int8_threshold": 6.0,
        "load_in_4bit": false,
        "load_in_8bit": true,
        "quant_method": "bitsandbytes"
    },
    "rms_norm_eps": 1e-05,
    "rope_scaling": {
        "factor": 32.0,
        "high_freq_factor": 4.0,
        "low_freq_factor": 1.0,
        "original_max_position_embeddings": 8192,
        "rope_type": "llama3"
    },
    "rope_theta": 500000.0,
    "tie_word_embeddings": true,
    "torch_dtype": "float16",
    "transformers_version": "4.46.2",
    "use_cache": true,
    "vocab_size": 128256,
    "api_key": null
}