{
    "_name_or_path": "/workspace/process/openllm-france_claire-7b-0.1/source",
    "alibi": false,
    "apply_residual_connection_post_layernorm": false,
    "architectures": [
        "FalconForCausalLM"
    ],
    "attention_dropout": 0.0,
    "auto_map": {
        "AutoConfig": "configuration_falcon.FalconConfig",
        "AutoModel": "modeling_falcon.FalconModel",
        "AutoModelForCausalLM": "modeling_falcon.FalconForCausalLM",
        "AutoModelForQuestionAnswering": "modeling_falcon.FalconForQuestionAnswering",
        "AutoModelForSequenceClassification": "modeling_falcon.FalconForSequenceClassification",
        "AutoModelForTokenClassification": "modeling_falcon.FalconForTokenClassification"
    },
    "bias": false,
    "bos_token_id": 11,
    "eos_token_id": 11,
    "hidden_dropout": 0.0,
    "hidden_size": 4544,
    "initializer_range": 0.02,
    "layer_norm_epsilon": 1e-05,
    "max_position_embeddings": 2048,
    "model_type": "falcon",
    "multi_query": true,
    "new_decoder_architecture": false,
    "num_attention_heads": 71,
    "num_hidden_layers": 32,
    "num_kv_heads": 71,
    "pad_token_id": 0,
    "parallel_attn": true,
    "pretraining_tp": 1,
    "quantization_config": {
        "batch_size": 1,
        "bits": 4,
        "block_name_to_quantize": "transformer.h",
        "cache_block_outputs": true,
        "damp_percent": 0.1,
        "desc_act": true,
        "exllama_config": {
            "version": 1
        },
        "group_size": 128,
        "max_input_length": null,
        "model_seqlen": 2048,
        "module_name_preceding_first_block": [
            "transformer.word_embeddings"
        ],
        "pad_token_id": null,
        "quant_method": "gptq",
        "sym": true,
        "tokenizer": null,
        "true_sequential": true,
        "use_cuda_fp16": false,
        "use_exllama": false
    },
    "rope_scaling": null,
    "rope_theta": 10000.0,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.35.0",
    "use_cache": true,
    "vocab_size": 65024
}