config.json

{
    "return_dict": true,
    "output_hidden_states": false,
    "output_attentions": false,
    "torchscript": false,
    "torch_dtype": null,
    "use_bfloat16": false,
    "tf_legacy_loss": false,
    "pruned_heads": {},
    "tie_word_embeddings": true,
    "chunk_size_feed_forward": 0,
    "is_encoder_decoder": false,
    "is_decoder": false,
    "cross_attention_hidden_size": null,
    "add_cross_attention": false,
    "tie_encoder_decoder": false,
    "max_length": 20,
    "min_length": 0,
    "do_sample": false,
    "early_stopping": false,
    "num_beams": 1,
    "num_beam_groups": 1,
    "diversity_penalty": 0.0,
    "temperature": 1.0,
    "top_k": 50,
    "top_p": 1.0,
    "typical_p": 1.0,
    "repetition_penalty": 1.0,
    "length_penalty": 1.0,
    "no_repeat_ngram_size": 0,
    "encoder_no_repeat_ngram_size": 0,
    "bad_words_ids": null,
    "num_return_sequences": 1,
    "output_scores": false,
    "return_dict_in_generate": false,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "remove_invalid_values": false,
    "exponential_decay_length_penalty": null,
    "suppress_tokens": null,
    "begin_suppress_tokens": null,
    "architectures": [
        "OlmoModelForCausalLM"
    ],
    "finetuning_task": null,
    "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
    },
    "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
    },
    "tokenizer_class": null,
    "prefix": null,
    "bos_token_id": null,
    "pad_token_id": 1,
    "eos_token_id": 50279,
    "sep_token_id": null,
    "decoder_start_token_id": null,
    "task_specific_params": null,
    "problem_type": null,
    "_name_or_path": "OLMo-7B",
    "transformers_version": "4.37.2",
    "d_model": 4096,
    "n_heads": 32,
    "n_layers": 32,
    "mlp_ratio": 4,
    "mlp_hidden_size": 22016,
    "activation_type": "swiglu",
    "block_type": "sequential",
    "block_group_size": 1,
    "alibi": false,
    "alibi_bias_max": 8.0,
    "rope": true,
    "rope_full_precision": true,
    "flash_attention": true,
    "attention_dropout": 0.0,
    "multi_query_attention": false,
    "attention_layer_norm": false,
    "residual_dropout": 0.0,
    "embedding_dropout": 0.0,
    "layer_norm_type": "default",
    "layer_norm_with_affine": false,
    "attention_layer_norm_with_affine": false,
    "max_sequence_length": 2048,
    "include_bias": false,
    "bias_for_layer_norm": false,
    "scale_logits": false,
    "vocab_size": 50280,
    "embedding_size": 50304,
    "weight_tying": false,
    "init_device": "meta",
    "init_fn": "mitchell",
    "init_std": 0.02,
    "init_cutoff_factor": null,
    "precision": "amp_bf16",
    "model_type": "olmo",
    "auto_map": {
        "AutoConfig": "configuration_olmo.OLMoConfig",
        "AutoModelForCausalLM": "modeling_olmo.OLMoForCausalLM",
        "AutoTokenizer": [
            "tokenization_olmo_fast.OLMoTokenizerFast",
            "tokenization_olmo_fast.OLMoTokenizerFast"
        ]
    },
    "use_cache": true,
    "quantization": {
        "group_size": 64,
        "bits": 4
    }
}