| { | |
| "vocab_size": 128256, | |
| "max_position_embeddings": 8192, | |
| "hidden_size": 4096, | |
| "intermediate_size": 14336, | |
| "num_hidden_layers": 32, | |
| "num_attention_heads": 32, | |
| "num_key_value_heads": 8, | |
| "hidden_act": "silu", | |
| "initializer_range": 0.02, | |
| "rms_norm_eps": 1e-05, | |
| "pretraining_tp": 1, | |
| "use_cache": true, | |
| "rope_theta": 500000.0, | |
| "rope_scaling": null, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "return_dict": true, | |
| "output_hidden_states": false, | |
| "output_attentions": false, | |
| "torchscript": false, | |
| "torch_dtype": "bfloat16", | |
| "use_bfloat16": false, | |
| "tf_legacy_loss": false, | |
| "pruned_heads": {}, | |
| "tie_word_embeddings": false, | |
| "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": [ | |
| "DeepseekForCausalLM" | |
| ], | |
| "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": 128000, | |
| "pad_token_id": null, | |
| "eos_token_id": 128001, | |
| "sep_token_id": null, | |
| "decoder_start_token_id": null, | |
| "task_specific_params": null, | |
| "problem_type": null, | |
| "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct", | |
| "transformers_version": "4.40.1", | |
| "model_type": "deepseek", | |
| "n_routed_experts": 4, | |
| "n_shared_experts": 1, | |
| "num_experts_per_tok": 4, | |
| "first_k_dense_replace": 0, | |
| "moe_layer_freq": 1, | |
| "scoring_func": "softmax", | |
| "norm_topk_prob": true, | |
| "moe_intermediate_size": 14336, | |
| "auto_map": { | |
| "AutoConfig": "deepseek-ai/deepseek-moe-16b-base--configuration_deepseek.DeepseekConfig", | |
| "AutoModel": "deepseek-ai/deepseek-moe-16b-base--modeling_deepseek.DeepseekModel", | |
| "AutoModelForCausalLM": "deepseek-ai/deepseek-moe-16b-base--modeling_deepseek.DeepseekForCausalLM" | |
| } | |
| } |