| { | |
| "_attn_implementation_internal": "flash_attention_2", | |
| "_commit_hash": null, | |
| "_name_or_path": "jetmoe/jetmoe-8b-sft", | |
| "activation_function": "silu", | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "JetMoEForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_jetmoe.JetMoEConfig", | |
| "AutoModelForCausalLM": "modeling_jetmoe.JetMoEForCausalLM" | |
| }, | |
| "aux_loss_coef": 0.01, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bias": true, | |
| "bos_token_id": 1, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": 2, | |
| "exponential_decay_length_penalty": null, | |
| "ffn_hidden_size": 5632, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "glu": true, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.01, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "kv_channels": 128, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layer_norm_epsilon": 1e-05, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "model_type": "jetmoe", | |
| "moe_num_experts": 8, | |
| "moe_top_k": 2, | |
| "n_embd": 2048, | |
| "n_head": 16, | |
| "n_layer": 24, | |
| "n_positions": 4096, | |
| "no_repeat_ngram_size": 0, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_key_value_heads": 16, | |
| "num_layers": 24, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000.0, | |
| "rotary_percent": 1.0, | |
| "sep_token_id": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torchscript": false, | |
| "transformers_version": null, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |