| { | |
| "_name_or_path": "/ML-A100/public/run/research/tianyuzheng/models/Scale_UP_Web/scaleup_STEM_merged_10M_MOE", | |
| "architectures": [ | |
| "MixtralForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 32768, | |
| "model_type": "mixtral", | |
| "num_attention_heads": 32, | |
| "num_experts_per_tok": 2, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "num_local_experts": 8, | |
| "output_router_logits": true, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 1000000.0, | |
| "router_aux_loss_coef": 0.02, | |
| "router_jitter_noise": 0.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.40.0", | |
| "use_cache": false, | |
| "vocab_size": 32000, | |
| "quantization_config": { | |
| "quant_method": "exl2", | |
| "version": "0.0.21", | |
| "bits": 3.0, | |
| "head_bits": 6, | |
| "calibration": { | |
| "rows": 100, | |
| "length": 2048, | |
| "dataset": "(default)" | |
| } | |
| } | |
| } |