| { | |
| "_name_or_path": "PowerMoE-3b", | |
| "activation_function": "silu", | |
| "architectures": [ | |
| "GraniteMoeForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attention_multiplier": 0.015625, | |
| "bos_token_id": 0, | |
| "embedding_multiplier": 12.0, | |
| "eos_token_id": 0, | |
| "hidden_act": "silu", | |
| "hidden_size": 1536, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 512, | |
| "logits_scaling": 6.0, | |
| "max_position_embeddings": 4096, | |
| "model_type": "granitemoe", | |
| "num_attention_heads": 24, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "num_local_experts": 40, | |
| "output_router_logits": false, | |
| "pad_token_id": 0, | |
| "quantization_config": { | |
| "_load_in_4bit": true, | |
| "_load_in_8bit": false, | |
| "bnb_4bit_compute_dtype": "float32", | |
| "bnb_4bit_quant_storage": "uint8", | |
| "bnb_4bit_quant_type": "fp4", | |
| "bnb_4bit_use_double_quant": false, | |
| "llm_int8_enable_fp32_cpu_offload": false, | |
| "llm_int8_has_fp16_weight": false, | |
| "llm_int8_skip_modules": null, | |
| "llm_int8_threshold": 6.0, | |
| "load_in_4bit": true, | |
| "load_in_8bit": false, | |
| "quant_method": "bitsandbytes" | |
| }, | |
| "residual_multiplier": 0.22, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000, | |
| "router_aux_loss_coef": 0.001, | |
| "router_jitter_noise": 0.0, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.46.2", | |
| "use_cache": true, | |
| "vocab_size": 49152 | |
| } | |