| { |
| "architectures": [ |
| "Param2MoEForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_param2moe.Param2MoEConfig", |
| "AutoModel": "modeling_param2moe.Param2MoEModel", |
| "AutoModelForCausalLM": "modeling_param2moe.Param2MoEForCausalLM" |
| }, |
| "dtype": "float16", |
| "embedding_dropout": 0.0, |
| "eos_token_id": 3, |
| "first_k_dense_replace": 1, |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 2048, |
| "initializer_range": 0.02, |
| "intermediate_size": 9216, |
| "max_position_embeddings": 4096, |
| "max_window_layers": 20, |
| "moe_intermediate_size": 2048, |
| "moe_router_enable_expert_bias": true, |
| "moe_shared_expert_intermediate_size": 4096, |
| "mtp_loss_scaling_factor": 0, |
| "n_group": 1, |
| "norm_topk_prob": true, |
| "num_attention_heads": 32, |
| "num_experts": 64, |
| "num_experts_per_tok": 6, |
| "num_hidden_layers": 21, |
| "num_key_value_heads": 8, |
| "num_nextn_predict_layers": 0, |
| "num_shared_experts": 2, |
| "output_dropout": 0.0, |
| "output_router_logits": false, |
| "pad_token_id": 0, |
| "partial_rotary_factor": 1.0, |
| "quantization_config": { |
| "_load_in_4bit": false, |
| "_load_in_8bit": true, |
| "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": false, |
| "load_in_8bit": true, |
| "quant_method": "bitsandbytes" |
| }, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 1000000.0, |
| "routed_scaling_factor": 2.5, |
| "router_dtype": "fp32", |
| "score_function": "sigmoid", |
| "tie_word_embeddings": true, |
| "topk_group": 1, |
| "transformers_version": "4.56.0", |
| "use_bias": false, |
| "use_cache": true, |
| "use_qk_norm": true, |
| "use_qkv_bias": false, |
| "use_rmsnorm": true, |
| "vocab_size": 128008 |
| } |
|
|