|
{ |
|
"_name_or_path": "/ceph/hdd/staff/charpent/.cache/modelsffntffke05jcv1jo", |
|
"add_weight_norm": false, |
|
"architectures": [ |
|
"LlamaMoEForCausalLM" |
|
], |
|
"attention_dropout": 0.0, |
|
"auto_map": { |
|
"AutoConfig": "configuration_llama_moe.LlamaMoEConfig", |
|
"AutoModel": "llama-moe/LLaMA-MoE-v1-3_0B-2_16--modeling_llama_moe_hf.LlamaMoEModel", |
|
"AutoModelForCausalLM": "modeling_llama_moe_hf.LlamaMoEForCausalLM" |
|
}, |
|
"bos_token_id": 1, |
|
"calculator_type": "UniversalCalculator", |
|
"capacity_factor": 1.25, |
|
"drop_tokens": true, |
|
"dropped_padding": "zero", |
|
"eos_token_id": 2, |
|
"gate_add_noise": true, |
|
"gate_balance_loss_weight": 0.01, |
|
"gate_network": "mlp", |
|
"gate_noise_epsilon": 0.01, |
|
"gate_type": "TopKBalancedNoisyGate", |
|
"gate_use_balance": true, |
|
"gate_use_softmax": true, |
|
"gates": "mlp", |
|
"hidden_act": "silu", |
|
"hidden_size": 4096, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 11008, |
|
"max_position_embeddings": 4096, |
|
"model_type": "llama_moe", |
|
"multiply_gate_scores": true, |
|
"num_attention_heads": 32, |
|
"num_experts": 16, |
|
"num_hidden_layers": 32, |
|
"num_key_value_heads": 32, |
|
"num_selects": 2, |
|
"pad_token_id": 0, |
|
"pretraining_tp": 1, |
|
"quantization_config": { |
|
"_load_in_4bit": true, |
|
"_load_in_8bit": false, |
|
"bnb_4bit_compute_dtype": "bfloat16", |
|
"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": [ |
|
"lm_head" |
|
], |
|
"llm_int8_threshold": 6.0, |
|
"load_in_4bit": true, |
|
"load_in_8bit": false, |
|
"quant_method": "bitsandbytes" |
|
}, |
|
"rms_norm_eps": 1e-05, |
|
"rope_scaling": null, |
|
"score_scale_factor": 8.0, |
|
"size_experts": [ |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
], |
|
[ |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688, |
|
688 |
|
] |
|
], |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "float16", |
|
"transformers_version": "4.41.2", |
|
"use_cache": true, |
|
"vocab_size": 32000 |
|
} |
|
|