HRM-MoE / config.json
Xiaoye08's picture
Enable HRM-MoE trust remote code
5ea3f7a verified
Raw
History Blame Contribute Delete
1.13 kB
{
"model_type": "hrm_text_moe",
"architectures": [
"HrmTextMoEForCausalLM"
],
"auto_map": {
"AutoConfig": "configuration_hrm_text_moe.HrmTextMoEConfig",
"AutoModelForCausalLM": "modeling_hrm_text_moe.HrmTextMoEForCausalLM"
},
"vocab_size": 65536,
"hidden_size": 1536,
"intermediate_size": 512,
"num_hidden_layers": 16,
"num_attention_heads": 12,
"num_key_value_heads": 12,
"head_dim": 128,
"H_cycles": 2,
"L_cycles": 3,
"L_bp_cycles": [
0,
3
],
"max_position_embeddings": 4096,
"rms_norm_eps": 1e-06,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"initializer_range": 0.025515518153991442,
"embedding_scale": 39.191835884530846,
"prefix_lm": true,
"moe_num_experts": 64,
"moe_top_k": 8,
"moe_intermediate_size": 512,
"moe_implementation": "grouped_triton",
"moe_norm_topk_prob": true,
"moe_router_aux_loss_coef": 0.001,
"pad_token_id": 5,
"condition_mapping": {
"cot": "<|object_ref_end|>",
"direct": "<|object_ref_start|>",
"noisy": "<|quad_start|>",
"synth": "<|quad_end|>"
},
"bos_token_id": 6,
"eos_token_id": 11
}