Hy-MT2-30B-A3B-FP8 / config.json
hhoh's picture
Upload 14 files
adcab0a verified
{
"architectures": [
"HYV3ForCausalLM"
],
"attn_impl": "eager",
"bos_token_id": 120000,
"enable_attention_fp32_softmax": false,
"enable_lm_head_fp32": true,
"enable_moe_fp32_combine": false,
"eod_token_id": 120026,
"eos_token_id": 120025,
"expert_hidden_dim": 768,
"moe_intermediate_size": 768,
"first_k_dense_replace": 1,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.006,
"intermediate_size": 6912,
"max_position_embeddings": 262144,
"model_type": "hy_v3",
"moe_router_enable_expert_bias": true,
"moe_router_use_sigmoid": true,
"num_attention_heads": 32,
"num_experts": 128,
"num_experts_per_tok": 8,
"num_hidden_layers": 48,
"num_key_value_heads": 4,
"num_shared_experts": 1,
"output_router_logits": true,
"pad_token_id": 120002,
"qk_norm": true,
"rms_norm_eps": 1e-05,
"rope_theta": 11158840.0,
"route_norm": true,
"router_scaling_factor": 2.826,
"sep_token_id": 120007,
"tie_word_embeddings": false,
"transformers_version": "4.57.1",
"use_cache": true,
"use_grouped_mm": false,
"vocab_size": 120832,
"quantization_config": {
"activation_scheme": "static",
"ignored_layers": [
"lm_head",
"model.embed_tokens"
],
"quant_method": "fp8",
"kv_cache_scheme": "static"
},
"attn_quant_config": {
"kv_cache_quant": {
"dtype": "fp8_e4m3",
"k_quant": {
"scheme": "static",
"granularity": "per_tensor"
},
"v_quant": {
"scheme": "static",
"granularity": "per_tensor"
}
},
"q_quant": {
"dtype": "fp8_e4m3",
"scheme": "dynamic",
"granularity": "per_token_per_head"
}
}
}