Hy3-1M / config.json
cloudyu's picture
Upload config.json with huggingface_hub
2e31c6a verified
Raw
History Blame Contribute Delete
2.14 kB
{
"architectures": [
"HYV3ForCausalLM"
],
"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": 1536,
"moe_intermediate_size": 1536,
"first_k_dense_replace": 1,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.006,
"intermediate_size": 13312,
"max_position_embeddings": 262144,
"model_type": "hy_v3",
"moe_router_enable_expert_bias": true,
"moe_router_use_sigmoid": true,
"num_attention_heads": 64,
"num_experts": 192,
"num_experts_per_tok": 8,
"num_hidden_layers": 80,
"num_key_value_heads": 8,
"num_shared_experts": 1,
"output_router_logits": true,
"pad_token_id": 120002,
"qk_norm": true,
"rms_norm_eps": 1e-05,
"rope_parameters": {
"rope_theta": 11158840.0,
"rope_type": "yarn",
"factor": 4.0,
"original_max_position_embeddings": 262144
},
"route_norm": true,
"router_scaling_factor": 2.826,
"sep_token_id": 120007,
"tie_word_embeddings": false,
"transformers_version": "5.6.0",
"use_cache": true,
"use_grouped_mm": false,
"vocab_size": 120832,
"num_nextn_predict_layers": 1,
"quantization_config": {
"config_groups": {
"group_0": {
"targets": [
"Linear"
],
"weights": {
"num_bits": 4,
"type": "int",
"symmetric": true,
"group_size": 128,
"strategy": "group",
"block_structure": null,
"dynamic": false,
"actorder": null,
"scale_dtype": null,
"zp_dtype": null,
"observer": "memoryless_minmax",
"observer_kwargs": {}
},
"input_activations": null,
"output_activations": null
}
},
"quant_method": "compressed-tensors",
"kv_cache_scheme": null,
"format": "pack-quantized",
"quantization_status": "compressed",
"global_compression_ratio": null,
"ignore": [
"lm_head",
"re:.*mlp.router.gate$",
"re:.*eh_proj$"
]
}
}