Team Ai
Modelpublic

kernelpool/GLM-5.2-6bit

sourceHugging Facemitupdated 4mo agoView on Hugging Face
0likes79downloads
config.json233 linesDownload Raw Back to root
1{2    "architectures": [3        "GlmMoeDsaForCausalLM"4    ],5    "attention_bias": false,6    "attention_dropout": 0.0,7    "dtype": "bfloat16",8    "eos_token_id": [9        154820,10        154827,11        15482912    ],13    "ep_size": 1,14    "first_k_dense_replace": 3,15    "head_dim": 192,16    "hidden_act": "silu",17    "hidden_size": 6144,18    "index_head_dim": 128,19    "index_n_heads": 32,20    "index_share_for_mtp_iteration": true,21    "index_skip_topk_offset": 3,22    "index_topk": 2048,23    "index_topk_freq": 4,24    "index_topk_pattern": null,25    "indexer_rope_interleave": true,26    "indexer_types": [27        "full",28        "full",29        "full",30        "shared",31        "shared",32        "shared",33        "full",34        "shared",35        "shared",36        "shared",37        "full",38        "shared",39        "shared",40        "shared",41        "full",42        "shared",43        "shared",44        "shared",45        "full",46        "shared",47        "shared",48        "shared",49        "full",50        "shared",51        "shared",52        "shared",53        "full",54        "shared",55        "shared",56        "shared",57        "full",58        "shared",59        "shared",60        "shared",61        "full",62        "shared",63        "shared",64        "shared",65        "full",66        "shared",67        "shared",68        "shared",69        "full",70        "shared",71        "shared",72        "shared",73        "full",74        "shared",75        "shared",76        "shared",77        "full",78        "shared",79        "shared",80        "shared",81        "full",82        "shared",83        "shared",84        "shared",85        "full",86        "shared",87        "shared",88        "shared",89        "full",90        "shared",91        "shared",92        "shared",93        "full",94        "shared",95        "shared",96        "shared",97        "full",98        "shared",99        "shared",100        "shared",101        "full",102        "shared",103        "shared",104        "shared"105    ],106    "initializer_range": 0.02,107    "intermediate_size": 12288,108    "kv_lora_rank": 512,109    "max_position_embeddings": 1048576,110    "mlp_layer_types": [111        "dense",112        "dense",113        "dense",114        "sparse",115        "sparse",116        "sparse",117        "sparse",118        "sparse",119        "sparse",120        "sparse",121        "sparse",122        "sparse",123        "sparse",124        "sparse",125        "sparse",126        "sparse",127        "sparse",128        "sparse",129        "sparse",130        "sparse",131        "sparse",132        "sparse",133        "sparse",134        "sparse",135        "sparse",136        "sparse",137        "sparse",138        "sparse",139        "sparse",140        "sparse",141        "sparse",142        "sparse",143        "sparse",144        "sparse",145        "sparse",146        "sparse",147        "sparse",148        "sparse",149        "sparse",150        "sparse",151        "sparse",152        "sparse",153        "sparse",154        "sparse",155        "sparse",156        "sparse",157        "sparse",158        "sparse",159        "sparse",160        "sparse",161        "sparse",162        "sparse",163        "sparse",164        "sparse",165        "sparse",166        "sparse",167        "sparse",168        "sparse",169        "sparse",170        "sparse",171        "sparse",172        "sparse",173        "sparse",174        "sparse",175        "sparse",176        "sparse",177        "sparse",178        "sparse",179        "sparse",180        "sparse",181        "sparse",182        "sparse",183        "sparse",184        "sparse",185        "sparse",186        "sparse",187        "sparse",188        "sparse"189    ],190    "model_type": "glm_moe_dsa",191    "moe_intermediate_size": 2048,192    "moe_layer_freq": 1,193    "n_group": 1,194    "n_routed_experts": 256,195    "n_shared_experts": 1,196    "norm_topk_prob": true,197    "num_attention_heads": 64,198    "num_experts_per_tok": 8,199    "num_hidden_layers": 78,200    "num_key_value_heads": 64,201    "num_nextn_predict_layers": 1,202    "pad_token_id": 154820,203    "pretraining_tp": 1,204    "q_lora_rank": 2048,205    "qk_head_dim": 256,206    "qk_nope_head_dim": 192,207    "qk_rope_head_dim": 64,208    "quantization": {209        "group_size": 64,210        "bits": 6,211        "mode": "affine"212    },213    "quantization_config": {214        "group_size": 64,215        "bits": 6,216        "mode": "affine"217    },218    "rms_norm_eps": 1e-05,219    "rope_interleave": true,220    "rope_parameters": {221        "rope_theta": 8000000,222        "rope_type": "default"223    },224    "routed_scaling_factor": 2.5,225    "scoring_func": "sigmoid",226    "tie_word_embeddings": false,227    "topk_group": 1,228    "topk_method": "noaux_tc",229    "transformers_version": "5.12.0",230    "use_cache": true,231    "v_head_dim": 256,232    "vocab_size": 154880233}