diffbot/Diffbot-Coder-2602
012
1{2 "architectures": [3 "Glm4MoeLiteForCausalLM"4 ],5 "attention_bias": false,6 "attention_dropout": 0.0,7 "bos_token_id": 0,8 "dtype": "bfloat16",9 "eos_token_id": [10 154820,11 154827,12 15482913 ],14 "first_k_dense_replace": 1,15 "head_dim": 64,16 "hidden_act": "silu",17 "hidden_size": 2048,18 "initializer_range": 0.02,19 "intermediate_size": 10240,20 "kv_lora_rank": 512,21 "max_position_embeddings": 202752,22 "mlp_layer_types": [23 "dense",24 "sparse",25 "sparse",26 "sparse",27 "sparse",28 "sparse",29 "sparse",30 "sparse",31 "sparse",32 "sparse",33 "sparse",34 "sparse",35 "sparse",36 "sparse",37 "sparse",38 "sparse",39 "sparse",40 "sparse",41 "sparse",42 "sparse",43 "sparse",44 "sparse",45 "sparse",46 "sparse",47 "sparse",48 "sparse",49 "sparse",50 "sparse",51 "sparse",52 "sparse",53 "sparse",54 "sparse",55 "sparse",56 "sparse",57 "sparse",58 "sparse",59 "sparse",60 "sparse",61 "sparse",62 "sparse",63 "sparse",64 "sparse",65 "sparse",66 "sparse",67 "sparse",68 "sparse",69 "sparse"70 ],71 "model_type": "glm4_moe_lite",72 "moe_intermediate_size": 1536,73 "n_group": 1,74 "n_routed_experts": 64,75 "n_shared_experts": 1,76 "norm_topk_prob": true,77 "num_attention_heads": 20,78 "num_experts_per_tok": 4,79 "num_hidden_layers": 47,80 "num_key_value_heads": 20,81 "num_nextn_predict_layers": 1,82 "pad_token_id": 154820,83 "partial_rotary_factor": 1.0,84 "pretraining_tp": 1,85 "q_lora_rank": 768,86 "qk_head_dim": 256,87 "qk_nope_head_dim": 192,88 "qk_rope_head_dim": 64,89 "rms_norm_eps": 1e-05,90 "rope_interleave": true,91 "rope_parameters": {92 "partial_rotary_factor": 1.0,93 "rope_theta": 1000000,94 "rope_type": "default"95 },96 "routed_scaling_factor": 1.8,97 "tie_word_embeddings": false,98 "topk_group": 1,99 "topk_method": "noaux_tc",100 "transformers_version": "5.0.0rc3",101 "use_cache": true,102 "v_head_dim": 256,103 "vocab_size": 154880104}105 