Team Ai
Modelpublic

thelamapi/next-codex

sourceHugging Facemitupdated 7mo agoView on Hugging Face
1likes22downloads
config.json56 linesDownload Raw Back to root
1{2  "architectures": [3    "Qwen3MoeForCausalLM"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "decoder_sparse_step": 1,8  "dtype": "bfloat16",9  "eos_token_id": 151645,10  "head_dim": 128,11  "hidden_act": "silu",12  "hidden_size": 2048,13  "initializer_range": 0.02,14  "intermediate_size": 5472,15  "max_position_embeddings": 262144,16  "max_window_layers": 28,17  "mlp_only_layers": [],18  "model_type": "qwen3_moe",19  "moe_intermediate_size": 768,20  "norm_topk_prob": true,21  "num_attention_heads": 32,22  "num_experts": 128,23  "num_experts_per_tok": 8,24  "num_hidden_layers": 48,25  "num_key_value_heads": 4,26  "output_router_logits": false,27  "pad_token_id": 151654,28  "qkv_bias": false,29  "quantization_config": {30    "bnb_4bit_compute_dtype": "bfloat16",31    "bnb_4bit_quant_type": "nf4",32    "bnb_4bit_use_double_quant": true,33    "llm_int8_enable_fp32_cpu_offload": false,34    "llm_int8_has_fp16_weight": false,35    "llm_int8_skip_modules": null,36    "llm_int8_threshold": 6.0,37    "load_in_4bit": true,38    "load_in_8bit": false,39    "quant_method": "bitsandbytes"40  },41  "rms_norm_eps": 1e-06,42  "rope_scaling": null,43  "rope_theta": 10000000,44  "router_aux_loss_coef": 0.0,45  "shared_expert_intermediate_size": 0,46  "sliding_window": null,47  "tie_word_embeddings": false,48  "transformers_version": "4.57.2",49  "unsloth_fixed": true,50  "unsloth_version": "2025.11.4",51  "use_cache": true,52  "use_qk_norm": true,53  "use_sliding_window": false,54  "vocab_size": 15193655}56