Xenova's picture
Xenova HF Staff
Update config.json
e6ca73e verified
{
"architectures": [
"DeepseekV3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"aux_loss_alpha": 0.001,
"bos_token_id": 0,
"dtype": "float32",
"eos_token_id": 1,
"ep_size": 1,
"first_k_dense_replace": 3,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 8,
"initializer_range": 0.02,
"intermediate_size": 128,
"kv_lora_rank": 512,
"max_position_embeddings": 163840,
"model_type": "deepseek_v3",
"moe_intermediate_size": 2048,
"moe_layer_freq": 1,
"n_group": 2,
"n_routed_experts": 4,
"n_shared_experts": 1,
"norm_topk_prob": true,
"num_attention_heads": 2,
"num_experts_per_tok": 2,
"num_hidden_layers": 2,
"num_key_value_heads": 2,
"num_nextn_predict_layers": 1,
"pad_token_id": null,
"pretraining_tp": 1,
"q_lora_rank": 1536,
"qk_head_dim": 192,
"qk_nope_head_dim": 128,
"qk_rope_head_dim": 64,
"rms_norm_eps": 1e-06,
"rope_interleave": true,
"rope_parameters": {
"beta_fast": 32.0,
"beta_slow": 1.0,
"factor": 40.0,
"mscale": 1.0,
"mscale_all_dim": 1.0,
"original_max_position_embeddings": 4096,
"rope_theta": 10000,
"rope_type": "yarn",
"type": "yarn"
},
"routed_scaling_factor": 2.5,
"scoring_func": "sigmoid",
"seq_aux": true,
"tie_word_embeddings": false,
"topk_group": 4,
"topk_method": "noaux_tc",
"transformers_version": "5.3.0.dev0",
"use_cache": true,
"v_head_dim": 128,
"vocab_size": 129280,
"transformers.js_config": {
"use_external_data_format": {
"model.onnx": 1,
"model_fp16.onnx": 1
},
"kv_cache_dtype": {
"q4f16": "float16",
"fp16": "float16"
}
}
}