slimed-qwen-3 / config.json
JacobAndersson's picture
Upload Qwen2MoeForCausalLM
ec77462 verified
raw
history blame contribute delete
No virus
963 Bytes
{
"_name_or_path": "Qwen/Qwen1.5-MoE-A2.7B-Chat",
"architectures": [
"Qwen2MoeForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"decoder_sparse_step": 1,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 5632,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2_moe",
"moe_intermediate_size": 1408,
"norm_topk_prob": false,
"num_attention_heads": 16,
"num_experts": 60,
"num_experts_per_tok": 4,
"num_hidden_layers": 3,
"num_key_value_heads": 16,
"output_router_logits": false,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"router_aux_loss_coef": 0.001,
"shared_expert_intermediate_size": 5632,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.40.1",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}