Upload config.json

config.json

@@ -0,0 +1,50 @@
+{
+  "architectures": [
+    "QuietQwenForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_quietqwen.QuietQwenConfig",
+    "AutoModel": "modeling_quietqwen.QuietQwenModel",
+    "AutoModelForCausalLM": "modeling_quietqwen.QuietQwenForCausalLM"
+  },
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 8192,
+  "max_window_layers": 21,
+  "model_type": "quietqwen",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936,
+  "decoder_sparse_step": 1,
+  "moe_intermediate_size": 1408,
+  "shared_expert_intermediate_size": 5632,
+  "num_experts_per_tok": 4,
+  "num_experts": 60,
+  "norm_topk_prob": false,
+  "output_router_logits": false,
+  "router_aux_loss_coef": 0.001,
+  "max_thoughts": 10,
+  "merged_talk_heads": true,
+  "merged_lm_and_talk_heads": false,
+  "merged_lm_and_think_heads": true,
+  "use_concat_talk_head": true,
+  "use_shallow_think": true,
+  "use_shallow_talk": false,
+  "use_complex_think_head": false,
+  "use_complex_talk_head": true,
+  "use_weighted_talk_head": true
+}