Upload Qwen2ForCausalLM

config.json

@@ -7,9 +7,9 @@
   "dtype": "float16",
   "eos_token_id": 151645,
   "hidden_act": "silu",
-  "hidden_size": 1536,
+  "hidden_size": 2048,
   "initializer_range": 0.02,
-  "intermediate_size": 8960,
+  "intermediate_size": 11008,
   "layer_types": [
     "full_attention",
     "full_attention",
@@ -38,13 +38,21 @@
     "full_attention",
     "full_attention",
     "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
     "full_attention"
   ],
   "max_position_embeddings": 32768,
-  "max_window_layers": 21,
+  "max_window_layers": 70,
   "model_type": "qwen2",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 28,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
   "num_key_value_heads": 2,
   "pad_token_id": null,
   "rms_norm_eps": 1e-06,

generation_config.json

@@ -6,7 +6,7 @@
     151643
   ],
   "pad_token_id": 151643,
-  "repetition_penalty": 1.1,
+  "repetition_penalty": 1.05,
   "temperature": 0.7,
   "top_k": 20,
   "top_p": 0.8,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88adc6d14c9bf5444828651c97182523ff6bb9c44dffd2a3b37fc4a5ba533c5b
-size 3087466808
+oid sha256:bd008fc3e1fc59da2078506ead79554be02422b09509aec3e16e51299def3940
+size 6171926680