Upload Qwen2ForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/Users/guyuxian/miniplm/200M/0",
+  "_name_or_path": "/Users/guyuxian/miniplm/1.2B/0",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -7,21 +7,21 @@
   "bos_token_id": 151643,
   "eos_token_id": 151643,
   "hidden_act": "silu",
-  "hidden_size": 768,
+  "hidden_size": 1536,
   "initializer_range": 0.02,
-  "intermediate_size": 2112,
+  "intermediate_size": 4224,
   "is_model_parallel": false,
   "max_position_embeddings": 32768,
-  "max_window_layers": 10,
+  "max_window_layers": 21,
   "model_type": "qwen2",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "num_key_value_heads": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 1000000.0,
   "sliding_window": null,
-  "tie_word_embeddings": true,
+  "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.45.2",
   "use_cache": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c942f3f200e29be6f28bb4dae54a936a95424e458e190f3d2102c3bfaa7093ea
-size 813767352
+oid sha256:4fd4402b98bf9e38e7205fbb813373cf775135dc7b95eb0db905f89b5315b800
+size 4642298144