Upload Qwen2ForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Qwen/Qwen2.5-3B-Instruct",
+  "_name_or_path": "Qwen/Qwen2.5-3B",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -11,7 +11,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 11008,
   "max_position_embeddings": 32768,
-  "max_window_layers": 70,
+  "max_window_layers": 36,
   "model_type": "qwen2",
   "num_attention_heads": 16,
   "num_hidden_layers": 36,
@@ -25,6 +25,7 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.47.0",
   "use_cache": true,
+  "use_mrope": false,
   "use_sliding_window": false,
   "vocab_size": 81920
 }

generation_config.json

@@ -1,14 +1,6 @@
 {
   "bos_token_id": 151643,
-  "do_sample": true,
-  "eos_token_id": [
-    151645,
-    151643
-  ],
-  "pad_token_id": 151643,
-  "repetition_penalty": 1.05,
-  "temperature": 0.7,
-  "top_k": 20,
-  "top_p": 0.8,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
   "transformers_version": "4.47.0"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75bcdac16b3e4ada74457ca4c1bdf3733835bb66dfba2e69a21b28f60ebfcc48
+oid sha256:465e486fa5b713642337fd96b3a1375a61ee4b31aae3fd9dbe45d631aea8f421
 size 4979085448

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c44112a82939a3b4e26f919cc4bed507fffcccb292077b6259a51907574ac7ff
+oid sha256:8bd10f9c3ae0b88422f5c3bf6ddaddf116894ae4892945498ccdd586cd5b5461
 size 906055968