Upload Qwen2ForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/home/notebook/data/group/ComplexTaskDecision/Hammer/ckpt/select_caller/hammer2.0/xlam_mask3_0.33_hammer_repari_qwen3b_depthjsonv1_0.05_batch64/merge_step2120",
+  "_name_or_path": "/home/notebook/data/group/ComplexTaskDecision/Hammer/ckpt/select_caller/hammer2.0/xlam_mask3_0.33_hammer_repari_qwen0.5b_depthjsonv1_0.05_batch64/merge_step2120",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -7,14 +7,14 @@
   "bos_token_id": 151643,
   "eos_token_id": 151645,
   "hidden_act": "silu",
-  "hidden_size": 2048,
+  "hidden_size": 896,
   "initializer_range": 0.02,
-  "intermediate_size": 11008,
+  "intermediate_size": 4864,
   "max_position_embeddings": 32768,
-  "max_window_layers": 70,
+  "max_window_layers": 21,
   "model_type": "qwen2",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 36,
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
   "num_key_value_heads": 2,
   "rms_norm_eps": 1e-06,
   "rope_theta": 1000000.0,

generation_config.json

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

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fb93435d1d8db2a3aee0a7ab109736c71c92c7462d8adb5e9d430d667986e50
+size 987612192