Upload Qwen2ForCausalLM

config.json

@@ -1,7 +1,7 @@
 {
   "_name_or_path": "/bask/homes/u/usjs9456/ai_workloads_project/S1_workspace/experiments/trainning/qwen2.5_3B_instruct_4H100_S1_gas1/ckpts/s1.1_20250328_144206",
   "architectures": [
-    "Qwen2ForSequenceClassification"
+    "Qwen2ForCausalLM"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 151643,

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "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,
+  "transformers_version": "4.46.1"
+}

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07f84908394952ae00b1817d91e03522a063e3b61fc8b6b198fff73361b49800
-size 2428739632
+oid sha256:172b8b9d83866cf322d41091d4050a25d53236aa1478dcdb08040fb0d4681d06
+size 2428723160

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 12343771136
+    "total_size": 12343754752
   },
   "weight_map": {
     "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
@@ -436,7 +436,6 @@
     "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
     "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.norm.weight": "model-00003-of-00003.safetensors",
-    "score.weight": "model-00003-of-00003.safetensors"
+    "model.norm.weight": "model-00003-of-00003.safetensors"
   }
 }