Upload Qwen2ForCausalLM

config.json

@@ -1,7 +1,7 @@
 {
   "_name_or_path": "/home/t0admin/s1/s1/ckpts/s1_N1-20250403_160832",
   "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-00029-of-00029.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f1644e1ff0386e60e3ef726d37bb8b32ef374ebe615d64f54e4d87f9ba78428
-size 566333984
+oid sha256:6144a6f48c4f92a6e2f01304f05b1d4d101d98281b50bc879e1368ee7dc4185b
+size 3680563768

model.safetensors.index.json

@@ -1,8 +1,9 @@
 {
   "metadata": {
-    "total_size": 127941275648
+    "total_size": 131055505408
   },
   "weight_map": {
+    "lm_head.weight": "model-00029-of-00029.safetensors",
     "model.embed_tokens.weight": "model-00001-of-00029.safetensors",
     "model.layers.0.input_layernorm.weight": "model-00002-of-00029.safetensors",
     "model.layers.0.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
@@ -772,7 +773,6 @@
     "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
     "model.layers.9.self_attn.v_proj.bias": "model-00005-of-00029.safetensors",
     "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
-    "model.norm.weight": "model-00029-of-00029.safetensors",
-    "score.weight": "model-00029-of-00029.safetensors"
+    "model.norm.weight": "model-00029-of-00029.safetensors"
   }
 }