xinyuema/llm-course-hw2-reward-model

README.md

@@ -35,7 +35,7 @@ This model was trained with Reward.
 ### Framework versions
 
 - TRL: 0.16.0
-- Transformers: 4.49.0
+- Transformers: 4.50.0
 - Pytorch: 2.6.0+cu124
 - Datasets: 3.4.1
 - Tokenizers: 0.21.1

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "HuggingFaceTB/SmolLM-135M-Instruct",
   "architectures": [
     "LlamaForSequenceClassification"
   ],
@@ -10,8 +9,14 @@
   "head_dim": 64,
   "hidden_act": "silu",
   "hidden_size": 576,
+  "id2label": {
+    "0": "LABEL_0"
+  },
   "initializer_range": 0.02,
   "intermediate_size": 1536,
+  "label2id": {
+    "LABEL_0": 0
+  },
   "max_position_embeddings": 2048,
   "mlp_bias": false,
   "model_type": "llama",
@@ -24,8 +29,8 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.49.0",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0",
   "use_cache": true,
   "vocab_size": 49152
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:794437c41a53c3d5680d5ae5b243e1b38f65d4bfcd2fcbb869ba5ba8540dc381
-size 538095096
+oid sha256:d11a70e6a705220894e1bc00859228b6aef19afe95cca3c3215028dc3c16aab2
+size 269061784

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8a3eadebc85ddacb0d776e22ac4673ebf425aedc8f8f2342dc98903c2d41b5c
-size 5368
+oid sha256:ade67e578833f20f5c8913a1c77b7caa58a6fb0ae69c8dba126634ba455f3c6a
+size 5432