Upload 3 files

reward_model/README.md

@@ -0,0 +1,20 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+### Framework versions
+
+
+- PEFT 0.4.0

reward_model/adapter_config.json

@@ -0,0 +1,22 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "gpt2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "modules_to_save": [
+    "scores"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "c_attn"
+  ],
+  "task_type": "SEQ_CLS"
+}

reward_model/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5e9821a962b6ee6a3e121817d225fb89109633a6bb7612635171e799443d34c
+size 2371004