ericrisco/llme2_sft_model_rlaif

README.md

@@ -49,8 +49,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.9.0
-- Transformers 4.39.0
-- Pytorch 2.2.1+cu121
-- Datasets 2.18.0
-- Tokenizers 0.15.2
+- PEFT 0.11.1
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

adapter_config.json

@@ -6,6 +6,7 @@
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
+  "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
-size 48
+oid sha256:5bf4be6bae354876359b072ee7c284b3e5a7ac87ae85844e280405cec03d3c16
+size 109069176

runs/Jun03_20-09-29_af0d8e52727a/events.out.tfevents.1717445369.af0d8e52727a.1115.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:451cbfcc6eef7b42cf07348043c7a8cc03f7cd558737c89a586191f482177593
+size 5639

tokenizer.json

@@ -139,6 +139,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
+    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6285d24d896b9c16bd512f85fa1d1353d0293df20262cce021cbde3aaaedb427
-size 4920
+oid sha256:e46b23b0b0cf45610335e7d169a29dedac7ed568f62aab9268cf8fe6eec52ebb
+size 5112