Hugging Face's logo

moodlep
/
smollm2-17b-dpo-cai-v1

PEFT
TensorBoard
Safetensors
llama
alignment-handbook
trl
dpo
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Metrics Community
moodlep commited on
Commit
3502899
·
verified ·
1 Parent(s): a0fe6cf

Training in progress, step 257

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. runs/Jan09_13-33-32_pkaiju/events.out.tfevents.1736429656.pkaiju.69119.0 +2 -2
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4240abb03e0408a67ad9fe783a905bc4b890b60e8e8449bd5e48b8e62ce73e0b
3
  size 72396376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5178696c4a94c545b3b048a1906e6fb292a637147b6496a1a3ba53e5799ef9f
3
  size 72396376
runs/Jan09_13-33-32_pkaiju/events.out.tfevents.1736429656.pkaiju.69119.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f5e0fe7544de2afe0bdf332d79f32924290cee34c09dabe5166f0d88b18eb48
3
- size 9993
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43ddf0d9b7083b3abdd48a2c42702d226af944f250bb4a93ad9db7c8bcf39463
3
+ size 10347