amd
/

X-EcoMLA-1B8B-fixed-kv64-DPO

alignment-handbook

Generated from Trainer

Model card Files Files and versions

X-EcoMLA-1B8B-fixed-kv64-DPO

Commit History

Convert weights to .safetensors and remove PyTorch .bin files

6185c74

mrgzadeh commited on Sep 23

Update mla_layer_config.json

66bb400

Mingyuyang-1 commited on Aug 11

Update mla_layer_config.json

264bdbb

Mingyuyang-1 commited on Aug 10

Upload LICENSE

16fee2f

ghl commited on Jun 25

Update README.md

94b8d6d

Mingyuyang-1 commited on Jun 25

Delete zero_to_fp32.py

ecd777a

Mingyuyang-1 commited on Jun 25

Delete training_args.bin

1246c89

Mingyuyang-1 commited on Jun 25

Delete trainer_state.json

e88d90f

Mingyuyang-1 commited on Jun 25

Delete train_results.json

42ad13a

Mingyuyang-1 commited on Jun 25

Delete tmp_0_dpo.yaml

b060e53

Mingyuyang-1 commited on Jun 25

Delete lm_harness_eval.md

fed5a2b

Mingyuyang-1 commited on Jun 25

Delete latest

7315c7d

Mingyuyang-1 commited on Jun 25

Delete eval_results.json

7d30520

Mingyuyang-1 commited on Jun 25

Delete all_results.json

f63c50f

Mingyuyang-1 commited on Jun 25

Update README.md

0e74c6f

Mingyuyang-1 commited on Jun 25

Upload folder using huggingface_hub

aca3f31

Mingyuyang-1 commited on Jun 25

initial commit

5bcfd6b

Mingyuyang-1 commited on Jun 25