Commit History

re-run RPP tuning with MAX_NEW_TOKENS=2048
ecfd23f

dh-mc commited on

Update eval-4gpu.sh
bdc35fb

dh-mc commited on

ready eval qwen2-72b
1f80432

dh-mc commited on

more results
cd538e0

inflaton commited on

complete gpt-4o-mini training
3f6b774

dh-mc commited on

Update eval-mac.sh
4221766

dh-mc commited on

Update eval-mac.sh
a1cdfad

dh-mc commited on

complete finetune rpp results
a2a97d3

inflaton commited on

add env var END_REPETITION_PENALTY
ee71b10

dh-mc commited on

more results
38f452c

inflaton commited on

eval rpp on fine-tuned checkpoints:
162cc09

dh-mc commited on

more results
28ac903

inflaton commited on

finetune results
77dd763

inflaton commited on

eval fine-tuned checkpoints
44cfb92

dh-mc commited on

updated scripts
fc9601b

inflaton commited on

fine-tuned checkpoints
e1e71f5

inflaton commited on

Update tune-lf-4gpu.sh
6e8064d

dh-mc commited on

train with 4gpu
a2100ac

dh-mc commited on

more results
22c212e

inflaton commited on

ready for LF lora training
6fc6dc9

dh-mc commited on

complete results for gpt-4o and gpt-4o-mini
fddc7fb

inflaton commited on

ready for few shots prompting 4gpu
0156aec

dh-mc commited on

eval with few-shots prompting
6c91c84

dh-mc commited on

more results
eb7323d

inflaton commited on

enable env: START_REPETITION_PENALTY
a457091

dh-mc commited on

more results
0f5efb0

inflaton commited on

more results
734bd6c

inflaton commited on

set max_new_tokens to 300
a37d279

dh-mc commited on

eval internlm
d60f8cb

inflaton commited on

qwen2/llama3
ef85f45

inflaton commited on

enable do_sample
a69b127

dh-mc commited on

more results
0004fdd

inflaton commited on

internlm results
e2b6c4d

inflaton commited on

ready for gpu cluster
c73d190

dh-mc commited on

WIP
07320d0

dh-mc commited on

clean up
54b1b8a

dh-mc commited on

initial code for Chinese/English translation
3860729

dh-mc commited on