 Jeff Tang
|
8989e69937
README for grpo
|
hace 3 semanas |
|
Jeff Tang
|
7edf3d8df0
llm as a judge running now
|
hace 4 semanas |
|
Jeff Tang
|
57c05170eb
added llm as a judge reward func
|
hace 4 semanas |
|
Jeff Tang
|
c88e10fab6
grpo llama 3.2 3b with 3 reward functions
|
hace 1 mes |
|
Jeff Tang
|
54e49bca09
added steps to run create_bird_eval_dataset.py
|
hace 2 meses |
|
Jeff Tang
|
0c7b3482eb
restored llama_eval.sh
|
hace 2 meses |
|
Jeff Tang
|
af3ea4fe64
script to save dev set in pandas csv format
|
hace 2 meses |
|
Jeff Tang
|
be4817c94b
Update FT README.md with llama 3.3 70b on multiple gpus
|
hace 2 meses |
|
Jeff Tang
|
fc80546035
Update FT EADME.md
|
hace 3 meses |
|
Jeff Tang
|
e38abf1202
Update eval README.md
|
hace 3 meses |
|
Jeff Tang
|
27a23afdd3
main README
|
hace 3 meses |
|
Jeff Tang
|
82bb0087b8
3 READMEs update; fine-tuning requirements update with vllm etc
|
hace 3 meses |
|
Jeff Tang
|
6501cf4566
FT readme update; removed old vllm py and sh files
|
hace 3 meses |
|
Jeff Tang
|
799dee6813
some cleanup and typo fix
|
hace 3 meses |
|
Jeff Tang
|
12a6dfa2ac
code cleanup and refactoring; cloud llama response generation in tqdm progress
|
hace 3 meses |
|
Jeff Tang
|
deca42ccd8
Merge branch 'text2sql' of https://github.com/meta-llama/llama-cookbook into text2sql
|
hace 3 meses |
|
Jeff Tang
|
77d3544c81
batch processing and vllm llama call in parallel; clean progress showing in 2-step eval
|
hace 3 meses |
|
Jeff Tang
|
cb8b0bd40e
Update eval README.md
|
hace 3 meses |
|
Jeff Tang
|
df598c474d
Update eval README.md
|
hace 3 meses |
|
Jeff Tang
|
1b802d30bf
Update FT README.md
|
hace 3 meses |
|
Jeff Tang
|
1ac67d9950
Update eval README.md for vllm based HF model
|
hace 3 meses |
|
Jeff Tang
|
b630735159
Update fine-tuning README.md
|
hace 3 meses |
|
Jeff Tang
|
f80e7bf5e9
Update fine-tuning README.md
|
hace 3 meses |
|
Jeff Tang
|
e059899812
Update the eval section using vllm for fine-tuning README.md
|
hace 3 meses |
 Amir Youssefi
|
ad485095ae
trl import
|
hace 3 meses |
|
Jeff Tang
|
f894d26f29
vllm enabled eval for HF and fine-tuned models; code cleanup and refactoring for text2sql_eval; minimum eval packages for eval requirements; merge peft script to make vllm happy
|
hace 3 meses |
|
Jeff Tang
|
5baa1e3fd7
vllm enabled eval for HF and fine-tuned models; code cleanup and refactoring for text2sql_eval; minimum eval packages for eval requirements; merge peft script to make vllm happy
|
hace 3 meses |
|
Amir Youssefi
|
e10ddda64a
some refactoring and cleaning
|
hace 3 meses |
|
Amir
|
33ac1abc9f
Update README.md
|
hace 3 meses |
|
Amir
|
58ea6cb115
Update README.md
|
hace 3 meses |
