Hugging Face's logo

MBZUAI
/
bactrian-x-llama-13b-lora

Model card Files Community
haonan-li commited on
Commit
cc6a29b
•
1 Parent(s): 238c109

update model

Browse files
Files changed (2) hide show
  1. README.md +2 -2
  2. adapter_model.bin +1 -1
README.md CHANGED
@@ -2,7 +2,7 @@
2
  license: mit
3
  ---
4
 
5
- #### Current Training Steps: 68,000
6
 
7
 
8
  This repo contains a low-rank adapter (LoRA) for LLaMA-13b
@@ -38,7 +38,7 @@ That is:
38
  ```
39
  python finetune.py \
40
  --base_model='decapoda-research/llama-13b-hf' \
41
- --num_epochs=10 \
42
  --batch_size=128 \
43
  --cutoff_len=512 \
44
  --group_by_length \
 
2
  license: mit
3
  ---
4
 
5
+ #### Current Training Steps: 108,000
6
 
7
 
8
  This repo contains a low-rank adapter (LoRA) for LLaMA-13b
 
38
  ```
39
  python finetune.py \
40
  --base_model='decapoda-research/llama-13b-hf' \
41
+ --num_epochs=5 \
42
  --batch_size=128 \
43
  --cutoff_len=512 \
44
  --group_by_length \
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a5209f73bf5942bfda97ea438272b02e43246db60dfd2c5e794086a17e2eeb5
3
  size 419546189
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54ae638cab1f3b74f130084678d80127c2df1d6d7fd864614e6b9c342e797f71
3
  size 419546189