jeremyc commited on
Commit
cb88b3f
•
1 Parent(s): 5240c6d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -1
README.md CHANGED
@@ -1,5 +1,21 @@
 
 
 
 
 
 
 
 
1
  ## Alpaca-Lora-Swe 7B
2
 
3
  Alpaca-Lora-Swe-7b is a LLaMA-7B model fine-tuned on the translated [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca) dataset to follow the 🇸🇪 Swedish instructions
4
 
5
- For more information, please visit the Github repo: https://github.com/jeremycochoy/alpaca-lora-swe
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ datasets:
3
+ - jeremyc/Alpaca-Lora-GPT4-Swedish
4
+ language:
5
+ - en
6
+ - sv
7
+ ---
8
+
9
  ## Alpaca-Lora-Swe 7B
10
 
11
  Alpaca-Lora-Swe-7b is a LLaMA-7B model fine-tuned on the translated [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca) dataset to follow the 🇸🇪 Swedish instructions
12
 
13
+ This model was trained for 5 epoch with a combined dataset of english + swedish and the original Alpca-Lora prompt using the following command:
14
+ ```
15
+ python3 finetune.py --base_model='./llama-7b' --output_dir='./lora-alpaca' --resume_from_checkpoint true --micro_batch_size=14 --num_epochs=3 --cutoff_len=512 --group_by_length --output_dir='./lora-alpaca-swe' --data_path='alpaca_gpt4_combined.json' --num_epochs 5 --lora_target_modules='[q_proj,k_proj,v_proj,o_proj]'
16
+
17
+ ```
18
+
19
+ The training run logs are available at https://wandb.ai/jeremy-cochoy/huggingface/runs/896ntg42
20
+
21
+ For more information, please visit the Github repo: https://github.com/jeremycochoy/alpaca-lora-swe