tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

fix inference

Browse Source
This commit is contained in:
mhenrichsen
2023-06-12 21:39:19 +02:00
parent 93dacba228
commit 34ae69989f
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@@ -500,16 +500,16 @@ Pass the appropriate flag to the train command:
- Pretrained LORA: - Pretrained LORA:
```bash ```bash
--inference --lora_model_dir ./completed-model --inference --lora_model_dir="./lora-output-dir"
``` ```
- Full weights finetune: - Full weights finetune:
```bash ```bash
--inference --base_model ./completed-model --inference --base_model="./completed-model"
``` ```
- Full weights finetune w/ a prompt from a text file: - Full weights finetune w/ a prompt from a text file:
```bash ```bash
cat /tmp/prompt.txt | python scripts/finetune.py configs/your_config.yml \ cat /tmp/prompt.txt | python scripts/finetune.py configs/your_config.yml \
--base_model ./completed-model --inference --prompter=None --load_in_8bit=True --base_model="./completed-model" --inference --prompter=None --load_in_8bit=True
``` ```
### Merge LORA to base ### Merge LORA to base