vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

examples : remove finetune and train-text-from-scratch (#8669)

Browse source 
* examples : remove finetune and train-text-from-scratch

* fix build

* update help message

* fix small typo for export-lora
This commit is contained in:
Xuan Son Nguyen 2024-07-25 10:39:04 +02:00 • committed by GitHub
parent 4b0eff3df5
commit be6d7c0791
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
15 changed files with 14 additions and 4299 deletions
Download patch file Download diff file Expand all files Collapse all files

12
examples/export-lora/README.md
View file

@ -19,7 +19,15 @@ For example:
./bin/llama-export-lora \
-m open-llama-3b-v2-q8_0.gguf \
-o open-llama-3b-v2-q8_0-english2tokipona-chat.gguf \
--lora lora-open-llama-3b-v2-q8_0-english2tokipona-chat-LATEST.bin
--lora lora-open-llama-3b-v2-q8_0-english2tokipona-chat-LATEST.gguf
```
Multiple LORA adapters can be applied by passing multiple `--lora FNAME` or `--lora-scaled FNAME S` command line parameters.
Multiple LORA adapters can be applied by passing multiple `--lora FNAME` or `--lora-scaled FNAME S` command line parameters:
```bash
./bin/llama-export-lora \
-m your_base_model.gguf \
-o your_merged_model.gguf \
--lora-scaled lora_task_A.gguf 0.5 \
--lora-scaled lora_task_B.gguf 0.5
```