diff options
Diffstat (limited to 'examples/finetune')
| -rw-r--r-- | examples/finetune/CMakeLists.txt | 2 | ||||
| -rw-r--r-- | examples/finetune/README.md | 12 | ||||
| -rw-r--r-- | examples/finetune/finetune.sh | 2 |
3 files changed, 8 insertions, 8 deletions
diff --git a/examples/finetune/CMakeLists.txt b/examples/finetune/CMakeLists.txt index 2b52d21c..64afe6dd 100644 --- a/examples/finetune/CMakeLists.txt +++ b/examples/finetune/CMakeLists.txt @@ -1,4 +1,4 @@ -set(TARGET finetune) +set(TARGET llama-finetune) add_executable(${TARGET} finetune.cpp) install(TARGETS ${TARGET} RUNTIME) target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT}) diff --git a/examples/finetune/README.md b/examples/finetune/README.md index 2fafd505..a6ae6498 100644 --- a/examples/finetune/README.md +++ b/examples/finetune/README.md @@ -7,7 +7,7 @@ Basic usage instructions: wget https://raw.githubusercontent.com/brunoklein99/deep-learning-notes/master/shakespeare.txt # finetune LORA adapter -./bin/finetune \ +./bin/llama-finetune \ --model-base open-llama-3b-v2-q8_0.gguf \ --checkpoint-in chk-lora-open-llama-3b-v2-q8_0-shakespeare-LATEST.gguf \ --checkpoint-out chk-lora-open-llama-3b-v2-q8_0-shakespeare-ITERATION.gguf \ @@ -18,7 +18,7 @@ wget https://raw.githubusercontent.com/brunoklein99/deep-learning-notes/master/s --use-checkpointing # predict -./bin/main -m open-llama-3b-v2-q8_0.gguf --lora lora-open-llama-3b-v2-q8_0-shakespeare-LATEST.bin +./bin/llama-cli -m open-llama-3b-v2-q8_0.gguf --lora lora-open-llama-3b-v2-q8_0-shakespeare-LATEST.bin ``` **Only llama based models are supported!** The output files will be saved every N iterations (config with `--save-every N`). @@ -38,14 +38,14 @@ After 10 more iterations: Checkpoint files (`--checkpoint-in FN`, `--checkpoint-out FN`) store the training process. When the input checkpoint file does not exist, it will begin finetuning a new randomly initialized adapter. llama.cpp compatible LORA adapters will be saved with filename specified by `--lora-out FN`. -These LORA adapters can then be used by `main` together with the base model, like in the 'predict' example command above. +These LORA adapters can then be used by `llama-cli` together with the base model, like in the 'predict' example command above. -In `main` you can also load multiple LORA adapters, which will then be mixed together. +In `llama-cli` you can also load multiple LORA adapters, which will then be mixed together. For example if you have two LORA adapters `lora-open-llama-3b-v2-q8_0-shakespeare-LATEST.bin` and `lora-open-llama-3b-v2-q8_0-bible-LATEST.bin`, you can mix them together like this: ```bash -./bin/main -m open-llama-3b-v2-q8_0.gguf \ +./bin/llama-cli -m open-llama-3b-v2-q8_0.gguf \ --lora lora-open-llama-3b-v2-q8_0-shakespeare-LATEST.bin \ --lora lora-open-llama-3b-v2-q8_0-bible-LATEST.bin ``` @@ -55,7 +55,7 @@ You can change how strong each LORA adapter is applied to the base model by usin For example to apply 40% of the 'shakespeare' LORA adapter, 80% of the 'bible' LORA adapter and 100% of yet another one: ```bash -./bin/main -m open-llama-3b-v2-q8_0.gguf \ +./bin/llama-cli -m open-llama-3b-v2-q8_0.gguf \ --lora-scaled lora-open-llama-3b-v2-q8_0-shakespeare-LATEST.bin 0.4 \ --lora-scaled lora-open-llama-3b-v2-q8_0-bible-LATEST.bin 0.8 \ --lora lora-open-llama-3b-v2-q8_0-yet-another-one-LATEST.bin diff --git a/examples/finetune/finetune.sh b/examples/finetune/finetune.sh index 079bfa11..d7f2165e 100644 --- a/examples/finetune/finetune.sh +++ b/examples/finetune/finetune.sh @@ -2,7 +2,7 @@ cd `dirname $0` cd ../.. -EXE="./finetune" +EXE="./llama-finetune" if [[ ! $LLAMA_MODEL_DIR ]]; then LLAMA_MODEL_DIR="./models"; fi if [[ ! $LLAMA_TRAINING_DIR ]]; then LLAMA_TRAINING_DIR="."; fi |