update openllama and clean up paths

2023-06-11 11:03:31 -04:00
parent a6ebf57e82
commit d0d7eaa4f3
6 changed files with 28 additions and 18 deletions
--- a/examples/gptj-qlora/config.yml
+++ b/examples/gptj-qlora/config.yml
--- a/examples/openllama-3b/README.md
+++ b/examples/openllama-3b/README.md
@@ -0,0 +1,16 @@
+# openllama-3b
+
+Basic full tune
+```shell
+accelerate launch scripts/finetune.py examples/qlora-openllama-3b/config.yml
+```
+
+LoRA
+```shell
+accelerate launch scripts/finetune.py examples/qlora-openllama-3b/lora.yml
+```
+
+QLoRA
+```shell
+accelerate launch scripts/finetune.py examples/qlora-openllama-3b/qlora.yml
+```
--- a/examples/lora-openllama-3b/config.yml
+++ b/examples/lora-openllama-3b/config.yml
@@ -1,5 +1,5 @@
-base_model: openlm-research/open_llama_3b_600bt_preview
-base_model_config: openlm-research/open_llama_3b_600bt_preview
+base_model: openlm-research/open_llama_3b
+base_model_config: openlm-research/open_llama_3b
 model_type: LlamaForCausalLM
 tokenizer_type: LlamaTokenizer
 load_in_8bit: true
--- a/examples/qlora-openllama-3b/config.yml
+++ b/examples/qlora-openllama-3b/config.yml
@@ -1,5 +1,5 @@
-base_model: openlm-research/open_llama_3b_600bt_preview
-base_model_config: openlm-research/open_llama_3b_600bt_preview
+base_model: openlm-research/open_llama_3b
+base_model_config: openlm-research/open_llama_3b
 model_type: LlamaForCausalLM
 tokenizer_type: LlamaTokenizer
 load_in_8bit: false
--- a/examples/qlora-openllama-3b/README.md
+++ b/examples/qlora-openllama-3b/README.md
@@ -1,6 +0,0 @@
-# qlora-openllama-3b
-
-```shell
-accelerate launch scripts/finetune.py examples/qlora-openllama-3b/config.yml
-
-```