try #2: pin hf transformers and accelerate to latest release, don't r…

…einstall pytorch (#867)

* isolate torch from the requirements.txt

* fix typo for removed line ending

* pin transformers and accelerate to latest releases

* try w auto-gptq==0.5.1

* update README to remove manual peft install

* pin xformers to 0.0.22

* bump flash-attn to 2.3.3

* pin flash attn to exact version

.github/workflows/tests.yml

@@ -71,6 +71,7 @@ jobs:
 
       - name: Install dependencies
         run: |
+          pip3 install --extra-index-url https://download.pytorch.org/whl/cu118 -U torch==2.0.1
           pip3 uninstall -y transformers accelerate
           pip3 install -U -e .[flash-attn]
           pip3 install -r requirements-tests.txt

README.md

@@ -91,7 +91,6 @@ cd axolotl
 
 pip3 install packaging
 pip3 install -e '.[flash-attn,deepspeed]'
-pip3 install -U git+https://github.com/huggingface/peft.git
 
 # finetune lora
 accelerate launch -m axolotl.cli.train examples/openllama-3b/lora.yml

requirements.txt

@@ -1,22 +1,20 @@
---extra-index-url https://download.pytorch.org/whl/cu118
 --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/
-torch==2.0.1
-auto-gptq==0.4.2
+auto-gptq==0.5.1
 packaging
 peft==0.6.0
-transformers @ git+https://github.com/huggingface/transformers.git@acc394c4f5e1283c19783581790b3dc3105a3697
+transformers==4.35.1
 bitsandbytes>=0.41.1
-accelerate @ git+https://github.com/huggingface/accelerate@80da9cfb09bb3cc9f1b385cb55d6b90d025a5fd9
+accelerate==0.24.1
 deepspeed
 addict
 fire
 PyYAML>=6.0
 datasets>=2.14.0
-flash-attn>=2.3.0
+flash-attn==2.3.3
 sentencepiece
 wandb
 einops
-xformers>=0.0.22
+xformers==0.0.22
 optimum==1.13.2
 hf_transfer
 colorama