diff --git a/examples/mistral/mixtral.yml b/examples/mistral/mixtral.yml index 4c8e4d0ca..f80d8950f 100644 --- a/examples/mistral/mixtral.yml +++ b/examples/mistral/mixtral.yml @@ -1,6 +1,7 @@ base_model: DiscoResearch/mixtral-7b-8expert model_type: MixtralForCausalLM tokenizer_type: LlamaTokenizer +trust_remote_code: true load_in_8bit: false load_in_4bit: true diff --git a/requirements.txt b/requirements.txt index 2ada901cb..f6aa30f67 100644 --- a/requirements.txt +++ b/requirements.txt @@ -2,7 +2,7 @@ auto-gptq==0.5.1 packaging peft==0.6.0 -transformers==4.35.2 +transformers @ git+https://github.com/huggingface/transformers.git@df5c5c62ae253055336f5bb0828ca8e3e15ab6bd tokenizers==0.15.0 bitsandbytes>=0.41.1 accelerate==0.24.1