diff --git a/devtools/dev_sharegpt.yml b/devtools/dev_sharegpt.yml index c3af66cc5..9c65b49dc 100644 --- a/devtools/dev_sharegpt.yml +++ b/devtools/dev_sharegpt.yml @@ -2,7 +2,6 @@ base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0 model_type: LlamaForCausalLM tokenizer_type: LlamaTokenizer -is_llama_derived_model: true load_in_8bit: true load_in_4bit: false diff --git a/examples/code-llama/13b/lora.yml b/examples/code-llama/13b/lora.yml index e4ffd0684..ce5a892d0 100644 --- a/examples/code-llama/13b/lora.yml +++ b/examples/code-llama/13b/lora.yml @@ -1,7 +1,6 @@ base_model: codellama/CodeLlama-13b-hf model_type: LlamaForCausalLM tokenizer_type: CodeLlamaTokenizer -is_llama_derived_model: true load_in_8bit: true load_in_4bit: false diff --git a/examples/code-llama/13b/qlora.yml b/examples/code-llama/13b/qlora.yml index 78ffd28ed..d822e6847 100644 --- a/examples/code-llama/13b/qlora.yml +++ b/examples/code-llama/13b/qlora.yml @@ -1,7 +1,6 @@ base_model: codellama/CodeLlama-13b-hf model_type: LlamaForCausalLM tokenizer_type: CodeLlamaTokenizer -is_llama_derived_model: true load_in_8bit: false load_in_4bit: true diff --git a/examples/code-llama/34b/lora.yml b/examples/code-llama/34b/lora.yml index 664c30884..dfef2538b 100644 --- a/examples/code-llama/34b/lora.yml +++ b/examples/code-llama/34b/lora.yml @@ -1,7 +1,6 @@ base_model: codellama/CodeLlama-34b-hf model_type: LlamaForCausalLM tokenizer_type: CodeLlamaTokenizer -is_llama_derived_model: true load_in_8bit: true load_in_4bit: false diff --git a/examples/code-llama/34b/qlora.yml b/examples/code-llama/34b/qlora.yml index ca9b14eaf..77f821e1c 100644 --- a/examples/code-llama/34b/qlora.yml +++ b/examples/code-llama/34b/qlora.yml @@ -1,7 +1,6 @@ base_model: codellama/CodeLlama-34b-hf model_type: LlamaForCausalLM tokenizer_type: CodeLlamaTokenizer -is_llama_derived_model: true load_in_8bit: false load_in_4bit: true diff --git a/examples/code-llama/7b/lora.yml b/examples/code-llama/7b/lora.yml index 9f0613ede..3e6c7fe62 100644 --- a/examples/code-llama/7b/lora.yml +++ b/examples/code-llama/7b/lora.yml @@ -1,7 +1,6 @@ base_model: codellama/CodeLlama-7b-hf model_type: LlamaForCausalLM tokenizer_type: CodeLlamaTokenizer -is_llama_derived_model: true load_in_8bit: true load_in_4bit: false diff --git a/examples/code-llama/7b/qlora.yml b/examples/code-llama/7b/qlora.yml index 0dc485e7e..e817b113c 100644 --- a/examples/code-llama/7b/qlora.yml +++ b/examples/code-llama/7b/qlora.yml @@ -1,7 +1,6 @@ base_model: codellama/CodeLlama-7b-hf model_type: LlamaForCausalLM tokenizer_type: CodeLlamaTokenizer -is_llama_derived_model: true load_in_8bit: false load_in_4bit: true diff --git a/examples/falcon/config-7b-lora.yml b/examples/falcon/config-7b-lora.yml index ff713d7d1..5be9c6425 100644 --- a/examples/falcon/config-7b-lora.yml +++ b/examples/falcon/config-7b-lora.yml @@ -2,7 +2,7 @@ base_model: tiiuae/falcon-7b trust_remote_code: true model_type: AutoModelForCausalLM tokenizer_type: AutoTokenizer -is_falcon_derived_model: true + load_in_8bit: true load_in_4bit: false gptq: false diff --git a/examples/falcon/config-7b-qlora.yml b/examples/falcon/config-7b-qlora.yml index c6c71ac89..eb1cdfcdb 100644 --- a/examples/falcon/config-7b-qlora.yml +++ b/examples/falcon/config-7b-qlora.yml @@ -5,7 +5,7 @@ base_model: tiiuae/falcon-7b trust_remote_code: true model_type: AutoModelForCausalLM tokenizer_type: AutoTokenizer -is_falcon_derived_model: true + load_in_8bit: false # enable 4bit for QLoRA load_in_4bit: true diff --git a/examples/falcon/config-7b.yml b/examples/falcon/config-7b.yml index 6082ee87e..1dd46a93f 100644 --- a/examples/falcon/config-7b.yml +++ b/examples/falcon/config-7b.yml @@ -2,7 +2,7 @@ base_model: tiiuae/falcon-7b trust_remote_code: true model_type: AutoModelForCausalLM tokenizer_type: AutoTokenizer -is_falcon_derived_model: true + load_in_8bit: false load_in_4bit: false gptq: false diff --git a/examples/llama-2/fft_optimized.yml b/examples/llama-2/fft_optimized.yml index a7e2a6310..74edc95e6 100644 --- a/examples/llama-2/fft_optimized.yml +++ b/examples/llama-2/fft_optimized.yml @@ -1,7 +1,6 @@ base_model: NousResearch/Llama-2-7b-hf model_type: LlamaForCausalLM tokenizer_type: LlamaTokenizer -is_llama_derived_model: true load_in_8bit: false load_in_4bit: false diff --git a/examples/llama-2/gptq-lora.yml b/examples/llama-2/gptq-lora.yml index a3235c1fb..68ca9ed31 100644 --- a/examples/llama-2/gptq-lora.yml +++ b/examples/llama-2/gptq-lora.yml @@ -1,5 +1,4 @@ base_model: TheBloke/Llama-2-7B-GPTQ -is_llama_derived_model: false gptq: true gptq_disable_exllama: true model_type: AutoModelForCausalLM diff --git a/examples/llama-2/loftq.yml b/examples/llama-2/loftq.yml index d0d78098d..4529a912d 100644 --- a/examples/llama-2/loftq.yml +++ b/examples/llama-2/loftq.yml @@ -1,7 +1,6 @@ base_model: NousResearch/Llama-2-7b-hf model_type: LlamaForCausalLM tokenizer_type: LlamaTokenizer -is_llama_derived_model: true load_in_8bit: false load_in_4bit: false diff --git a/examples/llama-2/lora.yml b/examples/llama-2/lora.yml index 45df96c56..a7793dce4 100644 --- a/examples/llama-2/lora.yml +++ b/examples/llama-2/lora.yml @@ -1,7 +1,6 @@ base_model: NousResearch/Llama-2-7b-hf model_type: LlamaForCausalLM tokenizer_type: LlamaTokenizer -is_llama_derived_model: true load_in_8bit: true load_in_4bit: false diff --git a/examples/llama-2/qlora.yml b/examples/llama-2/qlora.yml index badb67ac3..834dbfb33 100644 --- a/examples/llama-2/qlora.yml +++ b/examples/llama-2/qlora.yml @@ -1,7 +1,6 @@ base_model: NousResearch/Llama-2-7b-hf model_type: LlamaForCausalLM tokenizer_type: LlamaTokenizer -is_llama_derived_model: true load_in_8bit: false load_in_4bit: true diff --git a/examples/llama-2/relora.yml b/examples/llama-2/relora.yml index 60bd56638..9fd19953c 100644 --- a/examples/llama-2/relora.yml +++ b/examples/llama-2/relora.yml @@ -1,7 +1,7 @@ base_model: NousResearch/Llama-2-7b-hf model_type: LlamaForCausalLM tokenizer_type: LlamaTokenizer -is_llama_derived_model: true + load_in_8bit: false load_in_4bit: true diff --git a/examples/mistral/Mistral-7b-example/config.yml b/examples/mistral/Mistral-7b-example/config.yml index 45e69e548..fd1249462 100644 --- a/examples/mistral/Mistral-7b-example/config.yml +++ b/examples/mistral/Mistral-7b-example/config.yml @@ -2,7 +2,6 @@ base_model: mistralai/Mistral-7B-v0.1 model_type: MistralForCausalLM tokenizer_type: LlamaTokenizer -is_mistral_derived_model: true load_in_8bit: true load_in_4bit: false diff --git a/examples/mistral/config.yml b/examples/mistral/config.yml index a5297fae8..e4c73fac9 100644 --- a/examples/mistral/config.yml +++ b/examples/mistral/config.yml @@ -1,7 +1,6 @@ base_model: mistralai/Mistral-7B-v0.1 model_type: MistralForCausalLM tokenizer_type: LlamaTokenizer -is_mistral_derived_model: true load_in_8bit: false load_in_4bit: false diff --git a/examples/mistral/qlora.yml b/examples/mistral/qlora.yml index 70099b0e3..c8ab13b97 100644 --- a/examples/mistral/qlora.yml +++ b/examples/mistral/qlora.yml @@ -1,7 +1,6 @@ base_model: mistralai/Mistral-7B-v0.1 model_type: MistralForCausalLM tokenizer_type: LlamaTokenizer -is_mistral_derived_model: true load_in_8bit: false load_in_4bit: true diff --git a/examples/qwen/lora.yml b/examples/qwen/lora.yml index 1a006ac4e..da4d784e0 100644 --- a/examples/qwen/lora.yml +++ b/examples/qwen/lora.yml @@ -2,7 +2,6 @@ base_model: Qwen/Qwen-7B model_type: AutoModelForCausalLM tokenizer_type: AutoTokenizer -is_qwen_derived_model: true trust_remote_code: true load_in_8bit: true diff --git a/examples/qwen/qlora.yml b/examples/qwen/qlora.yml index 462746a59..501a866b2 100644 --- a/examples/qwen/qlora.yml +++ b/examples/qwen/qlora.yml @@ -2,7 +2,6 @@ base_model: Qwen/Qwen-7B model_type: AutoModelForCausalLM tokenizer_type: AutoTokenizer -is_qwen_derived_model: true trust_remote_code: true load_in_8bit: false diff --git a/examples/tiny-llama/lora-mps.yml b/examples/tiny-llama/lora-mps.yml index e744638ba..fd7b02cac 100644 --- a/examples/tiny-llama/lora-mps.yml +++ b/examples/tiny-llama/lora-mps.yml @@ -1,7 +1,6 @@ base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T model_type: LlamaForCausalLM tokenizer_type: LlamaTokenizer -is_llama_derived_model: true load_in_8bit: true load_in_4bit: false diff --git a/examples/tiny-llama/lora.yml b/examples/tiny-llama/lora.yml index 67930dacf..15cd45910 100644 --- a/examples/tiny-llama/lora.yml +++ b/examples/tiny-llama/lora.yml @@ -1,7 +1,6 @@ base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T model_type: LlamaForCausalLM tokenizer_type: LlamaTokenizer -is_llama_derived_model: true load_in_8bit: true load_in_4bit: false diff --git a/examples/tiny-llama/pretrain.yml b/examples/tiny-llama/pretrain.yml index 874bbcf52..3b68a7f54 100644 --- a/examples/tiny-llama/pretrain.yml +++ b/examples/tiny-llama/pretrain.yml @@ -2,7 +2,6 @@ base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0 model_type: LlamaForCausalLM tokenizer_type: LlamaTokenizer -is_llama_derived_model: true load_in_8bit: false load_in_4bit: false diff --git a/examples/tiny-llama/qlora.yml b/examples/tiny-llama/qlora.yml index 66860ee33..3ea313c83 100644 --- a/examples/tiny-llama/qlora.yml +++ b/examples/tiny-llama/qlora.yml @@ -1,7 +1,6 @@ base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T model_type: LlamaForCausalLM tokenizer_type: LlamaTokenizer -is_llama_derived_model: true load_in_8bit: false load_in_4bit: true diff --git a/examples/yi-34B-chat/qlora.yml b/examples/yi-34B-chat/qlora.yml index 5d55e143b..dc8c37d18 100644 --- a/examples/yi-34B-chat/qlora.yml +++ b/examples/yi-34B-chat/qlora.yml @@ -1,8 +1,7 @@ base_model: 01-ai/Yi-34B-Chat model_type: LlamaForCausalLM tokenizer_type: LlamaTokenizer -is_mistral_derived_model: false -is_llama_derived_model: true + load_in_8bit: false load_in_4bit: true strict: false