diff --git a/devtools/dev_sharegpt.yml b/devtools/dev_sharegpt.yml index c3af66cc5a..9c65b49dcd 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 e4ffd0684e..ce5a892d08 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 78ffd28ed5..d822e68470 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 664c308848..dfef2538b0 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 ca9b14eaf1..77f821e1c8 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 9f0613ede9..3e6c7fe620 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 0dc485e7e1..e817b113cc 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 ff713d7d13..5be9c64253 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 c6c71ac895..eb1cdfcdba 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 6082ee87eb..1dd46a93ff 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 a7e2a6310a..74edc95e6b 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 a3235c1fba..68ca9ed31c 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 d0d78098d7..4529a912dc 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 45df96c562..a7793dce4c 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 badb67ac3d..834dbfb33a 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 60bd566383..9fd19953c6 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 45e69e5486..fd12494627 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 a5297fae81..e4c73fac95 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 70099b0e33..c8ab13b979 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 1a006ac4e1..da4d784e0a 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 462746a59f..501a866b2d 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 e744638ba4..fd7b02caca 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 67930dacf6..15cd459104 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 874bbcf521..3b68a7f547 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 66860ee338..3ea313c838 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 5d55e143b5..dc8c37d187 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