remove strict=false from example yamls [skip ci] (#2523) [skip ci]

2025-04-12 07:25:11 -07:00
parent de8a625dd7
commit dd8bad06d0
99 changed files with 0 additions and 99 deletions
--- a/examples/cerebras/btlm-ft.yml
+++ b/examples/cerebras/btlm-ft.yml
@@ -8,7 +8,6 @@ tokenizer_type: GPT2Tokenizer
 trust_remote_code: true
 tokenizer_use_fast: true
 tokenizer_legacy: true
-strict: false
 push_dataset_to_hub:
 hf_use_auth_token: true
 datasets:
--- a/examples/cerebras/qlora.yml
+++ b/examples/cerebras/qlora.yml
@@ -4,7 +4,6 @@ base_model: cerebras/Cerebras-GPT-1.3B

 load_in_8bit: false
 load_in_4bit: true
-strict: false
 push_dataset_to_hub:
 datasets:
  - path: teknium/GPT4-LLM-Cleaned
--- a/examples/code-llama/13b/lora.yml
+++ b/examples/code-llama/13b/lora.yml
@@ -7,7 +7,6 @@ tokenizer_type: CodeLlamaTokenizer

 load_in_8bit: true
 load_in_4bit: false
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/code-llama/13b/qlora.yml
+++ b/examples/code-llama/13b/qlora.yml
@@ -7,7 +7,6 @@ tokenizer_type: CodeLlamaTokenizer

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/code-llama/34b/lora.yml
+++ b/examples/code-llama/34b/lora.yml
@@ -7,7 +7,6 @@ tokenizer_type: CodeLlamaTokenizer

 load_in_8bit: true
 load_in_4bit: false
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/code-llama/34b/qlora.yml
+++ b/examples/code-llama/34b/qlora.yml
@@ -7,7 +7,6 @@ tokenizer_type: CodeLlamaTokenizer

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/code-llama/7b/lora.yml
+++ b/examples/code-llama/7b/lora.yml
@@ -7,7 +7,6 @@ tokenizer_type: CodeLlamaTokenizer

 load_in_8bit: true
 load_in_4bit: false
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/code-llama/7b/qlora.yml
+++ b/examples/code-llama/7b/qlora.yml
@@ -7,7 +7,6 @@ tokenizer_type: CodeLlamaTokenizer

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/cohere/command-r-7b-qlora.yml
+++ b/examples/cohere/command-r-7b-qlora.yml
@@ -4,7 +4,6 @@ tokenizer_type: AutoTokenizer

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 # huggingface repo
 chat_template: cohere
--- a/examples/dbrx/16bit-lora.yaml
+++ b/examples/dbrx/16bit-lora.yaml
@@ -3,7 +3,6 @@ base_model: LnL-AI/dbrx-base-converted-v2
 # hub_model_id: username/custom_model_name

 trust_remote_code: true
-strict: false

 datasets:
  - path: tatsu-lab/alpaca
--- a/examples/dbrx/8bit-lora.yaml
+++ b/examples/dbrx/8bit-lora.yaml
@@ -6,7 +6,6 @@ trust_remote_code: true

 load_in_8bit: true
 load_in_4bit: false
-strict: false

 datasets:
  - path: tatsu-lab/alpaca
--- a/examples/dbrx/fft-ds-zero3.yaml
+++ b/examples/dbrx/fft-ds-zero3.yaml
@@ -3,7 +3,6 @@ base_model: LnL-AI/dbrx-base-converted-v2
 # hub_model_id: username/custom_model_name

 trust_remote_code: true
-strict: false

 datasets:
  - path: tatsu-lab/alpaca
--- a/examples/deepseek-v2/fft-fsdp-16b.yaml
+++ b/examples/deepseek-v2/fft-fsdp-16b.yaml
@@ -2,7 +2,6 @@ base_model: deepseek-ai/DeepSeek-V2-Lite
 # Automatically upload checkpoint and final model to HF
 # hub_model_id: username/custom_model_name
 trust_remote_code: true
-strict: false

 datasets:
  - path: tatsu-lab/alpaca
--- a/examples/deepseek-v2/qlora-fsdp-2_5.yaml
+++ b/examples/deepseek-v2/qlora-fsdp-2_5.yaml
@@ -6,7 +6,6 @@ trust_remote_code: true

 load_in_8bit: false
 load_in_4bit: true
-strict: false


 plugins:
--- a/examples/falcon/config-7b-lora.yml
+++ b/examples/falcon/config-7b-lora.yml
@@ -11,7 +11,6 @@ trust_remote_code: true
 load_in_8bit: true
 load_in_4bit: false
 gptq: false
-strict: false
 push_dataset_to_hub:
 datasets:
  - path: teknium/GPT4-LLM-Cleaned
--- a/examples/falcon/config-7b-qlora.yml
+++ b/examples/falcon/config-7b-qlora.yml
@@ -15,7 +15,6 @@ load_in_8bit: false
 # enable 4bit for QLoRA
 load_in_4bit: true
 gptq: false
-strict: false
 push_dataset_to_hub:
 datasets:
  - path: QingyiSi/Alpaca-CoT
--- a/examples/falcon/config-7b.yml
+++ b/examples/falcon/config-7b.yml
@@ -8,7 +8,6 @@ tokenizer_type: AutoTokenizer
 # required by falcon custom model code: https://huggingface.co/tiiuae/falcon-7b/tree/main
 trust_remote_code: true
 gptq: false
-strict: false
 push_dataset_to_hub:
 datasets:
  - path: teknium/GPT4-LLM-Cleaned
--- a/examples/gemma/qlora.yml
+++ b/examples/gemma/qlora.yml
@@ -8,7 +8,6 @@ tokenizer_type: AutoTokenizer

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 # huggingface repo
 datasets:
--- a/examples/gemma2/qlora.yml
+++ b/examples/gemma2/qlora.yml
@@ -7,7 +7,6 @@ tokenizer_type: AutoTokenizer

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 # huggingface repo
 chat_template: gemma
--- a/examples/gemma2/reward-model.yaml
+++ b/examples/gemma2/reward-model.yaml
@@ -5,7 +5,6 @@ num_labels: 1
 tokenizer_type: AutoTokenizer
 # Automatically upload checkpoint and final model to HF
 # hub_model_id: username/custom_model_name
-strict: false

 reward_model: true
 chat_template: gemma
--- a/examples/gemma3/gemma-3-1b-qlora.yml
+++ b/examples/gemma3/gemma-3-1b-qlora.yml
@@ -10,7 +10,6 @@ ddp_find_unused_parameters: true

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 # huggingface repo
 chat_template: gemma3
--- a/examples/gemma3/gemma-3-4b-qlora.yml
+++ b/examples/gemma3/gemma-3-4b-qlora.yml
@@ -1,5 +1,4 @@
 base_model: google/gemma-3-4b-it
-strict: false

 load_in_4bit: true

--- a/examples/gemma3/gemma-3-4b-vision-qlora.yml
+++ b/examples/gemma3/gemma-3-4b-vision-qlora.yml
@@ -1,6 +1,5 @@
 base_model: google/gemma-3-4b-it
 processor_type: AutoProcessor
-strict: false

 load_in_4bit: true

--- a/examples/gptj/qlora.yml
+++ b/examples/gptj/qlora.yml
@@ -4,7 +4,6 @@ base_model: EleutherAI/gpt-j-6b

 load_in_8bit: false
 load_in_4bit: true
-strict: false
 push_dataset_to_hub:
 datasets:
  - path: teknium/GPT4-LLM-Cleaned
--- a/examples/jamba/qlora.yaml
+++ b/examples/jamba/qlora.yaml
@@ -6,7 +6,6 @@ trust_remote_code: true

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/jamba/qlora_deepspeed.yaml
+++ b/examples/jamba/qlora_deepspeed.yaml
@@ -5,7 +5,6 @@ trust_remote_code: true

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/jamba/qlora_fsdp_large.yaml
+++ b/examples/jamba/qlora_fsdp_large.yaml
@@ -5,7 +5,6 @@ tokenizer_type: AutoTokenizer
 # hub_model_id: username/custom_model_name

 load_in_4bit: true
-strict: false
 use_tensorboard: true
 chat_template: jamba
 datasets:
--- a/examples/llama-2/fft_optimized.yml
+++ b/examples/llama-2/fft_optimized.yml
@@ -4,7 +4,6 @@ model_type: LlamaForCausalLM
 tokenizer_type: LlamaTokenizer
 # Automatically upload checkpoint and final model to HF
 # hub_model_id: username/custom_model_name
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/llama-2/gptq-lora.yml
+++ b/examples/llama-2/gptq-lora.yml
@@ -10,7 +10,6 @@ gptq_disable_exllama: true

 tokenizer_use_fast: true
 tokenizer_legacy: true
-strict: false
 push_dataset_to_hub:
 hf_use_auth_token: true
 datasets:
--- a/examples/llama-2/lisa.yml
+++ b/examples/llama-2/lisa.yml
@@ -4,7 +4,6 @@ model_type: LlamaForCausalLM
 tokenizer_type: LlamaTokenizer
 # Automatically upload checkpoint and final model to HF
 # hub_model_id: username/custom_model_name
-strict: false

 datasets:
  - path: teknium/GPT4-LLM-Cleaned
--- a/examples/llama-2/loftq.yml
+++ b/examples/llama-2/loftq.yml
@@ -4,7 +4,6 @@ model_type: LlamaForCausalLM
 tokenizer_type: LlamaTokenizer
 # Automatically upload checkpoint and final model to HF
 # hub_model_id: username/custom_model_name
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/llama-2/lora.yml
+++ b/examples/llama-2/lora.yml
@@ -7,7 +7,6 @@ tokenizer_type: LlamaTokenizer

 load_in_8bit: true
 load_in_4bit: false
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/llama-2/qlora-fsdp.yml
+++ b/examples/llama-2/qlora-fsdp.yml
@@ -7,7 +7,6 @@ tokenizer_type: LlamaTokenizer

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 datasets:
  - path: yahma/alpaca-cleaned
--- a/examples/llama-2/qlora.yml
+++ b/examples/llama-2/qlora.yml
@@ -7,7 +7,6 @@ tokenizer_type: LlamaTokenizer

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/llama-2/relora.yml
+++ b/examples/llama-2/relora.yml
@@ -5,7 +5,6 @@ tokenizer_type: LlamaTokenizer

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 datasets:
  - path: teknium/GPT4-LLM-Cleaned
--- a/examples/llama-3-vision/lora-11b.yaml
+++ b/examples/llama-3-vision/lora-11b.yaml
@@ -4,7 +4,6 @@ processor_type: AutoProcessor
 # Automatically upload checkpoint and final model to HF
 # hub_model_id: username/custom_model_name

-strict: false

 # these 3 lines are needed for now to handle vision chat templates w images
 skip_prepare_dataset: true
--- a/examples/llama-3/fft-8b-liger-fsdp.yaml
+++ b/examples/llama-3/fft-8b-liger-fsdp.yaml
@@ -9,7 +9,6 @@ liger_rms_norm: true
 liger_glu_activation: true
 liger_fused_linear_cross_entropy: true

-strict: false

 chat_template: llama3
 datasets:
--- a/examples/llama-3/fft-8b.yaml
+++ b/examples/llama-3/fft-8b.yaml
@@ -1,7 +1,6 @@
 base_model: NousResearch/Meta-Llama-3.1-8B
 # Automatically upload checkpoint and final model to HF
 # hub_model_id: username/custom_model_name
-strict: false

 datasets:
  - path: tatsu-lab/alpaca
--- a/examples/llama-3/instruct-dpo-lora-8b.yml
+++ b/examples/llama-3/instruct-dpo-lora-8b.yml
@@ -7,7 +7,6 @@ tokenizer_type: AutoTokenizer

 load_in_8bit: true
 load_in_4bit: false
-strict: false

 chat_template: llama3
 rl: dpo
--- a/examples/llama-3/instruct-lora-8b.yml
+++ b/examples/llama-3/instruct-lora-8b.yml
@@ -7,7 +7,6 @@ tokenizer_type: AutoTokenizer

 load_in_8bit: true
 load_in_4bit: false
-strict: false

 chat_template: llama3
 datasets:
--- a/examples/llama-3/lora-1b-deduplicate-dpo.yml
+++ b/examples/llama-3/lora-1b-deduplicate-dpo.yml
@@ -7,7 +7,6 @@ tokenizer_type: AutoTokenizer

 load_in_8bit: true
 load_in_4bit: false
-strict: false

 chat_template: llama3
 rl: dpo
--- a/examples/llama-3/lora-1b-deduplicate-sft.yml
+++ b/examples/llama-3/lora-1b-deduplicate-sft.yml
@@ -7,7 +7,6 @@ tokenizer_type: AutoTokenizer

 load_in_8bit: true
 load_in_4bit: false
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/llama-3/lora-1b-kernels.yml
+++ b/examples/llama-3/lora-1b-kernels.yml
@@ -1,7 +1,6 @@
 base_model: NousResearch/Llama-3.2-1B
 # Automatically upload checkpoint and final model to HF
 # hub_model_id: username/custom_model_name
-strict: false

 datasets:
  - path: teknium/GPT4-LLM-Cleaned
--- a/examples/llama-3/lora-1b-ray.yml
+++ b/examples/llama-3/lora-1b-ray.yml
@@ -1,7 +1,6 @@
 base_model: NousResearch/Llama-3.2-1B
 # Automatically upload checkpoint and final model to HF
 # hub_model_id: username/custom_model_name
-strict: false

 datasets:
  - path: teknium/GPT4-LLM-Cleaned
--- a/examples/llama-3/lora-1b-sample-packing-sequentially.yml
+++ b/examples/llama-3/lora-1b-sample-packing-sequentially.yml
@@ -7,7 +7,6 @@ tokenizer_type: AutoTokenizer

 load_in_8bit: true
 load_in_4bit: false
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/llama-3/lora-1b.yml
+++ b/examples/llama-3/lora-1b.yml
@@ -1,7 +1,6 @@
 base_model: NousResearch/Llama-3.2-1B
 # Automatically upload checkpoint and final model to HF
 # hub_model_id: username/custom_model_name
-strict: false

 datasets:
  - path: teknium/GPT4-LLM-Cleaned
--- a/examples/llama-3/lora-8b.yml
+++ b/examples/llama-3/lora-8b.yml
@@ -7,7 +7,6 @@ tokenizer_type: AutoTokenizer

 load_in_8bit: true
 load_in_4bit: false
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/llama-3/qlora-1b-kto.yaml
+++ b/examples/llama-3/qlora-1b-kto.yaml
@@ -4,7 +4,6 @@ base_model: meta-llama/Llama-3.2-1B

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 rl: kto
 rl_beta: 0.5
--- a/examples/llama-3/qlora-1b.yml
+++ b/examples/llama-3/qlora-1b.yml
@@ -4,7 +4,6 @@ base_model: NousResearch/Llama-3.2-1B

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 datasets:
  - path: teknium/GPT4-LLM-Cleaned
--- a/examples/llama-3/qlora-fsdp-405b.yaml
+++ b/examples/llama-3/qlora-fsdp-405b.yaml
@@ -5,7 +5,6 @@ tokenizer_type: AutoTokenizer
 # hub_model_id: username/custom_model_name

 load_in_4bit: true
-strict: false

 datasets:
  - path: tatsu-lab/alpaca
--- a/examples/llama-3/qlora-fsdp-70b.yaml
+++ b/examples/llama-3/qlora-fsdp-70b.yaml
@@ -7,7 +7,6 @@ tokenizer_type: AutoTokenizer  # PreTrainedTokenizerFast

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 datasets:
  - path: tatsu-lab/alpaca
--- a/examples/llama-3/qlora.yml
+++ b/examples/llama-3/qlora.yml
@@ -7,7 +7,6 @@ tokenizer_type: AutoTokenizer

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 datasets:
  - path: aaditya/alpaca_subset_1
--- a/examples/llama-4/maverick-qlora-fsdp1.yaml
+++ b/examples/llama-4/maverick-qlora-fsdp1.yaml
@@ -3,7 +3,6 @@ model_type: Llama4ForConditionalGeneration
 # Automatically upload checkpoint and final model to HF
 # hub_model_id: username/custom_model_name

-strict: false

 plugins:
  - axolotl.integrations.liger.LigerPlugin
--- a/examples/llama-4/scout-qlora-fsdp1.yaml
+++ b/examples/llama-4/scout-qlora-fsdp1.yaml
@@ -3,7 +3,6 @@ model_type: Llama4ForConditionalGeneration
  # Automatically upload checkpoint and final model to HF
  # hub_model_id: username/custom_model_name

-strict: false

 # torch_compile: true
 plugins:
--- a/examples/llama-4/scout-qlora-single-h100.yaml
+++ b/examples/llama-4/scout-qlora-single-h100.yaml
@@ -3,7 +3,6 @@ model_type: Llama4ForConditionalGeneration
 # Automatically upload checkpoint and final model to HF
 # hub_model_id: username/custom_model_name

-strict: false

 plugins:
  - axolotl.integrations.liger.LigerPlugin
--- a/examples/llama-4/scout-vision-qlora-fsdp.yaml
+++ b/examples/llama-4/scout-vision-qlora-fsdp.yaml
@@ -4,7 +4,6 @@ processor_type: Llama4Processor
  # Automatically upload checkpoint and final model to HF
  # hub_model_id: username/custom_model_name

-strict: false

 # these 3 lines are needed for now to handle vision chat templates w images
 skip_prepare_dataset: true
--- a/examples/llava/lora-7b.yaml
+++ b/examples/llava/lora-7b.yaml
@@ -1,6 +1,5 @@
 base_model: llava-hf/llava-1.5-7b-hf
 processor_type: AutoProcessor
-strict: false

 # these 3 lines are needed for now to handle vision chat templates w images
 skip_prepare_dataset: true
--- a/examples/mamba/config.yml
+++ b/examples/mamba/config.yml
@@ -5,7 +5,6 @@ tokenizer_type: AutoTokenizer
 tokenizer_config: EleutherAI/gpt-neox-20b
 # Automatically upload checkpoint and final model to HF
 # hub_model_id: username/custom_model_name
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/mistral/bigstral-ds-zero3.yaml
+++ b/examples/mistral/bigstral-ds-zero3.yaml
@@ -6,7 +6,6 @@ tokenizer_type: LlamaTokenizer
 # hub_model_id: username/custom_model_name

 trust_remote_code: true
-strict: false

 unfrozen_parameters:
  - ^lm_head.weight$
--- a/examples/mistral/config.yml
+++ b/examples/mistral/config.yml
@@ -4,7 +4,6 @@ model_type: MistralForCausalLM
 tokenizer_type: LlamaTokenizer
 # Automatically upload checkpoint and final model to HF
 # hub_model_id: username/custom_model_name
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/mistral/lora-mps.yml
+++ b/examples/mistral/lora-mps.yml
@@ -4,7 +4,6 @@ model_type: MistralForCausalLM
 tokenizer_type: LlamaTokenizer
 # Automatically upload checkpoint and final model to HF
 # hub_model_id: username/custom_model_name
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/mistral/lora.yml
+++ b/examples/mistral/lora.yml
@@ -7,7 +7,6 @@ tokenizer_type: LlamaTokenizer

 load_in_8bit: true
 load_in_4bit: false
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/mistral/mistral-dpo-qlora.yml
+++ b/examples/mistral/mistral-dpo-qlora.yml
@@ -12,7 +12,6 @@ tokenizer_type: LlamaTokenizer

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 chat_template: chatml
 rl: dpo
--- a/examples/mistral/mistral-qlora-fsdp.yml
+++ b/examples/mistral/mistral-qlora-fsdp.yml
@@ -9,7 +9,6 @@ trust_remote_code: true

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 datasets:
  - path: tatsu-lab/alpaca
--- a/examples/mistral/mistral-qlora-orpo.yml
+++ b/examples/mistral/mistral-qlora-orpo.yml
@@ -7,7 +7,6 @@ tokenizer_type: LlamaTokenizer

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 rl: orpo
 orpo_alpha: 0.1
--- a/examples/mistral/mistral-small-3.1-24B-lora.yml
+++ b/examples/mistral/mistral-small-3.1-24B-lora.yml
@@ -1,6 +1,5 @@
 base_model: mistralai/Mistral-Small-3.1-24B-Instruct-2503
 processor_type: AutoProcessor
-strict: false

 load_in_8bit: true

--- a/examples/mistral/mixtral-8x22b-qlora-fsdp.yml
+++ b/examples/mistral/mixtral-8x22b-qlora-fsdp.yml
@@ -7,7 +7,6 @@ tokenizer_type: LlamaTokenizer

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 datasets:
  - path: tatsu-lab/alpaca
--- a/examples/mistral/mixtral-qlora-fsdp.yml
+++ b/examples/mistral/mixtral-qlora-fsdp.yml
@@ -9,7 +9,6 @@ trust_remote_code: true

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 datasets:
  - path: tatsu-lab/alpaca
--- a/examples/mistral/mixtral.yml
+++ b/examples/mistral/mixtral.yml
@@ -9,7 +9,6 @@ trust_remote_code: true

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 datasets:
  - path: tatsu-lab/alpaca
--- a/examples/mistral/mixtral_22.yml
+++ b/examples/mistral/mixtral_22.yml
@@ -6,7 +6,6 @@ tokenizer_type: LlamaTokenizer
 # hub_model_id: username/custom_model_name

 trust_remote_code: true
-strict: false

 unfrozen_parameters:
  - ^lm_head.weight$
--- a/examples/mistral/qlora.yml
+++ b/examples/mistral/qlora.yml
@@ -7,7 +7,6 @@ tokenizer_type: LlamaTokenizer

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/openllama-3b/config.yml
+++ b/examples/openllama-3b/config.yml
@@ -4,7 +4,6 @@ model_type: LlamaForCausalLM
 tokenizer_type: LlamaTokenizer
 # Automatically upload checkpoint and final model to HF
 # hub_model_id: username/custom_model_name
-strict: false
 push_dataset_to_hub:
 datasets:
  - path: teknium/GPT4-LLM-Cleaned
--- a/examples/openllama-3b/lora.yml
+++ b/examples/openllama-3b/lora.yml
@@ -7,7 +7,6 @@ tokenizer_type: LlamaTokenizer

 load_in_8bit: true
 load_in_4bit: false
-strict: false
 push_dataset_to_hub:
 datasets:
  - path: teknium/GPT4-LLM-Cleaned
--- a/examples/openllama-3b/qlora.yml
+++ b/examples/openllama-3b/qlora.yml
@@ -7,7 +7,6 @@ tokenizer_type: LlamaTokenizer

 load_in_8bit: false
 load_in_4bit: true
-strict: false
 push_dataset_to_hub:
 datasets:
  - path: teknium/GPT4-LLM-Cleaned
--- a/examples/phi/lora-3.5.yaml
+++ b/examples/phi/lora-3.5.yaml
@@ -7,7 +7,6 @@ tokenizer_type: AutoTokenizer

 load_in_8bit: true
 load_in_4bit: false
-strict: false

 chat_template: phi_3
 datasets:
--- a/examples/phi/phi-ft.yml
+++ b/examples/phi/phi-ft.yml
@@ -4,7 +4,6 @@ model_type: AutoModelForCausalLM
 tokenizer_type: AutoTokenizer
 # Automatically upload checkpoint and final model to HF
 # hub_model_id: username/custom_model_name
-strict: false

 datasets:
  - path: garage-bAInd/Open-Platypus
--- a/examples/phi/phi-qlora.yml
+++ b/examples/phi/phi-qlora.yml
@@ -7,7 +7,6 @@ tokenizer_type: AutoTokenizer

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 datasets:
  - path: garage-bAInd/Open-Platypus
--- a/examples/phi/phi2-ft.yml
+++ b/examples/phi/phi2-ft.yml
@@ -4,7 +4,6 @@ model_type: AutoModelForCausalLM
 tokenizer_type: AutoTokenizer
 # Automatically upload checkpoint and final model to HF
 # hub_model_id: username/custom_model_name
-strict: false

 datasets:
  - path: garage-bAInd/Open-Platypus
--- a/examples/phi/phi3-ft-fsdp.yml
+++ b/examples/phi/phi3-ft-fsdp.yml
@@ -4,7 +4,6 @@ model_type: AutoModelForCausalLM
 tokenizer_type: AutoTokenizer
 # Automatically upload checkpoint and final model to HF
 # hub_model_id: username/custom_model_name
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/phi/phi3-ft.yml
+++ b/examples/phi/phi3-ft.yml
@@ -7,7 +7,6 @@ tokenizer_type: AutoTokenizer
 # hub_model_id: username/custom_model_name

 chat_template: phi_3
-strict: false

 datasets:
  - path: garage-bAInd/Open-Platypus
--- a/examples/pixtral/lora-12b.yml
+++ b/examples/pixtral/lora-12b.yml
@@ -1,6 +1,5 @@
 base_model: mistral-community/pixtral-12b
 processor_type: AutoProcessor
-strict: false

 # these 3 lines are needed for now to handle vision chat templates w images
 skip_prepare_dataset: true
--- a/examples/qwen/lora.yml
+++ b/examples/qwen/lora.yml
@@ -9,7 +9,6 @@ trust_remote_code: true

 load_in_8bit: true
 load_in_4bit: false
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/qwen/qlora.yml
+++ b/examples/qwen/qlora.yml
@@ -9,7 +9,6 @@ trust_remote_code: true

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/qwen/qwen2-moe-lora.yaml
+++ b/examples/qwen/qwen2-moe-lora.yaml
@@ -3,7 +3,6 @@ base_model: Qwen/Qwen1.5-MoE-A2.7B
 # hub_model_id: username/custom_model_name

 trust_remote_code: true
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/qwen/qwen2-moe-qlora.yaml
+++ b/examples/qwen/qwen2-moe-qlora.yaml
@@ -6,7 +6,6 @@ trust_remote_code: true

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/qwen2-vl/lora-7b.yaml
+++ b/examples/qwen2-vl/lora-7b.yaml
@@ -1,6 +1,5 @@
 base_model: Qwen/Qwen2-VL-7B-Instruct
 processor_type: AutoProcessor
-strict: false

 # these 3 lines are needed for now to handle vision chat templates w images
 skip_prepare_dataset: true
--- a/examples/qwen2/dpo.yaml
+++ b/examples/qwen2/dpo.yaml
@@ -2,7 +2,6 @@ base_model: Qwen/Qwen2.5-0.5B
 # Automatically upload checkpoint and final model to HF
 # hub_model_id: username/custom_model_name

-strict: false

 chat_template: qwen_25
 rl: dpo
--- a/examples/qwen2/prm.yaml
+++ b/examples/qwen2/prm.yaml
@@ -5,7 +5,6 @@ num_labels: 2
 tokenizer_type: AutoTokenizer
 # Automatically upload checkpoint and final model to HF
 # hub_model_id: username/custom_model_name
-strict: false

 process_reward_model: true
 chat_template:
--- a/examples/qwen2/qlora-fsdp.yaml
+++ b/examples/qwen2/qlora-fsdp.yaml
@@ -6,7 +6,6 @@ trust_remote_code: true

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 datasets:
  - path: tatsu-lab/alpaca
--- a/examples/qwen2/reward-model.yaml
+++ b/examples/qwen2/reward-model.yaml
@@ -5,7 +5,6 @@ num_labels: 1
 tokenizer_type: AutoTokenizer
 # Automatically upload checkpoint and final model to HF
 # hub_model_id: username/custom_model_name
-strict: false

 reward_model: true
 chat_template: qwen_25
--- a/examples/stablelm-2/1.6b/fft.yml
+++ b/examples/stablelm-2/1.6b/fft.yml
@@ -6,7 +6,6 @@ tokenizer_type: AutoTokenizer
 # hub_model_id: username/custom_model_name

 trust_remote_code: true
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/stablelm-2/1.6b/lora.yml
+++ b/examples/stablelm-2/1.6b/lora.yml
@@ -9,7 +9,6 @@ trust_remote_code: true

 load_in_8bit: true
 load_in_4bit: false
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/starcoder2/qlora.yml
+++ b/examples/starcoder2/qlora.yml
@@ -4,7 +4,6 @@ base_model: bigcode/starcoder2-3b

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/tiny-llama/lora-mps.yml
+++ b/examples/tiny-llama/lora-mps.yml
@@ -7,7 +7,6 @@ tokenizer_type: LlamaTokenizer

 load_in_8bit: true
 load_in_4bit: false
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/tiny-llama/lora.yml
+++ b/examples/tiny-llama/lora.yml
@@ -6,7 +6,6 @@ tokenizer_type: AutoTokenizer

 load_in_8bit: true
 load_in_4bit: false
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/tiny-llama/pretrain.yml
+++ b/examples/tiny-llama/pretrain.yml
@@ -4,7 +4,6 @@ model_type: LlamaForCausalLM
 tokenizer_type: LlamaTokenizer
 # Automatically upload checkpoint and final model to HF
 # hub_model_id: username/custom_model_name
-strict: false

 max_steps: 200
 pretraining_dataset:
--- a/examples/tiny-llama/qlora.yml
+++ b/examples/tiny-llama/qlora.yml
@@ -7,7 +7,6 @@ tokenizer_type: LlamaTokenizer

 load_in_8bit: false
 load_in_4bit: true
-strict: false

 datasets:
  - path: mhenrichsen/alpaca_2k_test
--- a/examples/xgen-7b/xgen-7b-8k-qlora.yml
+++ b/examples/xgen-7b/xgen-7b-8k-qlora.yml
@@ -13,7 +13,6 @@ load_in_8bit: false
 # enable 4bit for QLoRA
 load_in_4bit: true
 gptq: false
-strict: false
 push_dataset_to_hub:
 datasets:
  - path: timdettmers/openassistant-guanaco
--- a/examples/yi-34B-chat/qlora.yml
+++ b/examples/yi-34B-chat/qlora.yml
@@ -7,7 +7,6 @@ tokenizer_type: LlamaTokenizer

 load_in_8bit: false
 load_in_4bit: true
-strict: false
 sequence_len: 1024
 bf16: auto
 tf32: false