Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
4 changes: 2 additions & 2 deletions nb/CodeForces-cot-Finetune_for_Reasoning_on_CodeForces.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -253,8 +253,8 @@
" # [NEW] \"unsloth\" uses 30% less VRAM, fits 2x larger batch sizes!\n",
" use_gradient_checkpointing = \"unsloth\", # True or \"unsloth\" for very long context\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
")"
]
},
Expand Down
4 changes: 2 additions & 2 deletions nb/CodeGemma_(7B)-Conversational.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -153,8 +153,8 @@
" bias = \"none\", # Supports any, but = \"none\" is optimized\n",
" use_gradient_checkpointing = \"unsloth\", # True or \"unsloth\" for very long context\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
")"
]
},
Expand Down
4 changes: 2 additions & 2 deletions nb/Deepseek_OCR_(3B)-Eval.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -541,8 +541,8 @@
" lora_dropout = 0,\n",
" bias = \"none\",\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
" # target_modules = \"all-linear\", # Optional now! Can specify a list if needed\n",
")"
]
Expand Down
4 changes: 2 additions & 2 deletions nb/Deepseek_OCR_(3B)-Evaluation.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -694,8 +694,8 @@
" lora_dropout = 0,\n",
" bias = \"none\",\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
" # target_modules = \"all-linear\", # Optional now! Can specify a list if needed\n",
")"
]
Expand Down
4 changes: 2 additions & 2 deletions nb/Deepseek_OCR_(3B).ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -541,8 +541,8 @@
" lora_dropout = 0,\n",
" bias = \"none\",\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
" # target_modules = \"all-linear\", # Optional now! Can specify a list if needed\n",
")"
]
Expand Down
4 changes: 2 additions & 2 deletions nb/ERNIE_4_5_21B_A3B_PT-Conversational.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -618,8 +618,8 @@
" # [NEW] \"unsloth\" uses 30% less VRAM, fits 2x larger batch sizes!\n",
" use_gradient_checkpointing = \"unsloth\", # True or \"unsloth\" for very long context\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
")"
]
},
Expand Down
2 changes: 1 addition & 1 deletion nb/ERNIE_4_5_VL_28B_A3B_PT_Vision.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -875,7 +875,7 @@
" lora_dropout = 0,\n",
" bias = \"none\",\n",
" random_state = 3407,\n",
" use_rslora = False,\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" target_modules = [\n",
" \"q_proj\", \"k_proj\", \"v_proj\", \"o_proj\",\n",
" \"gate_proj\", \"up_proj\", \"down_proj\",\n",
Expand Down
4 changes: 2 additions & 2 deletions nb/Gemma2_(2B)-Alpaca.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -314,8 +314,8 @@
" # [NEW] \"unsloth\" uses 30% less VRAM, fits 2x larger batch sizes!\n",
" use_gradient_checkpointing = \"unsloth\", # True or \"unsloth\" for very long context\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
")"
]
},
Expand Down
4 changes: 2 additions & 2 deletions nb/Gemma2_(9B)-Alpaca.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -343,8 +343,8 @@
" # [NEW] \"unsloth\" uses 30% less VRAM, fits 2x larger batch sizes!\n",
" use_gradient_checkpointing = \"unsloth\", # True or \"unsloth\" for very long context\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
")"
]
},
Expand Down
4 changes: 2 additions & 2 deletions nb/Gemma3N_(4B)-Audio.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -416,8 +416,8 @@
" lora_dropout = 0,\n",
" bias = \"none\",\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
" target_modules = [\n",
" \"q_proj\", \"k_proj\", \"v_proj\", \"o_proj\",\n",
" \"gate_proj\", \"up_proj\", \"down_proj\",\n",
Expand Down
4 changes: 2 additions & 2 deletions nb/Gemma3N_(4B)-Vision.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -474,8 +474,8 @@
" lora_dropout = 0,\n",
" bias = \"none\",\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
" target_modules = \"all-linear\", # Optional now! Can specify a list if needed\n",
")"
]
Expand Down
4 changes: 2 additions & 2 deletions nb/Gemma3_(270M).ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -364,8 +364,8 @@
" # [NEW] \"unsloth\" uses 30% less VRAM, fits 2x larger batch sizes!\n",
" use_gradient_checkpointing = \"unsloth\", # True or \"unsloth\" for very long context\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
")"
]
},
Expand Down
4 changes: 2 additions & 2 deletions nb/Gemma3_(4B)-Vision-GRPO.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -448,8 +448,8 @@
" lora_dropout = 0,\n",
" bias = \"none\",\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
" use_gradient_checkpointing = \"unsloth\", # Reduces memory usage\n",
" # target_modules = \"all-linear\", # Optional now! Can specify a list if needed\n",
")"
Expand Down
4 changes: 2 additions & 2 deletions nb/Gemma3_(4B)-Vision.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -396,8 +396,8 @@
" lora_dropout = 0,\n",
" bias = \"none\",\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
" target_modules = \"all-linear\", # Optional now! Can specify a list if needed\n",
")"
]
Expand Down
4 changes: 2 additions & 2 deletions nb/Granite4.0.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -196,8 +196,8 @@
" # [NEW] \"unsloth\" uses 30% less VRAM, fits 2x larger batch sizes!\n",
" use_gradient_checkpointing = \"unsloth\", # True or \"unsloth\" for very long context\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
")"
]
},
Expand Down
4 changes: 2 additions & 2 deletions nb/Granite4.0_350M.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -366,8 +366,8 @@
" # [NEW] \"unsloth\" uses 30% less VRAM, fits 2x larger batch sizes!\n",
" use_gradient_checkpointing = \"unsloth\", # True or \"unsloth\" for very long context\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
")"
]
},
Expand Down
4 changes: 2 additions & 2 deletions nb/HuggingFace Course-Gemma3_(4B)-Vision-GRPO.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -450,8 +450,8 @@
" lora_dropout = 0,\n",
" bias = \"none\",\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
" use_gradient_checkpointing = \"unsloth\", # Reduces memory usage\n",
" # target_modules = \"all-linear\", # Optional now! Can specify a list if needed\n",
")"
Expand Down
4 changes: 2 additions & 2 deletions nb/HuggingFace Course-Qwen2_5_7B_VL_GRPO.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -619,8 +619,8 @@
" lora_dropout = 0,\n",
" bias = \"none\",\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
" use_gradient_checkpointing = \"unsloth\", # Reduces memory usage\n",
" # target_modules = \"all-linear\", # Optional now! Can specify a list if needed\n",
")"
Expand Down
4 changes: 2 additions & 2 deletions nb/HuggingFace Course-Qwen3_VL_(8B)-Vision-GRPO.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -558,8 +558,8 @@
" lora_dropout = 0,\n",
" bias = \"none\",\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
" use_gradient_checkpointing = \"unsloth\", # Reduces memory usage\n",
" # target_modules = \"all-linear\", # Optional now! Can specify a list if needed\n",
")"
Expand Down
4 changes: 2 additions & 2 deletions nb/HuggingFace Course-gpt-oss-(20B)_A100-GRPO.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -765,8 +765,8 @@
" # [NEW] \"unsloth\" uses 30% less VRAM, fits 2x larger batch sizes!\n",
" use_gradient_checkpointing = \"unsloth\", # True or \"unsloth\" for very long context\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
")"
]
},
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -253,8 +253,8 @@
" # [NEW] \"unsloth\" uses 30% less VRAM, fits 2x larger batch sizes!\n",
" use_gradient_checkpointing = \"unsloth\", # True or \"unsloth\" for very long context\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
")"
]
},
Expand Down
4 changes: 2 additions & 2 deletions nb/Kaggle-CodeGemma_(7B)-Conversational.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -153,8 +153,8 @@
" bias = \"none\", # Supports any, but = \"none\" is optimized\n",
" use_gradient_checkpointing = \"unsloth\", # True or \"unsloth\" for very long context\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
")"
]
},
Expand Down
4 changes: 2 additions & 2 deletions nb/Kaggle-Deepseek_OCR_(3B)-Eval.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -541,8 +541,8 @@
" lora_dropout = 0,\n",
" bias = \"none\",\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
" # target_modules = \"all-linear\", # Optional now! Can specify a list if needed\n",
")"
]
Expand Down
4 changes: 2 additions & 2 deletions nb/Kaggle-Deepseek_OCR_(3B)-Evaluation.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -694,8 +694,8 @@
" lora_dropout = 0,\n",
" bias = \"none\",\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
" # target_modules = \"all-linear\", # Optional now! Can specify a list if needed\n",
")"
]
Expand Down
4 changes: 2 additions & 2 deletions nb/Kaggle-Deepseek_OCR_(3B).ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -541,8 +541,8 @@
" lora_dropout = 0,\n",
" bias = \"none\",\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
" # target_modules = \"all-linear\", # Optional now! Can specify a list if needed\n",
")"
]
Expand Down
4 changes: 2 additions & 2 deletions nb/Kaggle-ERNIE_4_5_21B_A3B_PT-Conversational.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -618,8 +618,8 @@
" # [NEW] \"unsloth\" uses 30% less VRAM, fits 2x larger batch sizes!\n",
" use_gradient_checkpointing = \"unsloth\", # True or \"unsloth\" for very long context\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
")"
]
},
Expand Down
2 changes: 1 addition & 1 deletion nb/Kaggle-ERNIE_4_5_VL_28B_A3B_PT_Vision.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -875,7 +875,7 @@
" lora_dropout = 0,\n",
" bias = \"none\",\n",
" random_state = 3407,\n",
" use_rslora = False,\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" target_modules = [\n",
" \"q_proj\", \"k_proj\", \"v_proj\", \"o_proj\",\n",
" \"gate_proj\", \"up_proj\", \"down_proj\",\n",
Expand Down
4 changes: 2 additions & 2 deletions nb/Kaggle-Gemma2_(2B)-Alpaca.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -314,8 +314,8 @@
" # [NEW] \"unsloth\" uses 30% less VRAM, fits 2x larger batch sizes!\n",
" use_gradient_checkpointing = \"unsloth\", # True or \"unsloth\" for very long context\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
")"
]
},
Expand Down
4 changes: 2 additions & 2 deletions nb/Kaggle-Gemma2_(9B)-Alpaca.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -343,8 +343,8 @@
" # [NEW] \"unsloth\" uses 30% less VRAM, fits 2x larger batch sizes!\n",
" use_gradient_checkpointing = \"unsloth\", # True or \"unsloth\" for very long context\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
")"
]
},
Expand Down
4 changes: 2 additions & 2 deletions nb/Kaggle-Gemma3N_(4B)-Audio.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -416,8 +416,8 @@
" lora_dropout = 0,\n",
" bias = \"none\",\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
" target_modules = [\n",
" \"q_proj\", \"k_proj\", \"v_proj\", \"o_proj\",\n",
" \"gate_proj\", \"up_proj\", \"down_proj\",\n",
Expand Down
4 changes: 2 additions & 2 deletions nb/Kaggle-Gemma3N_(4B)-Vision.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -474,8 +474,8 @@
" lora_dropout = 0,\n",
" bias = \"none\",\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
" target_modules = \"all-linear\", # Optional now! Can specify a list if needed\n",
")"
]
Expand Down
4 changes: 2 additions & 2 deletions nb/Kaggle-Gemma3_(270M).ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -364,8 +364,8 @@
" # [NEW] \"unsloth\" uses 30% less VRAM, fits 2x larger batch sizes!\n",
" use_gradient_checkpointing = \"unsloth\", # True or \"unsloth\" for very long context\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
")"
]
},
Expand Down
4 changes: 2 additions & 2 deletions nb/Kaggle-Gemma3_(4B)-Vision-GRPO.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -441,8 +441,8 @@
" lora_dropout = 0,\n",
" bias = \"none\",\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
" use_gradient_checkpointing = \"unsloth\", # Reduces memory usage\n",
" # target_modules = \"all-linear\", # Optional now! Can specify a list if needed\n",
")"
Expand Down
4 changes: 2 additions & 2 deletions nb/Kaggle-Gemma3_(4B)-Vision.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -396,8 +396,8 @@
" lora_dropout = 0,\n",
" bias = \"none\",\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
" target_modules = \"all-linear\", # Optional now! Can specify a list if needed\n",
")"
]
Expand Down
4 changes: 2 additions & 2 deletions nb/Kaggle-Granite4.0.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -196,8 +196,8 @@
" # [NEW] \"unsloth\" uses 30% less VRAM, fits 2x larger batch sizes!\n",
" use_gradient_checkpointing = \"unsloth\", # True or \"unsloth\" for very long context\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
")"
]
},
Expand Down
4 changes: 2 additions & 2 deletions nb/Kaggle-Granite4.0_350M.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -366,8 +366,8 @@
" # [NEW] \"unsloth\" uses 30% less VRAM, fits 2x larger batch sizes!\n",
" use_gradient_checkpointing = \"unsloth\", # True or \"unsloth\" for very long context\n",
" random_state = 3407,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
" use_rslora = False, # rsLoRA: For correct scaling, set alpha ~ sqrt(r) if True.\n",
" loftq_config = None, # We support LoftQ\n",
")"
]
},
Expand Down
Loading