From 0d6e52b5c7723ed5c78b54c9a6eb67a1997f6038 Mon Sep 17 00:00:00 2001 From: Daniel Han Date: Fri, 19 Jan 2024 22:57:22 +1100 Subject: [PATCH] getattr issues (#103) * Fix tokenizer, dropout, bias for LoRA * Update loader.py * Fix LoRA downcasting * Update _utils.py * Saving to GGUF * fix * colab_quantize_to_gguf * move save modules * save module * Update __init__.py * Update save.py * Temp downgrade due to TRL issue * Fix up bugs * Faster saving + other changes * Update llama.py * Saving modules * spelling * Update llama.py * Update save.py * Update save.py * Update loader.py * Update llama.py * patch saving * Update save.py * Update save.py * Update save.py * patch saving * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * original_model * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * Update save.py * saving to RAM leakage? * Update save.py * new_save_directory * Update save.py * Update save.py * Update save.py * Update save.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Quick fixes * Update llama.py * Update llama.py * Update dpo.py * Update dpo.py * Update llama.py * Update save.py * getattr --- unsloth/models/llama.py | 2 +- unsloth/models/mistral.py | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py index 38b8f55d11..06b78d77c5 100644 --- a/unsloth/models/llama.py +++ b/unsloth/models/llama.py @@ -460,7 +460,7 @@ def LlamaModel_fast_forward( (batch_size, seq_length), inputs_embeds, past_key_values_length, - sliding_window = getattr(self.config, "sliding_window"), + sliding_window = getattr(self.config, "sliding_window", None), ) pass diff --git a/unsloth/models/mistral.py b/unsloth/models/mistral.py index eb9d10513f..2c85129010 100644 --- a/unsloth/models/mistral.py +++ b/unsloth/models/mistral.py @@ -131,7 +131,7 @@ def MistralAttention_fast_forward( Q = Q.transpose(1, 2) K = K.transpose(1, 2) V = V.transpose(1, 2) - sw = getattr(self.config, "sliding_window") + sw = getattr(self.config, "sliding_window", None) sw = q_len if sw is None else sw window = (-1, -1) if (q_len <= sw) else (sw, sw) A = flash_attn_func(Q, K, V, causal = True, window_size = window) @@ -175,7 +175,7 @@ def MistralForCausalLM_fast_forward( if causal_mask is None: bsz, q_len = input_ids.shape - sliding_window = getattr(self.config, "sliding_window") + sliding_window = getattr(self.config, "sliding_window", None) if sliding_window is None or sliding_window <= 0: causal_mask = xformers.attn_bias.LowerTriangularMask() elif q_len <= sliding_window: