diff --git a/ch05/01_main-chapter-code/ch05.ipynb b/ch05/01_main-chapter-code/ch05.ipynb index 7a0a3f2..b12efad 100644 --- a/ch05/01_main-chapter-code/ch05.ipynb +++ b/ch05/01_main-chapter-code/ch05.ipynb @@ -1852,7 +1852,7 @@ "metadata": {}, "outputs": [], "source": [ - "def generate(model, idx, max_new_tokens, context_size, temperature, top_k=None, eos_id=None):\n", + "def generate(model, idx, max_new_tokens, context_size, temperature=1.0, top_k=None, eos_id=None):\n", "\n", " # For-loop is the same as before: Get logits, and only focus on last time step\n", " for _ in range(max_new_tokens):\n", diff --git a/ch05/02_alternative_weight_loading/previous_chapters.py b/ch05/02_alternative_weight_loading/previous_chapters.py index 0c792ba..ba15ef8 100644 --- a/ch05/02_alternative_weight_loading/previous_chapters.py +++ b/ch05/02_alternative_weight_loading/previous_chapters.py @@ -254,7 +254,7 @@ def token_ids_to_text(token_ids, tokenizer): return tokenizer.decode(flat.tolist()) -def generate(model, idx, max_new_tokens, context_size, temperature, top_k=None, eos_id=None): +def generate(model, idx, max_new_tokens, context_size, temperature=1.0, top_k=None, eos_id=None): # For-loop is the same as before: Get logits, and only focus on last time step for _ in range(max_new_tokens): diff --git a/ch06/02_bonus_additional-experiments/previous_chapters.py b/ch06/02_bonus_additional-experiments/previous_chapters.py index bcc8684..862fe0b 100644 --- a/ch06/02_bonus_additional-experiments/previous_chapters.py +++ b/ch06/02_bonus_additional-experiments/previous_chapters.py @@ -316,7 +316,7 @@ def load_weights_into_gpt(gpt, params): gpt.out_head.weight = assign(gpt.out_head.weight, params["wte"]) -def generate(model, idx, max_new_tokens, context_size, temperature, top_k=None, eos_id=None): +def generate(model, idx, max_new_tokens, context_size, temperature=1.0, top_k=None, eos_id=None): # For-loop is the same as before: Get logits, and only focus on last time step for _ in range(max_new_tokens): idx_cond = idx[:, -context_size:]