books/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2026-04-10 12:33:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

Make quote style consistent (#891)

Browse Source
This commit is contained in:
Sebastian Raschka
2025-10-21 19:42:33 -05:00
committed by GitHub
parent 9276edbc37
commit 7ca7c47e4a
24 changed files with 239 additions and 81 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
pkg/llms_from_scratch/ch05.py
View File

@@ -30,7 +30,7 @@ def generate(model, idx, max_new_tokens, context_size, temperature=0.0, top_k=No
# Keep only top_k values
top_logits, _ = torch.topk(logits, top_k)
min_val = top_logits[:, -1]
logits = torch.where(logits < min_val, torch.tensor(float('-inf')).to(logits.device), logits)
logits = torch.where(logits < min_val, torch.tensor(float("-inf")).to(logits.device), logits)
# New: Apply temperature scaling
if temperature > 0.0:
@@ -125,8 +125,8 @@ def assign(left, right):
def load_weights_into_gpt(gpt, params):
gpt.pos_emb.weight = assign(gpt.pos_emb.weight, params['wpe'])
gpt.tok_emb.weight = assign(gpt.tok_emb.weight, params['wte'])
gpt.pos_emb.weight = assign(gpt.pos_emb.weight, params["wpe"])
gpt.tok_emb.weight = assign(gpt.tok_emb.weight, params["wte"])
for b in range(len(params["blocks"])):
q_w, k_w, v_w = np.split(