github/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2025-06-19 20:24:41 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: multi-turn data breaks

Browse Source
This commit is contained in:
Zach Nussbaum 2023-04-12 03:51:29 +00:00
parent 15f7c5b68f
commit 8a94a8c068
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
data.py
View File

@ -15,8 +15,8 @@ def tokenize_inputs(config, tokenizer, examples):
out = {"labels": [], "input_ids": []}
for prompt, response in zip(examples["prompt"], examples["response"]):
if different_eos:
if response.count("</s>") > 0:
response = response.replace("</s>", tokenizer.eos_token)
if response.count("</s> \n") > 0:
response = response.replace("</s> \n", f"{tokenizer.eos_token} \n")
prompt_len = len(tokenizer(prompt + "\n", return_tensors="pt")["input_ids"][0])