From 70637b41701bee4763da11ac2f30c0461564c152 Mon Sep 17 00:00:00 2001
From: OlivierDehaene <23298448+OlivierDehaene@users.noreply.github.com>
Date: Wed, 5 Apr 2023 17:18:16 +0200
Subject: [PATCH] use all tokens

---
 server/text_generation_server/models/flash_causal_lm.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/server/text_generation_server/models/flash_causal_lm.py b/server/text_generation_server/models/flash_causal_lm.py
index 61ebe3ec..c8934547 100644
--- a/server/text_generation_server/models/flash_causal_lm.py
+++ b/server/text_generation_server/models/flash_causal_lm.py
@@ -355,7 +355,7 @@ class FlashCausalLM(Model):
             # Generated token
             next_token_logprob = logprobs[-1, next_token_id_item]
             next_token_text, offset, token_offset = self.decode_token(
-                all_input_ids[-(stopping_criteria.current_tokens + 1) :],
+                all_input_ids,
                 offset,
                 token_offset,
             )