baalajimaestro/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Merge pull request #87 from SagsMug/main

Browse source 
Fix TypeError in low_level chat
This commit is contained in:
Andrei 2023-04-18 02:11:40 -04:00 committed by GitHub
commit 4ce6670bbd
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 8 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
examples/low_level_api/common.py
View file

@ -75,7 +75,7 @@ def gpt_params_parse(argv = None, params: Optional[GptParams] = None):
parser.add_argument("--top_p", type=float, default=0.95, help="top-p samplin",dest="top_p")
parser.add_argument("--top_k", type=int, default=40, help="top-k sampling",dest="top_k")
parser.add_argument("--temp", type=float, default=0.80, help="temperature",dest="temp")
parser.add_argument("--n_predict", type=int, default=128, help="number of model parts",dest="n_predict")
parser.add_argument("--n_predict", type=int, default=128, help="number of tokens to predict (-1 = infinity)",dest="n_predict")
parser.add_argument("--repeat_last_n", type=int, default=64, help="last n tokens to consider for penalize ",dest="repeat_last_n")
parser.add_argument("--repeat_penalty", type=float, default=1.10, help="penalize repeat sequence of tokens",dest="repeat_penalty")
parser.add_argument("-b", "--batch_size", type=int, default=8, help="batch size for prompt processing",dest="n_batch")

11
examples/low_level_api/low_level_api_chat_cpp.py
View file

@ -144,6 +144,7 @@ specified) expect poor results""", file=sys.stderr)
# determine newline token
self.llama_token_newline = self._tokenize("\n", False)
self.llama_token_eot = self._tokenize(" [end of text]\n", False)
if (self.params.verbose_prompt):
print(f"""
@ -203,16 +204,16 @@ n_keep = {self.params.n_keep}
_n = llama_cpp.llama_tokenize(self.ctx, prompt.encode("utf8"), _arr, len(_arr), bos)
return _arr[:_n]
def use_antiprompt(self):
return len(self.first_antiprompt) > 0
def set_color(self, c):
if (self.params.use_color):
print(c, end="")
def use_antiprompt(self):
return len(self.first_antiprompt) > 0
# generate tokens
def generate(self):
while self.remaining_tokens > 0 or self.params.interactive:
while self.remaining_tokens > 0 or self.params.interactive or self.params.n_predict == -1:
# predict
if len(self.embd) > 0:
# infinite text generation via context swapping
@ -313,7 +314,7 @@ n_keep = {self.params.n_keep}
# end of text token
if len(self.embd) > 0 and self.embd[-1] == llama_cpp.llama_token_eos():
if (not self.params.instruct):
for i in " [end of text]\n":
for i in self.llama_token_eot:
yield i
break