mmarch/text-generation-webui
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Bump llama-cpp-python to 0.2.18 (2nd attempt) (#4637)

Browse source 
* Update requirements*.txt

* Add back seed
This commit is contained in:
oobabooga 2023-11-18 00:31:27 -03:00 • committed by GitHub
parent 9d6f79db74
commit e0ca49ed9c
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
15 changed files with 108 additions and 116 deletions
Download patch file Download diff file Expand all files Collapse all files

11
modules/llamacpp_hf.py
View file

@ -39,7 +39,7 @@ class LlamacppHF(PreTrainedModel):
'n_tokens': self.model.n_tokens,
'input_ids': self.model.input_ids,
'scores': self.model.scores,
'ctx': self.model.ctx
'ctx': self.model._ctx
}
if shared.args.cfg_cache:
@ -65,7 +65,7 @@ class LlamacppHF(PreTrainedModel):
'n_tokens': self.model.n_tokens,
'input_ids': self.model.input_ids,
'scores': self.model.scores,
'ctx': self.model.ctx
'ctx': self.model._ctx
})
def save_negative_cache(self):
@ -73,20 +73,20 @@ class LlamacppHF(PreTrainedModel):
'n_tokens': self.model.n_tokens,
'input_ids': self.model.input_ids,
'scores': self.model.scores,
'ctx': self.model.ctx
'ctx': self.model._ctx
})
def load_cache(self):
self.model.n_tokens = self.llamacpp_cache['n_tokens']
self.model.input_ids = self.llamacpp_cache['input_ids']
self.model.scores = self.llamacpp_cache['scores']
self.model.ctx = self.llamacpp_cache['ctx']
self.model._ctx = self.llamacpp_cache['ctx']
def load_negative_cache(self):
self.model.n_tokens = self.llamacpp_cache_negative['n_tokens']
self.model.input_ids = self.llamacpp_cache_negative['input_ids']
self.model.scores = self.llamacpp_cache_negative['scores']
self.model.ctx = self.llamacpp_cache_negative['ctx']
self.model._ctx = self.llamacpp_cache_negative['ctx']
@property
def device(self) -> torch.device:
@ -192,7 +192,6 @@ class LlamacppHF(PreTrainedModel):
params = {
'model_path': str(model_file),
'n_ctx': shared.args.n_ctx,
'seed': int(shared.args.llama_cpp_seed),
'n_threads': shared.args.threads or None,
'n_threads_batch': shared.args.threads_batch or None,
'n_batch': shared.args.n_batch,