if not isinstance(self.data_type, QuantizedDataType):
raise Exception(f"Can't turn an unquantized tensor into a quantized type ({data_type})")
if self.data_type.have_g_idx:
- sys.stderr.write("Error: Input uses the newer GPTQ-for-LLaMa format (using g_idx), which is not yet natively supported by GGML. For now you can still convert this model by passing `--outtype f16` to dequantize, but that will result in a much larger output file for no quality benefit.\n")
+ sys.stderr.write(
+ "Error: Input uses the newer GPTQ-for-LLaMa format (using g_idx), "
+ "which is not yet natively supported by GGML. "
+ "For now you can still convert this model by passing `--outtype f16` to dequantize, "
+ "but that will result in a much larger output file for no quality benefit.\n")
sys.exit(1)
assert not data_type.have_g_idx and self.data_type.have_addends and data_type.have_addends
description = f'storage data_type={data_type} path-in-zip={filename} path={self.zip_file.filename}'
return LazyStorage(load=load, kind=pid[1], description=description)
- # @staticmethod
- def lazy_rebuild_tensor_v2(storage: Any, storage_offset: Any, size: Any, stride: Any, # pyright: ignore[reportSelfClsParameterName]
+ # @staticmethod
+ def lazy_rebuild_tensor_v2(storage: Any, storage_offset: Any, size: Any, stride: Any,
+ # pyright: ignore[reportSelfClsParameterName]
requires_grad: Any, backward_hooks: Any, metadata: Any = None) -> LazyTensor:
assert isinstance(storage, LazyStorage)
# Use mmap for the actual data to avoid race conditions with the file offset.
off = fp.raw.tell()
mapped = memoryview(mmap.mmap(fp.fileno(), 0, access=mmap.ACCESS_READ))
- fp.raw.seek(off) # needed on Windows
+ fp.raw.seek(off) # needed on Windows
def read_tensor() -> None: # this is a function so that variables captured in `load` don't change
shape_len, name_len, ftype = struct.unpack("iii", must_read(fp, 12))
files = list(path.glob("model-00001-of-*.safetensors"))
if not files:
# Try the PyTorch patterns too, with lower priority
- globs = ["consolidated.00.pth", "pytorch_model-00001-of-*.bin", "*.pt", "pytorch_model.bin" ]
+ globs = ["consolidated.00.pth", "pytorch_model-00001-of-*.bin", "*.pt", "pytorch_model.bin"]
files = [file for glob in globs for file in path.glob(glob)]
if not files:
# Try GGML too, but with lower priority, since if both a non-GGML
elif path3.exists():
path = path3
else:
- raise FileNotFoundError(f"Could not find tokenizer.model in {path} or its parent; if it's in another directory, pass the directory as --vocab-dir")
+ raise FileNotFoundError(
+ f"Could not find tokenizer.model in {path} or its parent; "
+ "if it's in another directory, pass the directory as --vocab-dir")
added_tokens_path = path.parent / "added_tokens.json"
print(f"Loading vocab file {path}")
return SentencePieceVocab(path, added_tokens_path if added_tokens_path.exists() else None)
}[params.file_type]
ret = model_paths[0].parent / f"ggml-model-{namestr}.bin"
if ret in model_paths:
- sys.stderr.write(f"Error: Default output path ({ret}) would overwrite the input. Please explicitly specify a path using --outfile.\n")
+ sys.stderr.write(
+ f"Error: Default output path ({ret}) would overwrite the input. "
+ "Please explicitly specify a path using --outfile.\n")
sys.exit(1)
return ret
parser.add_argument("--outtype", choices=["f32", "f16", "q4_1", "q4_0"], help="output format (default: based on input)")
parser.add_argument("--vocab-dir", type=Path, help="directory containing tokenizer.model, if separate from model file")
parser.add_argument("--outfile", type=Path, help="path to write to; default: based on input")
- parser.add_argument("model", type=Path, help="directory containing model file, or model file itself (*.pth, *.pt, *.bin)")
+ parser.add_argument("model", type=Path,
+ help="directory containing model file, or model file itself (*.pth, *.pt, *.bin)")
args = parser.parse_args(args_in)
vocab: Vocab
import matplotlib.pyplot as plt
-import sys, os
+import os
import csv
labels = []
rows = []
+
def bar_chart(numbers, labels, pos):
plt.bar(pos, numbers, color='blue')
plt.xticks(ticks=pos, labels=labels)
plt.ylabel("Questions Correct")
plt.show()
+
def calculatecorrect():
directory = os.fsencode("./examples/jeopardy/results/")
csv_reader = csv.reader(open("./examples/jeopardy/qasheet.csv", 'rt'), delimiter=',')
print(line)
else:
print("Correct answer: " + rows[i][2] + "\n")
- i+=1
+ i += 1
print("Did the AI get the question right? (y/n)")
if input() == "y":
totalcorrect += 1
numbers.append(totalcorrect)
-
if __name__ == '__main__':
calculatecorrect()
pos = list(range(numEntries))
overview / pkg / ggml / sources / llama.cpp / commitdiff