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

py : cleanup the code

Browse source 
- use f-strings where possible
- drop first param of encode/decode functions since "utf-8" is the default
This commit is contained in:
Pavol Rusnak 2023-03-29 21:31:24 +02:00
parent 9733104be5
commit cbef542879
6 changed files with 27 additions and 29 deletions
Download patch file Download diff file Expand all files Collapse all files

14
convert-gptq-to-ggml.py
View file

@ -50,7 +50,7 @@ fout.write(struct.pack("i", 4))
# This loop unchanged from convert-pth-to-ggml.py:
for i in range(tokenizer.vocab_size()):
if tokenizer.is_unknown(i):
text = " \u2047 ".encode("utf-8")
text = " \u2047 ".encode()
elif tokenizer.is_control(i):
text = b""
elif tokenizer.is_byte(i):
@ -61,13 +61,13 @@ for i in range(tokenizer.vocab_size()):
byte_value = int(piece[3:-1], 16)
text = struct.pack("B", byte_value)
else:
text = tokenizer.id_to_piece(i).replace("\u2581", " ").encode("utf-8")
text = tokenizer.id_to_piece(i).replace("\u2581", " ").encode()
fout.write(struct.pack("i", len(text)))
fout.write(text)
fout.write(struct.pack("f", tokenizer.get_score(i)))
def write_header(shape, dst_name, ftype_cur):
sname = dst_name.encode('utf-8')
sname = dst_name.encode()
fout.write(struct.pack("iii", len(shape), len(sname), ftype_cur))
fout.write(struct.pack("i" * len(shape), *shape[::-1]))
fout.write(sname)
@ -80,7 +80,7 @@ def write_header(shape, dst_name, ftype_cur):
def convert_non_q4(src_name, dst_name):
v = model[src_name]
shape = v.shape
print("Processing non-Q4 variable: " + src_name + " with shape: ", shape, " and type: ", v.dtype)
print(f"Processing non-Q4 variable: {src_name} with shape: {shape} and type: {v.dtype}")
if len(shape) == 1:
print(" Converting to float32")
v = v.to(torch.float32)
@ -105,7 +105,7 @@ def convert_q4(src_name, dst_name, permute=False):
# Each int32 item is actually 8 int4 items packed together, and it's transposed.
shape = (qweight.shape[0], qweight.shape[1] * 8)
print("Processing Q4 variable: " + src_name + " with shape: ", shape)
print(f"Processing Q4 variable: {src_name} with shape: {shape}")
# The output format has the int4 weights in groups of 32 rather than 8.
# It looks like this:
@ -168,5 +168,5 @@ for i in range(n_layer):
fout.close()
print("Done. Output file: " + fname_out)
print("")
print(f"Done. Output file: {fname_out}")
print()