summaryrefslogtreecommitdiff
path: root/convert-gptq-to-ggml.py
diff options
context:
space:
mode:
authorPavol Rusnak <pavol@rusnak.io>2023-03-29 21:31:24 +0200
committerPavol Rusnak <pavol@rusnak.io>2023-03-31 10:32:01 +0200
commitcbef542879962fdc491656cd0c8cadd65a5f1356 (patch)
treeba31f66c0613411466b31c822fb5bac2b24c910a /convert-gptq-to-ggml.py
parent9733104be5389ebb1ff05095eca2a70280cd875a (diff)
py : cleanup the code
- use f-strings where possible - drop first param of encode/decode functions since "utf-8" is the default
Diffstat (limited to 'convert-gptq-to-ggml.py')
-rw-r--r--convert-gptq-to-ggml.py14
1 files changed, 7 insertions, 7 deletions
diff --git a/convert-gptq-to-ggml.py b/convert-gptq-to-ggml.py
index 860eb148..42e99c2f 100644
--- a/convert-gptq-to-ggml.py
+++ b/convert-gptq-to-ggml.py
@@ -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()