py : cleanup the code

- use f-strings where possible
- drop first param of encode/decode functions since "utf-8" is the default

Author: prusnak

Diff for: convert-ggml-to-pth.py

@@ -27,9 +27,9 @@ def read_tokens(fin, vocab_size):
         text_len = struct.unpack("i", fin.read(4))[0]
         text_bytes = fin.read(text_len)
         try:
-            text = text_bytes.decode("utf-8")
+            text = text_bytes.decode()
         except UnicodeDecodeError:
-            text = text_bytes.decode("utf-8", "replace")
+            text = text_bytes.decode(errors="replace")
         score = struct.unpack("f", fin.read(4))[0]
         tokens.append((text, score))
     return tokens
@@ -82,7 +82,7 @@ def read_variables(fin):
 
         shape = tuple(struct.unpack("i" * n_dims, fin.read(4 * n_dims)))
         shape = shape[::-1]
-        name = fin.read(name_length).decode("utf-8")
+        name = fin.read(name_length).decode()
 
         # ensure tensor data is aligned
         tensor_data_offset = fin.tell()
@@ -199,19 +199,19 @@ def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, stops
     device = torch.device("cpu")
     llama = llama.to(device)
 
-    ctx = """You are AI. 
+    ctx = """You are AI.
 This is a dialog, where User interacts with AI. AI is helpful, kind, obedient, honest, respectful, direct, concise, should try to protect User's privacy, and knows its own limits. Also, AI must answer User and AI cannot stop the conversation by itself.
 User: Hello, AI.
 AI: Hello! How can I assist you today?
 """
     print(ctx.rstrip("\n"))
     while True:
         print("-" * 60)
-        prompt = input(f"User: ")
+        prompt = input("User: ")
         if ctx != "":
-            ctx = ctx + "User: " + prompt + "\n"
+            ctx = f"{ctx}User: {prompt}\n"
         else:
-            ctx = prompt + "\nAI:"
+            ctx = f"{prompt}\nAI:"
 
         ctx = (ctx[-1920:]) if len(ctx) >= 2048 else ctx
 
@@ -236,7 +236,7 @@ def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, stops
                 )
             s = generation_output.sequences[0]
             decoded = tokenizer.decode(s)
-            ctx = decoded + "\n"
+            ctx = f"{decoded}\n"
 
 
 def main():

Diff for: convert-gpt4all-to-ggml.py

@@ -49,7 +49,7 @@ def write_header(f_out, header):
 def write_tokens(fout, tokenizer):
     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):
@@ -60,13 +60,13 @@ def write_tokens(fout, tokenizer):
             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)))
 
     # TODO: GPT4All - add extra <pad> token
-    text = "<pad>".encode("utf-8")
+    text = "<pad>".encode()
     fout.write(struct.pack("i", len(text)))
     fout.write(text)
     fout.write(struct.pack("f", 0.0))

Diff for: convert-gptq-to-ggml.py

@@ -50,7 +50,7 @@
 # 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 @@
         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 @@ def convert_q4(src_name, dst_name, permute=False):
 
 fout.close()
 
-print("Done. Output file: " + fname_out)
-print("")
+print(f"Done. Output file: {fname_out}")
+print()

Diff for: convert-pth-to-ggml.py

@@ -120,7 +120,7 @@ def write_header(fout, hparams, ftype):
 def write_tokens(fout, tokenizer):
     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):
@@ -131,7 +131,7 @@ def write_tokens(fout, tokenizer):
             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)))
@@ -191,7 +191,7 @@ def process_and_write_variables(fout, model, ftype, part_id, n_parts):
         fullshape = list(partshape)
         if n_dims > 1:
             fullshape[split_dim] *= n_parts
-        sname = name.encode('utf-8')
+        sname = name.encode()
         fout.write(struct.pack("iii", n_dims, len(sname), ftype_cur))
         for dim in reversed(fullshape):
             fout.write(struct.pack("i", dim))
@@ -268,7 +268,25 @@ def main():
             process_and_write_variables(fout, model, ftype, part_id, n_parts)
             del model
 
+<<<<<<< HEAD
     print(f"Done. Output file: {fname_out}\n")
+=======
+        print(f"Processing part {p+1} of {n_parts}\n")
+
+        fname_model = f"{dir_model}/consolidated.0{p}.pth"
+        fname_out = f"{dir_model}/ggml-model-{ftype_str[ftype]}.bin{'' if p == 0 else f'.{p}'}"
+
+        model = torch.load(fname_model, map_location="cpu")
+
+        with open(fname_out, "wb") as fout:
+            write_header(fout, hparams, ftype)
+            write_tokens(fout, tokenizer)
+            process_and_write_variables(fout, model, ftype)
+
+        del model
+
+        print(f"Done. Output file: {fname_out}, (part {p})\n")
+>>>>>>> 33a6544 (py : cleanup the code)
 
 if __name__ == "__main__":
     main()

Diff for: convert-unversioned-ggml-to-ggml.py

@@ -44,7 +44,7 @@ def write_header(f_out, header):
 def write_tokens(fout, tokenizer):
     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):
@@ -55,7 +55,7 @@ def write_tokens(fout, tokenizer):
             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)))

Diff for: migrate-ggml-2023-03-30-pr613.py

@@ -272,13 +272,11 @@ def main():
         tokens = read_tokens(fin, hparams)
 
     if hparams['magic'] == 0x67676a74:  # ggjt
-        print("%s: input ggml has already been converted to 'ggjt' magic\n" %
-              (args.fin_path))
+        print(f"{args.fin_path}: input ggml has already been converted to 'ggjt' magic\n")
         sys.exit(1)
 
     if hparams['magic'] != 0x67676d66:  # ggmf
-        print("%s: input ggml file doesn't have expected 'ggmf' magic: %#x\n" %
-              (args.fin_path, hparams['magic']))
+        print(f"{args.fin_path}: input ggml file doesn't have expected 'ggmf' magic: {hparams['magic']:#x}\n")
         sys.exit(1)
 
     hparams['magic'] = 0x67676a74  # ggjt

Diff for: quantize.py

@@ -75,7 +75,7 @@ def main():
         )
 
         if not os.path.isfile(f16_model_path_base):
-            print(f'The file %s was not found' % f16_model_path_base)
+            print(f"The file {f16_model_path_base} was not found")
             sys.exit(1)
 
         f16_model_parts_paths = map(