lmstudiofixed/tools/hauhaucs-gguf/remove_gguf_thinking.py

import struct
import sys

src = r'Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-NoThink-Q4_K_M.gguf'
if len(sys.argv) > 1:
    src = sys.argv[1]

with open(src, 'rb') as f:
    data = bytearray(f.read())

key = b'tokenizer.chat_template'
kp = data.find(key)
kl = struct.unpack('<Q', data[kp-8:kp])[0]
sl = struct.unpack('<Q', data[kp+kl+4:kp+kl+12])[0]
sp = kp + kl + 12
template = data[sp:sp+sl].decode('utf-8').rstrip(' ')

old = (
    "{%- if add_generation_prompt %}\n"
    "    {{- '<|im_start|>assistant\\n' }}\n"
    "    {%- if enable_thinking is defined and enable_thinking is false %}\n"
    "        {{- '<think>\\n\\n</think>\\n\\n' }}\n"
    "    {%- else %}\n"
    "        {{- '<think>\\n' }}\n"
    "    {%- endif %}\n"
    "{%- endif %}"
)
new = (
    "{%- if add_generation_prompt %}\n"
    "    {{- '<|im_start|>assistant\\n' }}\n"
    "    {{- '<think>\\n\\n</think>\\n\\n' }}\n"
    "{%- endif %}"
)

if old in template:
    template = template.replace(old, new)
    new_bytes = template.encode('utf-8')
    if len(new_bytes) > sl:
        print("ERROR: New template longer than original")
        exit(1)
    padded = new_bytes + b' ' * (sl - len(new_bytes))
    data[sp:sp+sl] = padded
    with open(src, 'wb') as f:
        f.write(data)
    print("Done: enable_thinking conditional removed, forced empty think block")
else:
    print("No enable_thinking conditional found in template")
    idx = template.find('enable_thinking')
    if idx >= 0:
        print("Found at position", idx)
        print(template[idx-50:idx+200])