Reasoning-2.6-fixed

This is a Remake, refined and better version of the KingNish Reasoning model.

pip install -U bitsandbytes

pip install -U transformers

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM

MAX_REASONING_TOKENS = 1024
MAX_RESPONSE_TOKENS = 512

model = AutoModelForCausalLM.from_pretrained("Guilherme34/Reasoning-2.6", token="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")

tokenizer = AutoTokenizer.from_pretrained("Guilherme34/Reasoning-2.6")

prompt = "hey, how are you?"
messages = [
    {"role": "user", "content": prompt}
]

# Generate reasoning
reasoning_template = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True)
reasoning_inputs = tokenizer(reasoning_template, return_tensors="pt").to(model.device)
reasoning_ids = model.generate(**reasoning_inputs, max_new_tokens=MAX_REASONING_TOKENS)
reasoning_output = tokenizer.decode(reasoning_ids[0, reasoning_inputs.input_ids.shape[1]:], skip_special_tokens=True)

# print("REASONING: " + reasoning_output)

# Generate answer
messages.append({"role": "reasoning", "content": reasoning_output})
response_template = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
response_inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
response_ids = model.generate(**response_inputs, max_new_tokens=MAX_RESPONSE_TOKENS)
response_output = tokenizer.decode(response_ids[0, response_inputs.input_ids.shape[1]:], skip_special_tokens=True)

print("ANSWER: " + response_output)