no code yet

README.md

@@ -27,43 +27,7 @@ An uncensored reasoning EXAONE 3.5 model trained on reasoning data. Now with a f
 It has been trained using improved training code, and gives an improved performance.
 Here is what inference code you should use:
 ```py
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-MAX_REASONING_TOKENS = 1024
-MAX_RESPONSE_TOKENS = 512
-
-model_name = "lunahr/thea-pro-2b-100r"
-
-model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto", trust_remote_code=True)
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-
-prompt = "Which is greater 9.9 or 9.11 ??"
-messages = [
-    {"role": "user", "content": prompt}
-]
-
-# Generate reasoning
-input_ids = tokenizer.apply_chat_template(messages, tokenize=False, add_reasoning_prompt=True, return_tensors="pt")
-output = model.generate(
-    input_ids.to("cuda"),
-    eos_token_id=tokenizer.eos_token_id,
-    max_new_tokens=MAX_REASONING_TOKENS,
-    do_sample=False,
-)
-
-print("REASONING: " + tokenizer.decode(output[0]))
-
-# Generate answer
-messages.append({"role": "reasoning", "content": reasoning_output})
-input_ids = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, return_tensors="pt")
-output = model.generate(
-    input_ids.to("cuda"),
-    eos_token_id=tokenizer.eos_token_id,
-    max_new_tokens=MAX_RESPONSE_TOKENS,
-    do_sample=False,
-)
-
-print("REASONING: " + tokenizer.decode(output[0]))
+# DEBUGGING IN PROGRESS, check later
 ```
 
 - **Trained by:** [Piotr Zalewski](https://huggingface.co/lunahr)