Update README.md

README.md

@@ -1,9 +1,8 @@
 ---
-base_model: unsloth/qwen2.5-7b-instruct-bnb-4bit
+base_model: Qwen/Qwen2.5-7B-Instruct
 tags:
 - text-generation-inference
 - transformers
-- unsloth
 - qwen2
 - trl
 - sft
@@ -11,13 +10,56 @@ license: apache-2.0
 language:
 - en
 ---
+### Model detail
+Reasoning natural and smarter
+No system prompt training
+LoRA training rank 16 and alpha 16
+Tool calling support
+### Usage:
+```
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 
-# Uploaded  model
+MAX_REASONING_TOKENS = 4096
+MAX_RESPONSE_TOKENS = 1024
 
-- **Developed by:** beyoru
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/qwen2.5-7b-instruct-bnb-4bit
+model_name = "beyoru/ThinkAgain1.4"
 
-This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained(model_name)
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+messages = []
+
+def stream_output(output_text):
+    for char in output_text:
+        print(char, end="", flush=True)
+
+while True:
+    prompt = input("USER: ")
+    
+    messages.append({"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)
+    
+    messages.append({"role": "reasoning", "content": reasoning_output})
+    
+    print("REASONING: ", end="")
+    stream_output(reasoning_output)
+    print()
+    
+    # Generate answer
+    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)
+    
+    messages.append({"role": "assistant", "content": response_output})
+    
+    print("ASSISTANT: ", end="")
+    stream_output(response_output)
+    print()
+```