Create README.md

README.md

@@ -0,0 +1,75 @@
+---
+license: mit
+datasets:
+- CreitinGameplays/r1_annotated_math-mistral
+- CreitinGameplays/DeepSeek-R1-Distill-Qwen-32B_NUMINA_train_amc_aime-mistral
+language:
+- en
+base_model:
+- mistralai/Mistral-Nemo-Instruct-2407
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+Run the model:
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer
+
+def main():
+    model_id = "CreitinGameplays/Mistral-Nemo-12B-R1-alpha"
+
+    # Load the tokenizer.
+    tokenizer = AutoTokenizer.from_pretrained(model_id, add_eos_token=True)
+
+    # Load the model using bitsandbytes 8-bit quantization if CUDA is available.
+    if torch.cuda.is_available():
+        model = AutoModelForCausalLM.from_pretrained(
+            model_id,
+            load_in_8bit=True,
+            device_map="auto"
+        )
+        device = torch.device("cuda")
+    else:
+        model = AutoModelForCausalLM.from_pretrained(model_id)
+        device = torch.device("cpu")
+
+    # Define the generation parameters.
+    generation_kwargs = {
+        "max_new_tokens": 8192,
+        "do_sample": True,
+        "temperature": 0.8,
+        "top_p": 0.9,
+        "top_k": 40,
+        "repetition_penalty": 1.12,
+        "num_return_sequences": 1,
+        "forced_eos_token_id": tokenizer.eos_token_id,
+        "pad_token_id": tokenizer.eos_token_id
+    }
+
+    print("Enter your prompt (type 'exit' to quit):")
+    while True:
+        # Get user input.
+        user_input = input("Input> ")
+        if user_input.lower().strip() in ("exit", "quit"):
+            break
+
+        # Construct the prompt in your desired format.
+        prompt = f"""
+[INST]You are an AI assistant named Mistral Nemo. Always output your response after </think> block!\n\n{user_input}[/INST]<think>
+"""
+
+        # Tokenize the prompt and send to the selected device.
+        input_ids = tokenizer.encode(prompt, return_tensors="pt", add_special_tokens=True).to(device)
+
+        # Create a new TextStreamer instance for streaming responses.
+        streamer = TextStreamer(tokenizer)
+        generation_kwargs["streamer"] = streamer
+
+        print("\nAssistant Response:")
+        # Generate the text (tokens will stream to stdout via the streamer).
+        outputs = model.generate(input_ids, **generation_kwargs)
+
+if __name__ == "__main__":
+    main()
+```