Update README.md

README.md

@@ -33,167 +33,58 @@ This is the model card of a 🤗 transformers model that has been pushed on the
 - **Paper [optional]:** [More Information Needed]
 - **Demo [optional]:** [More Information Needed]
 
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
+# full_model_comparison.py
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+from peft import PeftModel
+import torch
+
+# ---------------------------
+# 1. Model setup
+# ---------------------------
+base_model_name = "microsoft/Phi-4-mini-instruct"
+lora_model_name = "JeloH/phi4_src_lora"
+
+# Load tokenizer
+tokenizer = AutoTokenizer.from_pretrained(base_model_name)
+
+# Load base model
+base_model = AutoModelForCausalLM.from_pretrained(base_model_name)
+
+# Load fine-tuned LoRA model
+finetuned_model = PeftModel.from_pretrained(base_model, lora_model_name)
+
+# ---------------------------
+# 2. Define prompts
+# ---------------------------
+prompts = [
+    "Translate the following assembly code to high-level source code. input: push    ebp\nmov     ebp, esp\nsub     esp, 3Ch\nmov     eax, ___security_cookie\nxor     eax, ebp\nmov     [ebp+var_4], eax\npush    ebx\npush    esi\npush    edi\npush    0; hWnd\ncall    ds:GetDC\nmov     edi, eax\npush    edi; hdc\ncall    ds:CreateCompatibleDC\nmov     esi, ds:GetSystemMetrics\npush    0; nIndex\nmov     [ebp+hdc], eax\ncall    esi ; GetSystemMetrics\npush    1; nIndex\nmov     [ebp+var_38], eax\ncall    esi ; GetSystemMetrics\nmov     esi, [ebp+var_38]\nmov     ebx, eax\npush    0; offset\npush    0; hSection\nlea     eax, [ebp+ppvBits]\nmov     [ebp+ppvBits], 0\npush    eax; ppvBits\npush    0; usage\nxorps   xmm0, xmm0\nmov     [ebp+pbmi.bmiHeader.biSize], 2Ch ; ','\nlea     eax, [ebp+pbmi]\nmovq    qword ptr [ebp+pbmi.bmiHeader.biClrImportant], xmm0\nmovups  xmmword ptr [ebp+pbmi.bmiHeader.biWidth], xmm0\npush    eax; pbmi\npush    edi; hdc\nmovups  xmmword ptr [ebp+pbmi.bmiHeader.biSizeImage], xmm0\nmov     dword ptr [ebp+pbmi.bmiHeader.biPlanes], 200001h\nmov     [ebp+pbmi.bmiHeader.biWidth], esi\nmov     [ebp+pbmi.bmiHeader.biHeight], ebx\ncall    ds:CreateDIBSection\npush    eax; h\npush    [ebp+hdc]; hdc\ncall    ds:SelectObject\nmov     edi, ebx\nimul    edi, esi\nnop     dword ptr [eax+00h]\npush    0; hWnd\ncall    ds:GetDC\npush    0CC0020h; rop\npush    0; y1\npush    0; x1\nmov     esi, eax\npush    esi; hdcSrc\npush    ebx; cy\npush    [ebp+var_38]; cx\npush    0; y\npush    0; x\npush    [ebp+hdc]; hdc\ncall    ds:BitBlt\nxor     eax, eax\ntest    edi, edi\njle     short loc_40127F\nnop     dword ptr [eax+eax+00h]\nmov     ecx, [ebp+ppvBits]\nadd     dword ptr [ecx+eax*4], 0E1h\ninc     eax\ncmp     eax, edi\njl      short loc_401270\npush    0CC0020h; rop\npush    0Ah; y1\npush    0; x1\npush    [ebp+hdc]; hdcSrc\npush    ebx; cy\npush    [ebp+var_38]; cx\npush    0; y\npush    0; x\npush    esi; hdc\ncall    ds:BitBlt\npush    0CC0020h; rop\nmov     eax, 0Ah\nsub     eax, ebx\npush    eax; y1\npush    0; x1\npush    [ebp+hdc]; hdcSrc\npush    ebx; cy\npush    [ebp+var_38]; cx\npush    0; y\npush    0; x\npush    esi; hdc\ncall    ds:BitBlt\npush    64h ; 'd'; dwMilliseconds\ncall    ds:Sleep\npush    esi; hDC\npush    0; hWnd\ncall    ds:ReleaseDC\npush    esi; hdc\ncall    ds:DeleteDC\njmp     loc_40124",
+    "Write a short story about a robot learning emotions."]
+
+# ---------------------------
+# 3. Generate outputs
+# ---------------------------
+def generate_text(model, tokenizer, prompt, max_length=1000):
+    input_ids = tokenizer(prompt, return_tensors="pt").input_ids
+    output_ids = model.generate(input_ids, max_length=max_length, do_sample=True, temperature=0.7)
+    return tokenizer.decode(output_ids[0], skip_special_tokens=True)
+
+# ---------------------------
+# 4. Run comparison
+# ---------------------------
+for i, prompt in enumerate(prompts, 1):
+    print(f"\n=== Prompt {i} ===")
+    print(f"Prompt: {prompt}\n")
+
+    base_output = generate_text(base_model, tokenizer, prompt)
+    print("Base Model Output:")
+    print(base_output)
+    print("\nFine-Tuned LoRA Model Output:")
+    ft_output = generate_text(finetuned_model, tokenizer, prompt)
+    print(ft_output)
+    print("="*60)
+
+
+
+
+ 
 [More Information Needed]