Add LoRA checkpoint, benchmark results table, and updated README

- checkpoint-25/: LoRA fine-tune checkpoint for Qwen2.5-1.5B-Instruct
(r=8, alpha=32, target q_proj+v_proj, trained on 50-topic CS Q&A data)
- README: Add Benchmark Results table with real numbers from benchmark_cache.json
(Baseline 81.5% acc / 1.46s, RAG 79.9% acc / 4.19s across 50 questions)
- README: Updated project structure to include checkpoint-25/ and run_benchmark.py
- README: Step 4 now shows how to merge LoRA adapter into finetuned_model/

README.md

@@ -57,6 +57,24 @@ Covers CS fundamentals, algorithms, web technologies, databases, and tooling:
 
 ---
 
+## Benchmark Results (n = 50 questions)
+
+| Metric | Baseline LLM | RAG Chatbot | Fine-Tuned | Unit |
+|--------|-------------|-------------|------------|------|
+| Answer Accuracy | 81.5 | 79.9 | — | % |
+| ROUGE-L | 0.216 | 0.291 | — | 0–1 |
+| Groundedness | 0.815 | 0.575 | — | 0–1 |
+| Answer Relevance | 0.720 | 0.768 | — | 0–1 |
+| Faithfulness | 0.216 | 0.172 | — | 0–1 |
+| Hallucination Rate | 0.0 | 6.0 | — | % |
+| Avg Response Time | 1.46 | 4.19 | — | sec |
+| Cost per Query | $0.0020 | $0.0020 | — | USD |
+
+> Fine-Tuned column shows `—` until `finetuned_model/` is placed in the project root (see Setup §4).  
+> Full per-question results are in `data/benchmark_cache.json`.
+
+---
+
 ## Project Structure
 
 ```
@@ -66,10 +84,15 @@ Covers CS fundamentals, algorithms, web technologies, databases, and tooling:
 ├── system2_rag.py                  # FAISS RAG pipeline
 ├── system3_inference.py            # Fine-tuned model inference
 ├── system3_finetune_colab.ipynb    # Qwen2.5 fine-tuning notebook (Colab)
+├── run_benchmark.py                # Standalone script to regenerate benchmark cache
 ├── requirements.txt
+├── checkpoint-25/                  # LoRA fine-tune checkpoint (Qwen2.5-1.5B, r=8, α=32)
+│   ├── adapter_model.safetensors   # Trained LoRA weights
+│   ├── adapter_config.json
+│   └── tokenizer.json / tokenizer_config.json
 ├── data/
 │   ├── reference_answers.json      # 50 Q&A pairs for auto-evaluation
-│   ├── benchmark_cache.json        # Persisted benchmark results (generated on first run)
+│   ├── benchmark_cache.json        # Pre-computed benchmark results (loads on startup)
 │   ├── finetune_data.jsonl         # Training data in ChatML format
 │   ├── faiss_index/                # FAISS vector store (built automatically)
 │   ├── docs/                       # Knowledge base .txt files
@@ -107,13 +130,31 @@ streamlit run demo.py
 
 The FAISS vector store is built automatically on first launch.
 
-### 4. (Optional) Fine-tune the model
+### 4. (Optional) Use the fine-tuned model
+
+A trained LoRA checkpoint is included in `checkpoint-25/`. To activate it for inference:
+
+```bash
+# Merge LoRA adapter into base model and save as finetuned_model/
+python -c "
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+base = AutoModelForCausalLM.from_pretrained('Qwen/Qwen2.5-1.5B-Instruct')
+model = PeftModel.from_pretrained(base, 'checkpoint-25')
+model.merge_and_unload().save_pretrained('finetuned_model')
+AutoTokenizer.from_pretrained('checkpoint-25').save_pretrained('finetuned_model')
+"
+```
+
+Alternatively, open `system3_finetune_colab.ipynb` in Google Colab to retrain from scratch.
 
-Open `system3_finetune_colab.ipynb` in Google Colab, run all cells, then download the resulting `finetuned_model/` folder and place it in the project root.
+### 5. Benchmark results — pre-loaded
 
-### 5. Run the benchmark (once)
+`data/benchmark_cache.json` is included with pre-computed results for all 50 questions. The Analytics tab shows results instantly on startup. To regenerate:
 
-Click **Run Auto-Benchmark** in the Analytics tab. Results are saved to `data/benchmark_cache.json` and displayed permanently on every subsequent app load — no need to re-run.
+```bash
+python run_benchmark.py
+```
 
 ---
 

checkpoint-25/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-1.5B-Instruct
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **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
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-25/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-25/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95ad32357e436c5010a145f4d3112e63be05302f70eb6a185cf869a030147895
+size 4372840

checkpoint-25/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-25/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b1c7b47dacc25704dc6d905d6cfabc8ac0771a14e643a1fbe598644348b0f6e
+size 8812555

checkpoint-25/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69610a701bcb39d3ec8463156b5457e3bd27b4732a2460a17492b205152b6237
+size 14645

checkpoint-25/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:652500b9116ca5d48648b8fc119f3c03e149cea9780a405ddba77469ca31da55
+size 1383

checkpoint-25/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51b5f7b55a43d2101a6b59146fef39ecf82d00ede346ad72ebb6609fa0b9ef0c
+size 1465

checkpoint-25/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4b3fd40ce9345a559acbb2f18d1b0061a94c4197e899ef94f623749188852d8
+size 11422167

checkpoint-25/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-25/trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 25,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.173736333847046,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 1.449178981781006,
+      "step": 10
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.3650461435317993,
+      "learning_rate": 4.8e-05,
+      "loss": 1.2445411682128906,
+      "step": 20
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 25,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 402871340236800.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-25/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b66ecf0437db273e03d6d6b1fe4f5c54801df73d52a5f028f60897bb705926a3
+size 5137