Update README.md

README.md

@@ -1,66 +1,145 @@
 ---
 license: apache-2.0
 base_model: google/functiongemma-270m-it
-tags:
-- function-calling
-- tool-use
-- gemma
-- gemma-270m
-- on-device
-- echo
-- agent
+library_name: transformers
 pipeline_tag: text-generation
+language:
+  - en
+tags:
+  - function-calling
+  - tool-use
+  - on-device
+  - edge
+  - functiongemma
+  - personal-assistant
+  - synthetic-data
+  - safetensors
+model-index:
+  - name: echo-functiongemma-270m
+    results: []
 ---
 
-# ECHO: On-Device OS & System Agent (270M)
+# ECHO FunctionGemma 270M
 
-**ECHO** is an ultra-lightweight, fine-tuned version of **Google's FunctionGemma (270M)** designed to run locally on PCs and edge devices for desktop and OS automation.
+ECHO is a small on-device personal assistant model. It reads a user request and chooses the right tool, with arguments, to carry it out on the local machine. It is a fine-tune of [`google/functiongemma-270m-it`](https://huggingface.co/google/functiongemma-270m-it) and is built to run without a cloud connection on hardware such as a Raspberry Pi 4B (4GB) or a Windows desktop.
 
-### Evaluation Score
-* **Final Exam Grade:** **89 / 100** (First Class / Distinction)
-* **Parameter Count:** 270 Million
-* **VRAM Footprint:** ~500 MB (runs comfortably on any laptop or phone)
+**Creators:** Lakshy M. Chaurasia and Pratigya M. Chaurasia, [Level Play Studio](#).
 
----
+## Model details
 
-### Supported Capabilities (13 Tools)
-1. **`file_manager`**: Full filesystem control (copy, move, delete, list, search files & directories)
-2. **`volume_manager`**: Adjust master system volume, mute, and unmute
-3. **`take_screenshot`**: Capture full screen, active window, or selected regions
-4. **`music_manager`**: Play, pause, skip tracks, and search songs
-5. **`open_application`**: Launch applications, terminals, and software
-6. **`close_application`**: Terminate and close running apps
-7. **`get_current_time`**: Precise system clock queries
-8. **`get_current_date`**: Calendar date, month, and day-of-week lookups
-9. **`get_weather`**: Meteorological reports and forecasts
-10. **`get_system_info`**: Real-time CPU, RAM, and disk diagnostics
-11. **`task_manager`**: Scheduled reminders, to-do lists, and calendar alarms
-12. **`web_search`**: Internet queries for external knowledge
-13. **`response`**: Conversational, non-tool dialogue and chit-chat
+| Item | Value |
+| :--- | :--- |
+| Base model | `google/functiongemma-270m-it` |
+| Parameters | ~270M |
+| Format | Safetensors (`model.safetensors`) |
+| Language | English (Indian English context) |
+| Task | Function calling for personal computer and assistant actions |
+| Intended hardware | Raspberry Pi 4B (4GB), Windows desktop, edge devices |
+| Context | Single-turn tool selection |
 
----
+## Supported tools
+
+The model is trained to call these 10 tools:
+
+| Tool | Purpose |
+| :--- | :--- |
+| `music_manager` | Play, pause, resume, next, previous. Includes classic Indian film and ghazal music. |
+| `get_weather` | Current weather and forecasts for a city or region. |
+| `open_application` | Launch desktop apps, terminals, and utilities. |
+| `close_application` | Close or terminate running apps. |
+| `task_manager` | Create, list, delete, and complete tasks and reminders. |
+| `get_current_time` | Return the local time. |
+| `get_current_date` | Return the date and day of the week. |
+| `get_system_info` | CPU, RAM, disk, and OS diagnostics. |
+| `volume_manager` | Set, mute, unmute, increase, or decrease audio volume (0–100). |
+| `take_screenshot` | Capture the full screen, the active window, or a region. |
+
+## Training data
+
+- **Source:** synthetic. User queries and tool calls were generated with Gemini and checked against the tool schemas before use.
+- **Size:** about 5,200 examples in total, split roughly 90% train and 10% evaluation, stratified by tool.
+- **Format:** each example is a chat with a `developer` message (date, time, day of week, and the tool list), a `user` message, and an `assistant` tool call. Tool lists are shuffled per example.
+- **Coverage:** English only. Indian cities, names, festivals, and Windows paths. Varied styles: formal requests, short voice commands, slang, typos, and multi-sentence commands.
+- **Validation:** arguments must match the schema exactly (names, types, enum values, and the 0–100 volume range). Non-English text and duplicate queries were removed.
+
+## Evaluation
+
+Evaluation uses a held-out split of the synthetic data. Replace the placeholders below with your measured results.
+
+| Metric | Score |
+| :--- | :--- |
+| Tool-name accuracy | `XX.XX%` |
+| Exact-arguments accuracy | `XX.XX%` |
+| Schema-valid calls | `XX.XX%` |
+
+Synthetic evaluation does not show real-world performance. Test on real user phrasings before relying on the model.
 
-### Quickstart / Inference
+## How to use
 
 ```python
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
-model_id = "Lakshychaurasia/echo"
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(
-    model_id, torch_dtype=torch.float32, device_map="auto"
-)
+repo_id = "YOUR_USERNAME/echo-functiongemma-270m"
+tokenizer = AutoTokenizer.from_pretrained(repo_id)
+model = AutoModelForCausalLM.from_pretrained(repo_id, torch_dtype="auto")
+
+tools = [
+    {
+        "type": "function",
+        "function": {
+            "name": "volume_manager",
+            "description": "Adjusts host master audio volume or toggles mute status.",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "action": {"type": "string", "description": "Volume action: 'set', 'mute', 'unmute', 'increase', 'decrease'."},
+                    "level": {"type": "integer", "description": "Integer audio level between 0 and 100."},
+                },
+                "required": ["action"],
+            },
+        },
+    },
+    # Add the other tools from the table above as needed.
+]
 
-# Use FunctionGemma chat template with tools declared
 messages = [
-    {"role": "developer", "content": "You are ECHO, a function-calling agent."},
-    {"role": "user", "content": "Mute the system volume right now"},
+    {"role": "developer", "content": "Current date and time given in YYYY-MM-DDTHH:MM:SS format: 2026-10-18T09:30:00\nDay of week is Sunday\nYou are a model that can do function calling with the following functions\n"},
+    {"role": "user", "content": "Lower the sound to 20 percent"},
 ]
 
-inputs = tokenizer.apply_chat_template(
-    messages, tools=EVAL_TOOLS, add_generation_prompt=True, return_tensors="pt"
-).to(model.device)
+inputs = tokenizer.apply_chat_template(messages, tools=tools, add_generation_prompt=True, return_tensors="pt", return_dict=True)
+output = model.generate(**inputs, max_new_tokens=128)
+print(tokenizer.decode(output[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=False))
+```
+
+Parse the generated tool call and run it through your own tool dispatcher. Do not execute model output directly without checking the tool name and arguments against the schema.
+
+## Limitations
+
+- Trained on synthetic data, so it may miss phrasings and situations that real users write.
+- Supports only the 10 tools listed above. Requests for other tools will not be handled correctly.
+- Single-turn tool selection. It is not trained for long multi-step workflows or for reading tool output in later turns.
+- English only.
+- Music knowledge covers mainly Indian film and ghazal music from about 1950 to 1980. Verify artist and song names for other genres.
+- Argument values such as file paths and times should be checked before any action is taken on the device.
+
+## Safety
+
+ECHO can open and close applications, change system volume, and capture the screen. Run actions through a confirmation step for anything destructive, and never run it with elevated permissions without review.
+
+## Citation
+
+```
+@misc{echo_functiongemma_270m,
+  title  = {ECHO FunctionGemma 270M},
+  author = {Chaurasia, Lakshy M. and Chaurasia, Pratigya M.},
+  year   = {2026},
+  note   = {Level Play Studio}
+}
+```
+
+## License
+
+This model is licensed under the Apache License, Version 2.0. See the [`LICENSE`](LICENSE) file for the full text.
 
-outputs = model.generate(**inputs, max_new_tokens=128)
-print(tokenizer.decode(outputs[0][inputs.shape[1]:]))
+Note: the base model `google/functiongemma-270m-it` is distributed under Google's Gemma terms of use, not Apache 2.0. Those terms may apply to derivative weights, so check them before you rely on Apache 2.0 for this model alone.