Upload README.md with huggingface_hub

README.md

@@ -21,8 +21,16 @@ pipeline_tag: text-generation
 Fine-tuned [FunctionGemma 270M](https://huggingface.co/unsloth/functiongemma-270m-it) LoRA adapter
 specialized for **general tool/function calling**.
 
+| | Link |
+|---|---|
+| **Source code** | [tech-sumit/tool-agent](https://github.com/tech-sumit/tool-agent) |
+| **Blog post** | [sumitagrawal.dev/blog/finetuning-functiongemma-270m-tool-calling](https://sumitagrawal.dev/blog/finetuning-functiongemma-270m-tool-calling/) |
+| **Base model** | [unsloth/functiongemma-270m-it](https://huggingface.co/unsloth/functiongemma-270m-it) |
+
 ## Benchmark Results
 
+![Benchmark Results](benchmark-results.png)
+
 Evaluated using [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) on 100 held-out general function-calling examples:
 
 | Metric | Base | Fine-tuned | Delta |
@@ -32,20 +40,23 @@ Evaluated using [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluat
 | Negative Rejection | 100.0% | 100.0% | +0.0% |
 | Param Accuracy | 49.0% | 68.9% | **+19.9%** |
 
+End-to-end through the [tool agent](https://github.com/tech-sumit/tool-agent) pipeline: **14% → 57%** tool selection accuracy on a 7-query evaluation.
+
 ## Training
 
-- **Base model**: `unsloth/functiongemma-270m-it`
-- **Method**: LoRA (r=16, alpha=32) via PEFT + TRL SFTTrainer
+- **Base model**: [`unsloth/functiongemma-270m-it`](https://huggingface.co/unsloth/functiongemma-270m-it) (Gemma 3 270M)
+- **Method**: [LoRA](https://arxiv.org/abs/2106.09685) (r=16, alpha=32) via [PEFT](https://huggingface.co/docs/peft) + [TRL](https://huggingface.co/docs/trl) SFTTrainer
 - **Dataset**: 13,000 general function-calling examples
 - **Epochs**: 3
-- **Hardware**: NVIDIA H100 SXM 80GB
+- **Training time**: 25 minutes
+- **Hardware**: NVIDIA H100 SXM 80GB via [vast.ai](https://vast.ai)
 
 ### Data composition
 
 | Source | Examples | Purpose |
 |--------|----------|---------|
-| xlam-function-calling-60k | ~10,000 | General function calling |
-| xlam-irrelevance-7.5k | ~3,000 | Negative examples / refusal |
+| [Salesforce/xlam-function-calling-60k](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k) | ~10,000 | General function calling |
+| [MadeAgents/xlam-irrelevance-7.5k](https://huggingface.co/datasets/MadeAgents/xlam-irrelevance-7.5k) | ~3,000 | Negative examples / refusal |
 | **Total** | **~13,000** | |
 
 ## Usage
@@ -58,22 +69,36 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 
 base = AutoModelForCausalLM.from_pretrained("unsloth/functiongemma-270m-it", torch_dtype="auto")
 model = PeftModel.from_pretrained(base, "sumitagrawal/functiongemma-270m-tool-agent")
+model = model.merge_and_unload()
 tokenizer = AutoTokenizer.from_pretrained("sumitagrawal/functiongemma-270m-tool-agent")
 
-prompt = """<start_of_turn>developer
-You are a helpful assistant with access to the following tools:
-- send_email(to, subject, body): Send an email
-- search_contacts(query): Search contacts by name
-<end_of_turn>
-<start_of_turn>user
-Send an email to John about the meeting tomorrow
-<end_of_turn>
+prompt = """<start_of_turn>user
+You are a model that can do function calling with the following functions
+
+{"name": "get_weather", "description": "Get current weather", "parameters": {"type": "object", "properties": {"city": {"type": "string"}}, "required": ["city"]}}
+{"name": "send_email", "description": "Send an email", "parameters": {"type": "object", "properties": {"to": {"type": "string"}, "subject": {"type": "string"}, "body": {"type": "string"}}, "required": ["to", "subject", "body"]}}
+
+What's the weather in Tokyo?<end_of_turn>
 <start_of_turn>model
 """
 
 inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
-out = model.generate(**inputs, max_new_tokens=128, temperature=0.1)
-print(tokenizer.decode(out[0], skip_special_tokens=False))
+out = model.generate(**inputs, max_new_tokens=128, temperature=0.1, do_sample=True)
+print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
+# <start_function_call>call:get_weather{city:<escape>Tokyo<escape>}<end_function_call>
+```
+
+### With the Tool Agent Server
+
+```bash
+git clone https://github.com/tech-sumit/tool-agent.git
+cd tool-agent
+pip install -e .
+
+TOOL_AGENT_BACKEND=transformers \
+TOOL_AGENT_MODEL=./models/finetuned \
+python -m agent.server
+# Server starts on http://localhost:8888 with REST, WebSocket, MCP, and A2A
 ```
 
 ### With Ollama (GGUF)
@@ -90,7 +115,7 @@ ollama run tool-agent
 The model uses FunctionGemma's native control-token format:
 
 ```
-<start_function_call>call:function_name{param1:<escape>value1<escape>param2:<escape>value2<escape>}<end_function_call>
+<start_function_call>call:function_name{param1:<escape>value1<escape>,param2:<escape>value2<escape>}<end_function_call>
 ```
 
 ## License