Upload folder using huggingface_hub

README.md

@@ -0,0 +1,41 @@
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "minpeter/Llama-3.2-1B-chatml-tool-v3"
+
+model = AutoModelForCausalLM.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+input_text = """
+<|im_start|>system
+You are a function calling AI model. You are provided with function signatures within <tools> </tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions.
+<tools>
+[{"function": {"description": "Get the current weather in a given location", "name": "get_current_weather", "parameters": {"properties": {"location": {"description": "The city and state, e.g. San Francisco, CA", "type": "string"}, "unit": {"enum": ["celsius", "fahrenheit"], "type": "string"}}, "required": ["location"], "type": "object"}}, "type": "function"}]
+</tools>
+For each function call return a json object with function name and arguments within <tool_call> </tool_call> tags with the following schema:
+<tool_call>
+{'arguments': <args-dict>, 'name': <function-name>}
+</tool_call><|im_end|>
+<|im_start|>user
+What is the weather like in Boston?<|im_end|>
+<|im_start|>assistant
+"""
+
+input_length = len(tokenizer.tokenize(input_text))
+
+input_ids = tokenizer.encode(input_text, return_tensors="pt")
+
+output = model.generate(input_ids, max_new_tokens=600)
+generated_ids = output[0][input_length:]
+
+generated_text = tokenizer.decode(generated_ids, skip_special_tokens=True)
+
+tokens = tokenizer.tokenize(generated_text)
+token_ids = tokenizer.convert_tokens_to_ids(tokens)
+
+for token, id in zip(tokens, token_ids):
+    print(f"Token: {token:20} ID: {id}")
+
+print(f"\nGenerated text:\n{generated_text}")
+```