Views
No views yet
transformers.1input_example=
2{
3 "query": "Track crosschain message verification, implement timeout recovery procedures.",
4 "tools": [
5 {"type": "function", "function": {"name": "track_crosschain_message", "description": "Track the status of a crosschain message", "parameters": {"type": "object", "properties": {"message_id": {"type": "string"}}}}},
6 {"type": "function", "function": {"name": "schedule_timeout_check", "description": "Schedule a timeout check for a message", "parameters": {"type": "object", "properties": {"message_id": {"type": "string"}, "timeout": {"type": "integer"}}}}}
7 ]
8}
91from transformers import AutoModelForCausalLM, AutoTokenizer
2import json
3
4model_name = "flock-io/Flock_Web3_Agent_Model"
5model = AutoModelForCausalLM.from_pretrained(
6 model_name,
7 torch_dtype="auto",
8 device_map="auto"
9)
10tokenizer = AutoTokenizer.from_pretrained(model_name)
11
12messages = [
13 {"role": "system", "content": "You are a helpful assistant with access to the following functions. Use them if required -"
14 + json.dumps(input_example["tools"], ensure_ascii=False)},
15 {"role": "user", "content": input_example["query"]}
16]
17text = tokenizer.apply_chat_template(
18 messages,
19 tokenize=False,
20 add_generation_prompt=True
21)
22model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
23generated_ids = model.generate(
24 **model_inputs,
25 max_new_tokens=3000
26)
27generated_ids = [
28 output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
29]
30response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0][
{"name": "track_crosschain_message", "arguments": {"message_id": "msg12345"}},
{"name": "schedule_timeout_check", "arguments": {"message_id": "msg12345", "timeout": "30"}}
]