File size: 5,751 Bytes
aab8e2a 9e364fd aab8e2a 9e364fd aab8e2a 839a756 aab8e2a 839a756 6f6d8fd 839a756 aab8e2a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 |
---
base_model: meta-llama/Llama-3.2-1B-Instruct
datasets: argilla-warehouse/apigen-smollm-trl-FC
library_name: transformers
model_name: Llama-3.2-1B-Instruct-v2-FC
tags:
- generated_from_trainer
- trl
- sft
licence: license
---
# Model Card for Llama-3.2-1B-Instruct-v2-FC
This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on the [argilla-warehouse/apigen-smollm-trl-FC](https://huggingface.co/datasets/argilla-warehouse/apigen-smollm-trl-FC) dataset.
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
import json
import re
from typing import Optional
from jinja2 import Template
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.utils import get_json_schema
system_prompt = Template("""You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the functions can be used, point it out and refuse to answer.
If the given question lacks the parameters required by the function, also point it out.
You have access to the following tools:
<tools>{{ tools }}</tools>
The output MUST strictly adhere to the following format, and NO other text MUST be included.
The example format is as follows. Please make sure the parameter type is correct. If no function call is needed, please make the tool calls an empty list '[]'.
<tool_call>[
{"name": "func_name1", "arguments": {"argument1": "value1", "argument2": "value2"}},
... (more tool calls as required)
]</tool_call>""")
def prepare_messages(
query: str,
tools: Optional[dict[str, any]] = None,
history: Optional[list[dict[str, str]]] = None
) -> list[dict[str, str]]:
"""Prepare the system and user messages for the given query and tools.
Args:
query: The query to be answered.
tools: The tools available to the user. Defaults to None, in which case if a
list without content will be passed to the model.
history: Exchange of messages, including the system_prompt from
the first query. Defaults to None, the first message in a conversation.
"""
if tools is None:
tools = []
if history:
messages = history.copy()
messages.append({"role": "user", "content": query})
else:
messages = [
{"role": "system", "content": system_prompt.render(tools=json.dumps(tools))},
{"role": "user", "content": query}
]
return messages
def parse_response(text: str) -> str | dict[str, any]:
"""Parses a response from the model, returning either the
parsed list with the tool calls parsed, or the
model thought or response if couldn't generate one.
Args:
text: Response from the model.
"""
pattern = r"<tool_call>(.*?)</tool_call>"
matches = re.findall(pattern, text, re.DOTALL)
if matches:
return json.loads(matches[0])
return text
model_name_llama = "argilla-warehouse/Llama-3.2-1B-Instruct-v2-FC"
model = AutoModelForCausalLM.from_pretrained(model_name_llama, device_map="auto", torch_dtype="auto", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name_llama)
from datetime import datetime
import random
def get_current_time() -> str:
"""Returns the current time in 24-hour format.
Returns:
str: Current time in HH:MM:SS format.
"""
return datetime.now().strftime("%H:%M:%S")
def get_random_number_between(min: int, max: int) -> int:
"""
Gets a random number between min and max.
Args:
min: The minimum number.
max: The maximum number.
Returns:
A random number between min and max.
"""
return random.randint(min, max)
tools = [get_json_schema(get_random_number_between), get_json_schema(get_current_time)]
toolbox = {"get_random_number_between": get_random_number_between, "get_current_time": get_current_time}
query = "Give me a number between 1 and 300"
query = "Can you give me the hour?"
messages = prepare_messages(query, tools=tools)
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
tool_calls = parse_response(result)
# [{'name': 'get_random_number_between', 'arguments': {'min': 1, 'max': 300}}
# Get tool responses
tool_responses = [toolbox.get(tc["name"])(*tc["arguments"].values()) for tc in tool_calls]
# ['07:20:47']
tool_response = get_random_number_between(*tool_calls[0].get("arguments").values())
# 45
```
## Training procedure
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/plaguss/huggingface/runs/kac9pnd7)
This model was trained with SFT.
### Framework versions
- TRL: 0.12.0.dev0
- Transformers: 4.46.0.dev0
- Pytorch: 2.4.1
- Datasets: 3.0.1
- Tokenizers: 0.20.1
## Citations
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
``` |