Llama-3.1-Amelia-FD-8B-v1

Model Information

This model was fine-tuned from the meta-llama/Llama-3.1-8B-Instruct LLM for the task of Fallacies classification

• Developed by: Henri Savigny 
• Funded by: University Claude Bernard, Lyon 1 - Project AMELIA 

Model Sources 

• Github repository: https://github.com/brunoyun/amelia
• Paper: TBC

How to Get Started with the Model

The model use with a temperature of 1.5 and a min p sampling of 0.1

Using Unsloth

from unsloth import FastLanguageModel
from transformers import TextStreamer

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name=f'brunoyun/Llama-3.1-Amelia-FD-8B-v1',
    max_seq_length=2048,
    dtype=None,
    load_in_4bit=False,
    gpu_memory_utilization=0.6,
)

FastLanguageModel.for_inference(model)

messages = [{'role': 'system', 'content': 'You are an expert in argumentation. Your task is to determine the type of fallacy in the given [SENTENCE]. The fallacy would be in the [FALLACY] Set. Utilize the [TITLE] and the [FULL TEXT] as context to support your decision.\nYour answer must be in the following format with only the fallacy in the answer section:\n<|ANSWER|><answer><|ANSWER|>.'}, {'role': 'user', 'content': "[FALLACY]: {'appeal to ridicule', 'none', 'appeal to worse problems', 'straw man', 'causal oversimplification', 'guilt by association', 'false analogy', 'ad hominem', 'appeal to authority', 'appeal to fear', 'appeal to tradition', 'slippery slope', 'circular reasoning', 'ad populum', 'hasty generalization', 'false dilemma', 'equivocation', 'appeal to nature', 'appeal to majority', 'false causality'}\n[TITLE]: Cats, crows and planet Earth: drawings by Belarusian political prisoners\n[SENTENCE]:  Belarus doesn't operate under the laws of the USA or something. If people were found guilty of whatever crimes and find themselves in prison, that is by definition lawful, whether we like the laws in question or not. We should criticize the bad laws for being bad laws and refrain from politically charged and inaccurate language. I think that is the best path towards ensuring the system is just.\n[FULL TEXT]: How can you say that without fully knowing the laws of another county? What is illegal here may be legal there. Belarus doesn't operate under the laws of the USA or something. If people were found guilty of whatever crimes and find themselves in prison, that is by definition lawful, whether we like the laws in question or not. We should criticize the bad laws for being bad laws and refrain from politically charged and inaccurate language. I think that is the best path towards ensuring the system is just.\n"}]

txt_streamer = TextStreamer(tokenizer, skip_prompt=True)

txt = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt",
).to('cuda')

_ = model.generate(
    txt,
    streamer=txt_streamer,
    max_new_tokens=128,
    pad_token_id=tokenizer.eos_token_id
)

Using LM Studio

To use the GGUF model with LM Studio, you need to set as system prompt, temperature and min_p sampling:

• System prompt : You are an expert in argumentation. Your task is to determine the type of fallacy in the given [SENTENCE]. The fallacy would be in the [FALLACY] Set. Utilize the [TITLE] and the [FULL TEXT] as context to support your decision.\nYour answer must be in the following format with only the fallacy in the answer section:\n<|ANSWER|><answer><|ANSWER|>.
• temperature : 1.5
• min_p sampling : 0.1

or use the following preset:

{
  "name": "Llama 3 V2",
  "inference_params": {
    "input_prefix": "<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n",
    "input_suffix": "<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
    "pre_prompt": "You are an expert in argumentation. Your task is to determine the type of fallacy in the given [SENTENCE]. The fallacy would be in the [FALLACY] Set. Utilize the [TITLE] and the [FULL TEXT] as context to support your decision.\nYour answer must be in the following format with only the fallacy in the answer section:\n<|ANSWER|><answer><|ANSWER|>.",
    "pre_prompt_prefix": "<|start_header_id|>system<|end_header_id|>\n\n",
    "pre_prompt_suffix": "",
    "antiprompt": [
      "<|start_header_id|>",
      "<|eot_id|>"
    ]
  }
}

Training Details

Training Data

This model was trained on 4000 elements sampled from the following datasets:

• CoColofa paper
• MAFALDA paper

The sample used for the training can be accessed from the Github repository.

Training Procedure

We used LoRA with the Unsloth library. 

Training Hyperparameters

• Training regime: Model loaded in 4 bits by Unsloth, LoRA r=16, LoRA alpha=16, batch_size=32, epoch=2. The full training code can be viewed from the Github repository.

Evaluation

Testing Data & Metrics

Testing Data

This model was trained on 800 elements sampled from the following datasets:

• CoColofa paper
• MAFALDA paper

The sample used for the testing can be accessed from the Github repository.

Metrics

To evaluate the argument mining task, we used standard classification metrics: $F1$ score, precision and recall.  In the case of the fallacies detection task, where for a single sentence $s$ there is a set of fallacies identified as true labels $F_s$, we adapted the precision and the recall. Given the sampled testing dataset $T$ with 800 elements (see previous section), we build the multiset $T’$ where sentences are repeated as many times as the number of corresponding true labels. Namely, we have:

$$ T’ = { s_1, \dots, s_n \mid s_i = s, n = |F_s|, s \in T}$$ Given our non-deterministic model $\phi$, we obtain the predictions: $$Y = { \phi(s’) \mid s’ \in T’}$$ The new precision is the fraction of correct predictions among all the predictions, where a prediction is correct if the predicted fallacy belongs to the set of true labels.  $$ Precision = \frac{\sum_{s \in T}   \left( |{ s' \in T'\mid s'=s, \phi(s') \in F_s }| / |F_s| \right) }{|T|}$$ Recall was measured based on the consistency of prediction distribution, i.e., over a series of instances annotated with the same fallacies, the model was expected to generate the corresponding fallacy task with similar frequency. $$Recall = \frac{\sum_{s \in T} \sum_{f \in F_s} \min\left( \frac{|{ s' \in T' \mid \phi(s') = f, s'= s}|}{|F_s|}, \frac{1}{|F_s|}\right)}{|T|}$$

Results

Intended Use

Intended Use Cases

Llama 3.1 is intended for commercial and research use in multiple languages. Instruction tuned text only models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks. The Llama 3.1 model collection also supports the ability to leverage the outputs of its models to improve other models including synthetic data generation and distillation. The Llama 3.1 Community License allows for these use cases. 

Out-of-scope

Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3.1 Community License. Use in languages beyond those explicitly referenced as supported in this model card**.

Bias, Risks, and Limitations

This model is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, its potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of this model, developers should perform safety testing and tuning tailored to their specific applications of the model.