---
license: bigscience-bloom-rail-1.0
datasets:
- Anthropic/hh-rlhf
language:
- en
- fr
---

### bloomz-3b-dpo-chat Model Card


**Model Overview**

The bloomz-3b-dpo-chat is a conversational model fine-tuned using Direct Preference Optimization (DPO) from the base bloomz-3b-sft-chat model. This model aims to
provide high-quality conversational abilities in both English and French, leveraging the pre-trained strengths of its SFT (Supervised Fine-Tuning) predecessor.

**Parent Model: [bloomz-3b-sft-chat](https://huggingface.co/cmarkea/bloomz-3b-sft-chat)**

---

**Model Description**

The bloomz-3b-dpo-chat model builds upon the solid foundation of the bloomz-3b-sft-chat, which is notable for its chatbot-specific pre-training and efficient
tokenization strategy. The DPO fine-tuning process enhances the model's ability to generate more human-preferred responses in conversational contexts.

**Multilingual Capabilities**

The model was initially trained on both French and English datasets, ensuring high efficiency and performance in these languages. Due to the DPO process and potential
data type changes (from float16 to bfloat16), the model's multilingual capabilities might not be as robust as its SFT predecessor, but fine-tuning can help in restoring
performance in other languages.

**Model Applications**

This model is suitable for chatbot applications, customer service automation, and other conversational AI systems where bilingual (French and English) support is
essential. 


**Dataset**

The training dataset for the bloomz-7b1-mt-dpo-chat model consists of interactions between individuals and third parties, balanced equally between French and English. A
total of 0.9 billion tokens were used, with translations facilitated by the Google Translate API to maintain balance and quality.


**Evaluation**

Evaluation of the model was conducted using the PoLL (Pool of LLM) technique, assessing performance on 100 French questions with scores aggregated from six evaluations
(two per evaluator). The evaluators included GPT-4o, Gemini-1.5-pro, and Claude3.5-sonnet.

**Performance Scores (on a scale of 5):**
| Model                                        | Score   |
|---------------------------------------------:|:--------|
| gpt-4o                                       | 4.13    |
| mistralai/Mixtral-8x7B-Instruct-v0.1         | 3.71    |
| gpt-3.5-turbo                                | 3.66    |
| cmarkea/bloomz-7b1-mt-sft-chat               | 1.69    |
| cmarkea/bloomz-3b-dpo-chat                   | 1.68    |
| cmarkea/bloomz-3b-sft-chat                   | 1.51    |
| croissantllm/CroissantLLMChat-v0.1           | 1.19    |
| cmarkea/bloomz-560m-sft-chat                 | 1.04    |
| OpenLLM-France/Claire-Mistral-7B-0.1         | 0.38    |

The bloomz-3b-dpo-chat model demonstrates improved performance over its SFT counterpart, particularly in zero-shot contexts, making it a competitive choice for
production environments.


**Usage**

To utilize the bloomz-3b-dpo-chat model, format the prompt for chatbot interactions as follows:
```
</s>[human prompt 1]<s>[bot answer 1]</s>[human prompt 2]<s>
```
Example code to load the model using HuggingFace's pipeline:

```python
from transformers import pipeline

model = pipeline("text-generation", "cmarkea/bloomz-3b-dpo-chat")
result = model("</s>C'est quoi le deep learning ?<s>", max_new_tokens=512)

result
[{'generated_text': "</s>C'est quoi le deep learning ?<s>L'apprentissage
   en profondeur est un sous-ensemble de l'apprentissage automatique qui
   utilise des réseaux de neurones artificiels pour apprendre à partir de
   données. Ces réseaux sont conçus pour reconnaître des modèles dans les
   données et peuvent être utilisés pour des tâches telles que la reconnaissance
   d'images, le traitement du langage naturel et la reconnaissance vocale."}]
```


**Citation**

```bibtex
@online{DeBloomzChat,
  AUTHOR = {Cyrile Delestre},
  URL = {https://huggingface.co/cmarkea/bloomz-3b-dpo-chat},
  YEAR = {2024},
  KEYWORDS = {NLP ; Transformers ; LLM ; Bloomz},
}
```