Update README.md

README.md

@@ -12,7 +12,9 @@ pipeline_tag: text-generation
 
 # cerbero-7b Italian LLM 🚀 
 
-> 🔥 Attention! The **new** and **more capable** version of **cerbero-7b** is now **available**!
+> 🚀 **New Release**: **cerbero-7b-openchat** our latest SOTA model based on [**openchat3.5**](https://github.com/imoneoi/openchat), delivering performance **on par with** or **superior** to **ChatGPT 3.5**!
+
+> 🔥 The research paper unveiling the secrets behind **cerbero-7b** is now available on [arXiv](https://arxiv.org/abs/2311.15698)!
 
 > 📢 **cerbero-7b** is the first **100% Free** and Open Source **Italian Large Language Model** (LLM) ready to be used for **research** or **commercial applications**.
 
@@ -42,6 +44,7 @@ The Stanford Question Answering Dataset (SQuAD) in Italian (SQuAD-it) is used to
 
 | Model                                        | F1 Score | Exact Match (EM) |
 |----------------------------------------------|--------------|----------------------|
+| **cerbero-7b-openchat**                      | **74.09%**   | **56.0%**            |
 | **cerbero-7b**                               | **72.55%**   | **55.6%**            |
 | Fauno                                        | 44.46%       | 0.00%                |
 | Camoscio                                     | 37.42%       | 0.00%                |
@@ -53,6 +56,7 @@ EVALITA benchmarks assess the model's performance in tasks like toxicity detecti
 
 | Model                                        | Toxicity Detection | Irony Detection | Sentiment Analysis |
 |----------------------------------------------|--------------------|-----------------|--------------------|
+| **cerbero-7b-openchat**                      | **63.33%**         | **69.16%**      | **66.89%**         |
 | **cerbero-7b**                               | **63.04%**         | **48.51%**      | **61.80%**         |
 | Fauno                                        | 33.84%             | 39.17%          | 12.23%             |
 | Camoscio                                     | 38.18%             | 39.65%          | 13.33%             |
@@ -67,11 +71,107 @@ The name "Cerbero," inspired by the three-headed dog that guards the gates of th
   cerbero-7b builds upon the formidable **mistral-7b** as its base model. This choice ensures a robust foundation, leveraging the power and capabilities of a cutting-edge language model.
 
 - **Datasets: Cerbero Dataset** 📚
-  The Cerbero Dataset is a groundbreaking collection specifically curated to enhance the proficiency of cerbero-7b in understanding and generating Italian text. This dataset is a product of an innovative method combining dynamic self-chat mechanisms with advanced Large Language Model (LLM) technology. Refer to the [paper](README.md) for more details.
+  The Cerbero Dataset is a groundbreaking collection specifically curated to enhance the proficiency of cerbero-7b in understanding and generating Italian text. This dataset is a product of an innovative method combining dynamic self-chat mechanisms with advanced Large Language Model (LLM) technology. Refer to the [paper](https://arxiv.org/abs/2311.15698) for more details.
 
 - **Licensing: Apache 2.0** 🕊️
   Released under the **permissive Apache 2.0 license**, cerbero-7b promotes openness and collaboration. This licensing choice empowers developers with the freedom for unrestricted usage, fostering a community-driven approach to advancing AI in Italy and beyond.
 
+## Models 🧬
+
+**cerbero-7b** is available in various flavors, each tailored for specific applications and use cases. Below is a table listing these versions along with their respective training datasets and base models:
+
+| Model Name              | Training Dataset  | Base Model  | Huggingface Model | Llama.cpp and Quantized Model |
+|-------------------------|-------------------|-------------|-------------------|-------------------------------|
+| cerbero-7b              | Cerbero Dataset   | mistral-7b  | [link](https://huggingface.co/galatolo/cerbero-7b) | [link](https://huggingface.co/galatolo/cerbero-7b-gguf) |
+| cerbero-7b-openchat     | Cerbero Dataset   | openchat3.5 | [link](https://huggingface.co/galatolo/cerbero-7b-openchat) | [link](https://huggingface.co/galatolo/cerbero-7b-openchat-gguf) |
+
+
+Each of these models brings its unique strengths to the table, making **cerbero-7b** a versatile tool for both research and commercial applications in the Italian language AI domain.
+
+We are committed to continuously enhancing **cerbero-7b**. Our team plans to keep training and releasing new models as advancements in the 7b SOTA occur. This ensures that **cerbero-7b** remains at the forefront of AI technology, offering the most advanced and efficient solutions in the Italian language AI sector.
+
+If you do not have enough RAM to fit the `float32` model (for example when using Colab) we provide for each model a `float16` version using the `revision="float16"` argument 
+
+```python
+model = AutoModelForCausalLM.from_pretrained("galatolo/cerbero-7b", revision="float16")
+```
+
+## Training Details 🚀
+
+**cerbero-7b** is a **fully fine-tuned** LLM, distinguishing itself from LORA or QLORA fine-tunes. 
+The model is trained on an expansive Italian Large Language Model (LLM) using synthetic datasets generated through dynamic self-chat on a large context window of **8192 tokens**
+
+### Dataset Composition 📊
+
+> 📢 Details on the **Cerbero Dataset** will be updated shortly!
+
+### Training Setup ⚙️
+
+**cerbero-7b** is trained on an NVIDIA DGX H100:
+
+- **Hardware:** Utilizing 8xH100 GPUs, each with 80 GB VRAM. 🖥️
+- **Parallelism:** DeepSpeed Zero stage 1 parallelism for optimal training efficiency.✨
+
+The model has been trained for **1 epoch**, ensuring a convergence of knowledge and proficiency in handling diverse linguistic tasks.
+
+## Getting Started 🚀
+
+You can load **cerbero-7b** (or **cerbero-7b-openchat**) using [🤗transformers](https://huggingface.co/docs/transformers/index)
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("galatolo/cerbero-7b")
+tokenizer = AutoTokenizer.from_pretrained("galatolo/cerbero-7b")
+
+prompt = """Questa è una conversazione tra un umano ed un assistente AI.
+[|Umano|] Come posso distinguere un AI da un umano?
+[|Assistente|]"""
+
+input_ids = tokenizer(prompt, return_tensors='pt').input_ids
+with torch.no_grad():
+    output_ids = model.generate(input_ids, max_new_tokens=128)
+
+generated_text = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+print(generated_text)
+```
+
+### GGUF and llama.cpp
+
+**cerbero-7b** is fully **compatibile** with [llama.cpp](https://github.com/ggerganov/llama.cpp)
+
+You can find the **original** and **quantized** versions of **cerbero-7b** in the `gguf` format [here](https://huggingface.co/galatolo/cerbero-7b-gguf/tree/main)
+
+```python
+from llama_cpp import Llama
+from huggingface_hub import hf_hub_download  
+
+llm = Llama(
+    model_path=hf_hub_download(
+        repo_id="galatolo/cerbero-7b-gguf",
+        filename="ggml-model-f16.gguf",
+    ),
+    n_ctx=4086,
+) 
+
+llm.generate("""Questa è una conversazione tra un umano ed un assistente AI.
+[|Umano|] Come posso distinguere un AI da un umano?
+[|Assistente|]""")
+```
+
+## Citation 📖
+
+If you use **cerbero-7b** in your research, please cite our paper:
+
+```bibtex
+@article{galatolo2023cerbero,
+  title={Cerbero-7B: A Leap Forward in Language-Specific LLMs Through Enhanced Chat Corpus Generation and Evaluation},
+  author={Galatolo, Federico A and Cimino, Mario GCA},
+  journal={arXiv preprint arXiv:2311.15698},
+  year={2023}
+}
+```
 ## Training Details 🚀
 
 **cerbero-7b** is a **fully fine-tuned** LLM, distinguishing itself from LORA or QLORA fine-tunes.